no code implementations • COLING 2022 • Zichu Fei, Xin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang
Existing KBQG models still face two main challenges: (1) Most models often focus on the most relevant part of the answer entity, while neglecting the rest of the subgraph.
no code implementations • ICLR 2019 • Pengfei Liu, Xuanjing Huang
In this paper, we describe a general framework to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks.
2 code implementations • ACL 2022 • Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, Zhihua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training.
1 code implementation • ACL 2022 • Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, Xuanjing Huang
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
1 code implementation • EMNLP 2020 • Siyuan Wang, Zhongyu Wei, Zhihao Fan, Zengfeng Huang, Weijian Sun, Qi Zhang, Xuanjing Huang
Human evaluation also proves that our model is able to generate relevant and informative questions.
no code implementations • EMNLP 2020 • Qinzhuo Wu, Qi Zhang, Jinlan Fu, Xuanjing Huang
With the advancements in natural language processing tasks, math word problem solving has received increasing attention.
1 code implementation • COLING 2022 • Lei Chen, Guanying Li, Zhongyu Wei, Yang Yang, Baohua Zhou, Qi Zhang, Xuanjing Huang
Existing works on rumor resolution have shown great potential in recognizing word appearance and user participation.
no code implementations • COLING 2022 • Rui Zheng, Rong Bao, Qin Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
no code implementations • COLING 2022 • Zhichao Geng, Ming Zhong, Zhangyue Yin, Xipeng Qiu, Xuanjing Huang
For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed.
1 code implementation • COLING 2022 • Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
no code implementations • Findings (ACL) 2022 • Jianhan Xu, Cenyuan Zhang, Xiaoqing Zheng, Linyang Li, Cho-Jui Hsieh, Kai-Wei Chang, Xuanjing Huang
Most of the existing defense methods improve the adversarial robustness by making the models adapt to the training set augmented with some adversarial examples.
1 code implementation • COLING 2022 • Xin Zhou, Ruotian Ma, Yicheng Zou, Xuanting Chen, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu
Specifically, we re-formulate both token and sentence classification tasks into a unified language modeling task, and map label spaces of different tasks into the same vocabulary space.
no code implementations • 5 May 2024 • Jun Zhao, Jingqi Tong, Yurong Mou, Ming Zhang, Qi Zhang, Xuanjing Huang
In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning.
no code implementations • 1 May 2024 • Shihan Dou, Yan Liu, Enyu Zhou, Tianlong Li, Haoxiang Jia, Limao Xiong, Xin Zhao, Junjie Ye, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
These two issues can be united as a challenge posed by the shifted distribution of the environment.
1 code implementation • 18 Apr 2024 • Jie Wang, Tao Ji, Yuanbin Wu, Hang Yan, Tao Gui, Qi Zhang, Xuanjing Huang, Xiaoling Wang
Generalizing to longer sentences is important for recent Transformer-based language models.
1 code implementation • 2 Apr 2024 • Mengfei Du, Binhao Wu, Jiwen Zhang, Zhihao Fan, Zejun Li, Ruipu Luo, Xuanjing Huang, Zhongyu Wei
For task completion, the agent needs to align and integrate various navigation modalities, including instruction, observation and navigation history.
1 code implementation • 1 Apr 2024 • wei he, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
The generated demos strategically interpolate between existing demos and the given query, transforming the query from OOD to ID.
no code implementations • 24 Mar 2024 • Rui Zheng, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
We first empirically show that the features of either clean signals or adversarial perturbations are redundant and span in low-dimensional linear subspaces respectively with minimal overlap, and the classical low-dimensional subspace projection can suppress perturbation features out of the subspace of clean signals.
1 code implementation • 18 Mar 2024 • Weikang Zhou, Xiao Wang, Limao Xiong, Han Xia, Yingshuang Gu, Mingxu Chai, Fukang Zhu, Caishuang Huang, Shihan Dou, Zhiheng Xi, Rui Zheng, Songyang Gao, Yicheng Zou, Hang Yan, Yifan Le, Ruohui Wang, Lijun Li, Jing Shao, Tao Gui, Qi Zhang, Xuanjing Huang
This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs.
no code implementations • 17 Mar 2024 • Cenyuan Zhang, Xiaoqing Zheng, Ruicheng Yin, Shujie Geng, Jianhan Xu, Xuan Gao, Changze Lv, Zixuan Ling, Xuanjing Huang, Miao Cao, Jianfeng Feng
Deciphering natural language from brain activity through non-invasive devices remains a formidable challenge.
1 code implementation • 12 Mar 2024 • Jingcong Liang, Rong Ye, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei
How can we construct an automated debate judge to evaluate an extensive, vibrant, multi-turn debate?
1 code implementation • 11 Mar 2024 • Yuhang Lai, Siyuan Wang, Shujun Liu, Xuanjing Huang, Zhongyu Wei
We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences.
no code implementations • 26 Feb 2024 • Yuansen Zhang, Xiao Wang, Zhiheng Xi, Han Xia, Tao Gui, Qi Zhang, Xuanjing Huang
In this paper, drawing inspiration from recent works that LLMs are sensitive to the design of the instructions, we utilize instructions in code style, which are more structural and less ambiguous, to replace typically natural language instructions.
no code implementations • 26 Feb 2024 • Xinyi Mou, Zhongyu Wei, Xuanjing Huang
Simulating the response of the public and forecasting the potential impact has become increasingly important.
1 code implementation • 26 Feb 2024 • Huijie Lv, Xiao Wang, Yuansen Zhang, Caishuang Huang, Shihan Dou, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs).
no code implementations • 23 Feb 2024 • Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Jianhao Zhu, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters.
no code implementations • 22 Feb 2024 • Junjie Ye, Nuo Xu, Yikun Wang, Jie zhou, Qi Zhang, Tao Gui, Xuanjing Huang
To overcome the limitations of existing data augmentation methods that compromise semantic integrity and address the uncertainty inherent in LLM-generated text, we leverage the distinctive characteristics of the NER task by augmenting the original data at both the contextual and entity levels.
no code implementations • 22 Feb 2024 • Zhihao Zhang, Jun Zhao, Qi Zhang, Tao Gui, Xuanjing Huang
Furthermore, this core region exhibits significant dimensional dependency, perturbations to even a single parameter on specific dimensions leading to a loss of linguistic competence.
no code implementations • 22 Feb 2024 • Siyin Wang, Jie zhou, Qin Chen, Qi Zhang, Tao Gui, Xuanjing Huang
Domain adaption has been widely adapted for cross-domain sentiment analysis to transfer knowledge from the source domain to the target domain.
1 code implementation • 22 Feb 2024 • Ningyu Xu, Qi Zhang, Menghan Zhang, Peng Qian, Xuanjing Huang
Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference.
no code implementations • 20 Feb 2024 • Xinnong Zhang, Haoyu Kuang, Xinyi Mou, Hanjia Lyu, Kun Wu, Siming Chen, Jiebo Luo, Xuanjing Huang, Zhongyu Wei
The powerful Large Vision Language Models make it possible to handle a variety of tasks simultaneously, but even with carefully designed prompting methods, the general domain models often fall short in aligning with the unique speaking style and context of social media tasks.
no code implementations • 18 Feb 2024 • Nuo Xu, Jun Zhao, Can Zu, Sixian Li, Lu Chen, Zhihao Zhang, Rui Zheng, Shihan Dou, Wenjuan Qin, Tao Gui, Qi Zhang, Xuanjing Huang
To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations.
1 code implementation • 18 Feb 2024 • Jun Zhao, Can Zu, Hao Xu, Yi Lu, wei he, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks.
1 code implementation • 18 Feb 2024 • Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei, Xuanjing Huang
Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their problem-solving sub-abilities.
no code implementations • 17 Feb 2024 • Siyin Wang, ShiMin Li, Tianxiang Sun, Jinlan Fu, Qinyuan Cheng, Jiasheng Ye, Junjie Ye, Xipeng Qiu, Xuanjing Huang
HAG extends the current paradigm in the text generation process, highlighting the feasibility of endowing the LLMs with self-regulate decoding strategies.
1 code implementation • 16 Feb 2024 • Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang, Songyang Gao, Yilong Wu, Qi Zhang, Tao Gui, Xuanjing Huang
Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios.
1 code implementation • 16 Feb 2024 • Yi Lu, Xin Zhou, wei he, Jun Zhao, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks.
1 code implementation • 8 Feb 2024 • Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, wei he, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
no code implementations • 3 Feb 2024 • Ruotian Ma, Xiaolei Wang, Xin Zhou, Jian Li, Nan Du, Tao Gui, Qi Zhang, Xuanjing Huang
Despite the success, the underlying mechanism of this approach remains unexplored, and the true effectiveness of LLMs as Prompt Optimizers requires further validation.
no code implementations • 2 Feb 2024 • Changze Lv, Yansen Wang, Dongqi Han, Xiaoqing Zheng, Xuanjing Huang, Dongsheng Li
Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, provide a unique pathway for capturing the intricacies of temporal data.
1 code implementation • 2 Feb 2024 • Shihan Dou, Yan Liu, Haoxiang Jia, Limao Xiong, Enyu Zhou, Wei Shen, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Xuanjing Huang, Tao Gui
The advancement of large language models (LLMs) has significantly propelled the field of code generation.
no code implementations • 31 Jan 2024 • Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
Large language models are meticulously aligned to be both helpful and harmless.
no code implementations • 31 Jan 2024 • Wei Chen, Hengxu Lin, Qun Zhang, Xiaojin Zhang, Xiang Bai, Xuanjing Huang, Zhongyu Wei
Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response.
1 code implementation • 30 Jan 2024 • Xiaoran Fan, Tao Ji, Changhao Jiang, Shuo Li, Senjie Jin, Sirui Song, Junke Wang, Boyang Hong, Lu Chen, Guodong Zheng, Ming Zhang, Caishuang Huang, Rui Zheng, Zhiheng Xi, Yuhao Zhou, Shihan Dou, Junjie Ye, Hang Yan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
This technique introduces a fusion network to unify the processing of outputs from different visual experts, while bridging the gap between image encoders and pre-trained LLMs.
Ranked #43 on Visual Question Answering on MM-Vet
1 code implementation • 26 Jan 2024 • Yu Sun, Keyu Chen, Shujie Wang, Qipeng Guo, Hang Yan, Xipeng Qiu, Xuanjing Huang, Dahua Lin
However, these evaluation benchmarks are limited to assessing the instruction-following capabilities, overlooking the fundamental abilities that emerge during the pre-training stage.
1 code implementation • 16 Jan 2024 • Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang
To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning.
no code implementations • 12 Jan 2024 • Tianlong Li, Shihan Dou, Wenhao Liu, Muling Wu, Changze Lv, Xiaoqing Zheng, Xuanjing Huang
To overcome these limitations, we propose a novel jailbreaking approach, named Jailbreaking LLMs through Representation Engineering (JRE).
1 code implementation • 11 Jan 2024 • Binghai Wang, Rui Zheng, Lu Chen, Yan Liu, Shihan Dou, Caishuang Huang, Wei Shen, Senjie Jin, Enyu Zhou, Chenyu Shi, Songyang Gao, Nuo Xu, Yuhao Zhou, Xiaoran Fan, Zhiheng Xi, Jun Zhao, Xiao Wang, Tao Ji, Hang Yan, Lixing Shen, Zhan Chen, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
no code implementations • 2 Jan 2024 • Jun Zhao, Zhihao Zhang, Luhui Gao, Qi Zhang, Tao Gui, Xuanjing Huang
In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks.
1 code implementation • 1 Jan 2024 • Junjie Ye, Guanyu Li, Songyang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Qi Zhang, Tao Gui, Xuanjing Huang
Furthermore, a sole emphasis on outcomes disregards the intricate capabilities essential for LLMs to effectively utilize tools.
no code implementations • 26 Dec 2023 • Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Jianhao Zhu, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness.
1 code implementation • 21 Dec 2023 • Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
The results show the competitiveness of our proposed framework and evaluator in counter-argument generation tasks.
no code implementations • 16 Dec 2023 • Jingyi Zhou, Jie zhou, Jiabao Zhao, Siyin Wang, Haijun Shan, Gui Tao, Qi Zhang, Xuanjing Huang
Few-shot text classification has attracted great interest in both academia and industry due to the lack of labeled data in many fields.
no code implementations • 16 Dec 2023 • Wei Chen, Gang Zhao, Xiaojin Zhang, Xiang Bai, Xuanjing Huang, Zhongyu Wei
Automatic psychological counseling requires mass of professional knowledge that can be found in online counseling forums.
1 code implementation • 15 Dec 2023 • Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, ShiLiang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
no code implementations • 12 Dec 2023 • Yue Zhang, Ming Zhang, Haipeng Yuan, Shichun Liu, Yongyao Shi, Tao Gui, Qi Zhang, Xuanjing Huang
The three crucial questions for LLM evaluation are ``what, where, and how to evaluate''.
1 code implementation • 4 Dec 2023 • Zhangyue Yin, Qiushi Sun, Cheng Chang, Qipeng Guo, Junqi Dai, Xuanjing Huang, Xipeng Qiu
Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique.
1 code implementation • 1 Dec 2023 • Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
In this paper, we propose the Hierarchical Argumentation Graph (Hi-ArG), a new structure to organize arguments.
no code implementations • 2 Nov 2023 • Xin Zhou, Yi Lu, Ruotian Ma, Tao Gui, Qi Zhang, Xuanjing Huang
Specifically, we introduce ``security vectors'', a few new parameters that can be separated from the LLM, to ensure LLM's responses are consistent with the harmful behavior.
no code implementations • 25 Oct 2023 • Tianlong Li, Shihan Dou, Changze Lv, Wenhao Liu, Jianhan Xu, Muling Wu, Zixuan Ling, Xiaoqing Zheng, Xuanjing Huang
Users can utilize UBPL to adjust the probability vectors of predicted words in the decoding phase of LLMs, thus influencing the personality expression of LLMs.
1 code implementation • 23 Oct 2023 • Wei Chen, Qiushi Wang, Zefei Long, Xianyin Zhang, Zhongtian Lu, Bingxuan Li, Siyuan Wang, Jiarong Xu, Xiang Bai, Xuanjing Huang, Zhongyu Wei
We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM.
no code implementations • 23 Oct 2023 • Jun Zhao, Zhihao Zhang, Yide Ma, Qi Zhang, Tao Gui, Luhui Gao, Xuanjing Huang
We have discovered a core region in LLMs that corresponds to linguistic competence, accounting for approximately 1% of the total model parameters.
1 code implementation • 22 Oct 2023 • Xiao Wang, Tianze Chen, Qiming Ge, Han Xia, Rong Bao, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks.
1 code implementation • 19 Oct 2023 • Ningyu Xu, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang
We then propose a meta-learning-based method to learn to align conceptual spaces of different languages, which facilitates zero-shot and few-shot generalization in concept classification and also offers insights into the cross-lingual in-context learning phenomenon.
no code implementations • 18 Oct 2023 • Rui Zheng, Wei Shen, Yuan Hua, Wenbin Lai, Shihan Dou, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Haoran Huang, Tao Gui, Qi Zhang, Xuanjing Huang
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
no code implementations • 17 Oct 2023 • Enyu Zhou, Rui Zheng, Zhiheng Xi, Songyang Gao, Xiaoran Fan, Zichu Fei, Jingting Ye, Tao Gui, Qi Zhang, Xuanjing Huang
Reports of human-like behaviors in foundation models are growing, with psychological theories providing enduring tools to investigate these behaviors.
1 code implementation • 14 Oct 2023 • Junjie Ye, Jie zhou, Junfeng Tian, Rui Wang, Qi Zhang, Tao Gui, Xuanjing Huang
Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars.
no code implementations • 14 Oct 2023 • Yuxin Wang, Xiannian Hu, Quan Gan, Xuanjing Huang, Xipeng Qiu, David Wipf
Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories.
1 code implementation • 10 Oct 2023 • Xiao Wang, Yuansen Zhang, Tianze Chen, Songyang Gao, Senjie Jin, Xianjun Yang, Zhiheng Xi, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xuanjing Huang
In this paper, we introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
no code implementations • 10 Oct 2023 • Tianlong Li, Wenhao Liu, Changze Lv, Jianhan Xu, Cenyuan Zhang, Muling Wu, Xiaoqing Zheng, Xuanjing Huang
Spiking neural networks (SNNs) have demonstrated the capability to achieve comparable performance to deep neural networks (DNNs) in both visual and linguistic domains while offering the advantages of improved energy efficiency and adherence to biological plausibility.
no code implementations • 8 Oct 2023 • Wei Shen, Rui Zheng, WenYu Zhan, Jun Zhao, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
1 code implementation • 4 Oct 2023 • Zejun Li, Ye Wang, Mengfei Du, Qingwen Liu, Binhao Wu, Jiwen Zhang, Chengxing Zhou, Zhihao Fan, Jie Fu, Jingjing Chen, Xuanjing Huang, Zhongyu Wei
Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs).
2 code implementations • 20 Sep 2023 • Shengbin Yue, Wei Chen, Siyuan Wang, Bingxuan Li, Chenchen Shen, Shujun Liu, Yuxuan Zhou, Yao Xiao, Song Yun, Xuanjing Huang, Zhongyu Wei
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
1 code implementation • 14 Sep 2023 • Zhiheng Xi, Wenxiang Chen, Xin Guo, wei he, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, Xuanjing Huang, Tao Gui
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
1 code implementation • 29 Aug 2023 • Changze Lv, Tianlong Li, Jianhan Xu, Chenxi Gu, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
Spiking neural networks (SNNs) offer a promising avenue to implement deep neural networks in a more energy-efficient way.
1 code implementation • 28 Aug 2023 • Zhijie Bao, Wei Chen, Shengze Xiao, Kuang Ren, Jiaao Wu, Cheng Zhong, Jiajie Peng, Xuanjing Huang, Zhongyu Wei
We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.
1 code implementation • 11 Jul 2023 • Rui Zheng, Shihan Dou, Songyang Gao, Yuan Hua, Wei Shen, Binghai Wang, Yan Liu, Senjie Jin, Qin Liu, Yuhao Zhou, Limao Xiong, Lu Chen, Zhiheng Xi, Nuo Xu, Wenbin Lai, Minghao Zhu, Cheng Chang, Zhangyue Yin, Rongxiang Weng, Wensen Cheng, Haoran Huang, Tianxiang Sun, Hang Yan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
1 code implementation • 27 Jun 2023 • Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications.
1 code implementation • 16 Jun 2023 • Yuxin Wang, Quan Gan, Xipeng Qiu, Xuanjing Huang, David Wipf
Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest.
1 code implementation • 8 Jun 2023 • Jun Zhao, Xin Zhao, WenYu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yunwen Chen, Xiang Gao, Xuanjing Huang
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
1 code implementation • 29 May 2023 • Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Xuanjing Huang
Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks.
no code implementations • 26 May 2023 • Wei Chen, Shiqi Wei, Zhongyu Wei, Xuanjing Huang
Symptom diagnosis in medical conversations aims to correctly extract both symptom entities and their status from the doctor-patient dialogue.
1 code implementation • 23 May 2023 • Siyuan Wang, Zhongyu Wei, Meng Han, Zhihao Fan, Haijun Shan, Qi Zhang, Xuanjing Huang
The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.
1 code implementation • 23 May 2023 • Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Tao Gui, Qi Zhang, Xuanjing Huang
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales.
1 code implementation • 21 May 2023 • Limao Xiong, Jie zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan
Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
1 code implementation • 20 May 2023 • Ting Wu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.
no code implementations • 11 May 2023 • Ting Wu, Jingyi Liu, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge.
1 code implementation • 9 May 2023 • Peng Li, Tianxiang Sun, Qiong Tang, Hang Yan, Yuanbin Wu, Xuanjing Huang, Xipeng Qiu
A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it.
no code implementations • 4 May 2023 • Songyang Gao, Shihan Dou, Junjie Shan, Qi Zhang, Xuanjing Huang
Dataset bias, i. e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models.
no code implementations • 18 Mar 2023 • Junjie Ye, Xuanting Chen, Nuo Xu, Can Zu, Zekai Shao, Shichun Liu, Yuhan Cui, Zeyang Zhou, Chao Gong, Yang shen, Jie zhou, Siming Chen, Tao Gui, Qi Zhang, Xuanjing Huang
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities.
no code implementations • 1 Mar 2023 • Xuanting Chen, Junjie Ye, Can Zu, Nuo Xu, Rui Zheng, Minlong Peng, Jie zhou, Tao Gui, Qi Zhang, Xuanjing Huang
The GPT-3. 5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities.
Natural Language Inference Natural Language Understanding +1
1 code implementation • 21 Dec 2022 • Ningyu Xu, Tao Gui, Ruotian Ma, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang
We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.
2 code implementations • 19 Dec 2022 • Zhangyue Yin, Yuxin Wang, Xiannian Hu, Yiguang Wu, Hang Yan, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction.
1 code implementation • 28 Nov 2022 • Zhengfu He, Tianxiang Sun, Kuanning Wang, Xuanjing Huang, Xipeng Qiu
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models.
1 code implementation • 14 Nov 2022 • Zhiheng Xi, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs).
2 code implementations • ACL 2022 • Rui Zheng, Rong Bao, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
1 code implementation • 20 Oct 2022 • Xiangyang Liu, Tianxiang Sun, Xuanjing Huang, Xipeng Qiu
Through extensive experimental results across various tasks and PTMs, we show that LPT can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios while possessing faster training speed and lower memory cost.
1 code implementation • 14 Oct 2022 • Tianxiang Sun, Zhengfu He, Qin Zhu, Xipeng Qiu, Xuanjing Huang
MP2 is a set of combinable prompts pre-trained on 38 Chinese tasks.
1 code implementation • 14 Oct 2022 • Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models.
1 code implementation • 14 Oct 2022 • Tianxiang Sun, Junliang He, Xipeng Qiu, Xuanjing Huang
Automatic evaluation metrics are crucial to the development of generative systems.
1 code implementation • COLING 2022 • Chenxin An, Ming Zhong, Zhiyong Wu, Qin Zhu, Xuanjing Huang, Xipeng Qiu
Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives.
no code implementations • COLING 2022 • Jie zhou, Qi Zhang, Qin Chen, Liang He, Xuanjing Huang
Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing.
1 code implementation • COLING 2022 • Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, Xuanjing Huang
In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.
no code implementations • COLING 2022 • Siyin Wang, Jie zhou, Changzhi Sun, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang
In this work, we propose a causal intervention model for Implicit Sentiment Analysis using Instrumental Variable (ISAIV).
no code implementations • 11 Jun 2022 • Zhihao Fan, Zhongyu Wei, Jingjing Chen, Siyuan Wang, Zejun Li, Jiarong Xu, Xuanjing Huang
These two steps are iteratively performed in our framework for continuous learning.
2 code implementations • 29 May 2022 • Chenxin An, Jiangtao Feng, Kai Lv, Lingpeng Kong, Xipeng Qiu, Xuanjing Huang
We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation.
1 code implementation • 27 May 2022 • Yuxin Wang, Chu-Tak Lee, Qipeng Guo, Zhangyue Yin, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu
Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities.
1 code implementation • 23 May 2022 • Tianxiang Sun, Zhengfu He, Hong Qian, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu
By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment.
1 code implementation • 19 Apr 2022 • Wei Chen, Zhiwei Li, Hongyi Fang, Qianyuan Yao, Cheng Zhong, Jianye Hao, Qi Zhang, Xuanjing Huang, Jiajie Peng, Zhongyu Wei
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
2 code implementations • ACL 2022 • Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
NER model has achieved promising performance on standard NER benchmarks.
Ranked #8 on Named Entity Recognition (NER) on WNUT 2017
1 code implementation • Findings (ACL) 2022 • Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu
Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning.
2 code implementations • COLING 2022 • Shihan Dou, Rui Zheng, Ting Wu, Songyang Gao, Junjie Shan, Qi Zhang, Yueming Wu, Xuanjing Huang
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
1 code implementation • 29 Jan 2022 • Zejun Li, Zhihao Fan, Huaixiao Tou, Jingjing Chen, Zhongyu Wei, Xuanjing Huang
In MVPTR, we follow the nested structure of both modalities to introduce concepts as high-level semantics.
2 code implementations • 10 Jan 2022 • Tianxiang Sun, Yunfan Shao, Hong Qian, Xuanjing Huang, Xipeng Qiu
In such a scenario, which we call Language-Model-as-a-Service (LMaaS), the gradients of PTMs are usually unavailable.
no code implementations • 14 Oct 2021 • Xin Zhou, Ruotian Ma, Tao Gui, Yiding Tan, Qi Zhang, Xuanjing Huang
Specifically, for each task, a label word set is first constructed by selecting a high-frequency word for each class respectively, and then, task-specific vectors are inserted into the inputs and optimized to manipulate the model predictions towards the corresponding label words.
1 code implementation • NAACL 2022 • Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement.
1 code implementation • 6 Oct 2021 • Linyang Li, Demin Song, Ruotian Ma, Xipeng Qiu, Xuanjing Huang
Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems.
1 code implementation • NAACL 2022 • Ruotian Ma, Xin Zhou, Tao Gui, Yiding Tan, Linyang Li, Qi Zhang, Xuanjing Huang
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words.
1 code implementation • 26 Sep 2021 • Tianxiang Sun, Xiangyang Liu, Xipeng Qiu, Xuanjing Huang
In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks.
no code implementations • 12 Sep 2021 • Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Haijun Shan, Xuanjing Huang, Jianqing Fan
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image.
no code implementations • 10 Sep 2021 • Yitao Liu, Tianxiang Sun, Xipeng Qiu, Xuanjing Huang
This one-way interaction leads to the teacher's inability to perceive the characteristics of the student and its training progress.
no code implementations • 19 Aug 2021 • Tong Liu, Siyuan Wang, Jingchao Fu, Lei Chen, Zhongyu Wei, Yaqi Liu, Heng Ye, Liaosa Xu, Weiqiang Wan, Xuanjing Huang
Existing system dealing with online complaint provides a final decision without explanations.
1 code implementation • ACL 2021 • Qinzhuo Wu, Qi Zhang, Zhongyu Wei, Xuanjing Huang
In recent years, math word problem solving has received considerable attention and achieved promising results, but previous methods rarely take numerical values into consideration.
1 code implementation • ACL 2021 • Yi Zhou, Xiaoqing Zheng, Cho-Jui Hsieh, Kai-Wei Chang, Xuanjing Huang
Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples.
no code implementations • ACL 2021 • Xinyi Mou, Zhongyu Wei, Lei Chen, Shangyi Ning, Yancheng He, Changjian Jiang, Xuanjing Huang
In addition, we propose a novel task, namely hashtag usage prediction to model the ideology of legislators on Twitter.
1 code implementation • ACL 2021 • Ruotian Ma, Tao Gui, Linyang Li, Qi Zhang, Yaqian Zhou, Xuanjing Huang
In this work, we propose the use of negative training (NT), in which a model is trained using complementary labels regarding that ``the instance does not belong to these complementary labels".
no code implementations • 21 Jun 2021 • Zhihao Fan, Zhongyu Wei, Siyuan Wang, Ruize Wang, Zejun Li, Haijun Shan, Xuanjing Huang
Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN.
1 code implementation • ACL 2021 • Jinlan Fu, Xuanjing Huang, PengFei Liu
Recent years have seen the paradigm shift of Named Entity Recognition (NER) systems from sequence labeling to span prediction.
1 code implementation • ACL 2021 • Chong Li, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.
1 code implementation • ACL 2021 • Xiaonan Li, Yunfan Shao, Tianxiang Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang
To alleviate this problem, we extend the recent successful early-exit mechanism to accelerate the inference of PTMs for sequence labeling tasks.
no code implementations • 28 May 2021 • Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
In this paper, we show that a novel objective function for the training of the ensemble internal classifiers can be naturally induced from the perspective of ensemble learning and information theory.
1 code implementation • 8 May 2021 • Jiehang Zeng, Xiaoqing Zheng, Jianhan Xu, Linyang Li, Liping Yuan, Xuanjing Huang
Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions.
no code implementations • 17 Apr 2021 • Lu Ji, Jing Li, Zhongyu Wei, Qi Zhang, Xuanjing Huang
Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding.
no code implementations • NAACL 2021 • Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang, PengFei Liu
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks.
1 code implementation • 7 Apr 2021 • Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang
Previous work for text summarization in scientific domain mainly focused on the content of the input document, but seldom considering its citation network.
1 code implementation • NAACL 2021 • Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang
We therefore introduce a new layer named dynamic mask attention network (DMAN) with a learnable mask matrix which is able to model localness adaptively.
Ranked #11 on Machine Translation on WMT2014 English-German
no code implementations • 22 Mar 2021 • Liping Yuan, Jiangtao Feng, Xiaoqing Zheng, Xuanjing Huang
The key idea is that at each time step, the network takes as input a ``bundle'' of similar words predicted at the previous step instead of a single ground truth.
1 code implementation • ACL 2021 • Tao Gui, Xiao Wang, Qi Zhang, Qin Liu, Yicheng Zou, Xin Zhou, Rui Zheng, Chong Zhang, Qinzhuo Wu, Jiacheng Ye, Zexiong Pang, Yongxin Zhang, Zhengyan Li, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Bolin Zhu, Shan Qin, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
no code implementations • 21 Mar 2021 • Zejun Li, Zhongyu Wei, Zhihao Fan, Haijun Shan, Xuanjing Huang
In this paper, we focus on the problem of unsupervised image-sentence matching.
no code implementations • 29 Dec 2020 • Linyang Li, Yunfan Shao, Demin Song, Xipeng Qiu, Xuanjing Huang
The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers.
1 code implementation • EMNLP 2020 • Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, Xuanjing Huang
Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks.
1 code implementation • 14 Dec 2020 • Yicheng Zou, Lujun Zhao, Yangyang Kang, Jun Lin, Minlong Peng, Zhuoren Jiang, Changlong Sun, Qi Zhang, Xuanjing Huang, Xiaozhong Liu
In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.
1 code implementation • 14 Dec 2020 • Yicheng Zou, Jun Lin, Lujun Zhao, Yangyang Kang, Zhuoren Jiang, Changlong Sun, Qi Zhang, Xuanjing Huang, Xiaozhong Liu
Automatic chat summarization can help people quickly grasp important information from numerous chat messages.
no code implementations • 12 Dec 2020 • Yichao Luo, Zhengyan Li, Bingning Wang, Xiaoyu Xing, Qi Zhang, Xuanjing Huang
Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content.
no code implementations • COLING 2020 • Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan, Ruofei Zhang
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts.
no code implementations • COLING 2020 • Lei Chen, Zhongyu Wei, Jing Li, Baohua Zhou, Qi Zhang, Xuanjing Huang
Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately.
no code implementations • 16 Nov 2020 • Jingjing Gong, Hang Yan, Yining Zheng, Xipeng Qiu, Xuanjing Huang
A lot of natural language processing problems need to encode the text sequence as a fix-length vector, which usually involves aggregation process of combining the representations of all the words, such as pooling or self-attention.
1 code implementation • EMNLP 2020 • Jinlan Fu, PengFei Liu, Qi Zhang, Xuanjing Huang
The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Lu Liu, Yi Zhou, Jianhan Xu, Xiaoqing Zheng, Kai-Wei Chang, Xuanjing Huang
The words in each sentence of a source language corpus are rearranged to meet the word order in a target language under the guidance of a part-of-speech based language model (LM).
no code implementations • Findings of the Association for Computational Linguistics 2020 • Minlong Peng, Ruotian Ma, Qi Zhang, Lujun Zhao, Mengxi Wei, Changlong Sun, Xuanjing Huang
In this work, we explore the way to quickly adjust an existing named entity recognition (NER) system to make it capable of recognizing entity types not defined in the system.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yanjian Zhang, Qin Chen, Yiteng Zhang, Zhongyu Wei, Yixu Gao, Jiajie Peng, Zengfeng Huang, Weijian Sun, Xuanjing Huang
Terms contained in Gene Ontology (GO) have been widely used in biology and bio-medicine.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Yiran Chen, PengFei Liu, Ming Zhong, Zi-Yi Dou, Danqing Wang, Xipeng Qiu, Xuanjing Huang
In this paper, we perform an in-depth analysis of characteristics of different datasets and investigate the performance of different summarization models under a cross-dataset setting, in which a summarizer trained on one corpus will be evaluated on a range of out-of-domain corpora.
1 code implementation • COLING 2020 • Tianxiang Sun, Yunfan Shao, Xipeng Qiu, Qipeng Guo, Yaru Hu, Xuanjing Huang, Zheng Zhang
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models.
1 code implementation • ACL 2021 • Zhichao Geng, Hang Yan, Xipeng Qiu, Xuanjing Huang
The joint-model is trained and evaluated on 13 corpora of four tasks, yielding near state-of-the-art (SOTA) performance in dependency parsing and NER, achieving SOTA performance in CWS and POS.
1 code implementation • EMNLP 2020 • Xiaoyu Xing, Zhijing Jin, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang
Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • ACL 2020 • Xiaoqing Zheng, Jiehang Zeng, Yi Zhou, Cho-Jui Hsieh, Minhao Cheng, Xuanjing Huang
Despite achieving prominent performance on many important tasks, it has been reported that neural networks are vulnerable to adversarial examples.
1 code implementation • 20 Jun 2020 • Yi Zhou, Xiaoqing Zheng, Cho-Jui Hsieh, Kai-Wei Chang, Xuanjing Huang
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples.
no code implementations • EMNLP 2020 • Ruize Wang, Duyu Tang, Nan Duan, Wanjun Zhong, Zhongyu Wei, Xuanjing Huang, Daxin Jiang, Ming Zhou
We study the detection of propagandistic text fragments in news articles.
4 code implementations • 29 Apr 2020 • Cheng Zhong, Kangenbei Liao, Wei Chen, Qianlong Liu, Baolin Peng, Xuanjing Huang, Jiajie Peng, Zhongyu Wei
Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • ACL 2020 • Danqing Wang, PengFei Liu, Yining Zheng, Xipeng Qiu, Xuanjing Huang
An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships.
1 code implementation • ACL 2020 • Xiaonan Li, Hang Yan, Xipeng Qiu, Xuanjing Huang
Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information.
Ranked #5 on Chinese Named Entity Recognition on MSRA
Chinese Named Entity Recognition named-entity-recognition +3
2 code implementations • ACL 2020 • Ming Zhong, PengFei Liu, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
Ranked #1 on Text Summarization on BBC XSum
no code implementations • 13 Apr 2020 • Zhen Ke, Liang Shi, Erli Meng, Bin Wang, Xipeng Qiu, Xuanjing Huang
Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework.
no code implementations • The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 • Ruize Wang, Zhongyu Wei, Piji Li, Qi Zhang, Xuanjing Huang
In particular, on the within-image level, we employ a Graph Convolution Network (GCN) to enrich local fine-grained region representations of objects on scene graphs.
Ranked #7 on Visual Storytelling on VIST
3 code implementations • 18 Mar 2020 • Xipeng Qiu, Tianxiang Sun, Yige Xu, Yunfan Shao, Ning Dai, Xuanjing Huang
Recently, the emergence of pre-trained models (PTMs) has brought natural language processing (NLP) to a new era.
1 code implementation • 24 Feb 2020 • Yige Xu, Xipeng Qiu, Ligao Zhou, Xuanjing Huang
Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks.
2 code implementations • Findings (ACL) 2021 • Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Jianshu ji, Guihong Cao, Daxin Jiang, Ming Zhou
We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa.
Ranked #1 on Entity Typing on Open Entity
1 code implementation • 12 Jan 2020 • Jinlan Fu, PengFei Liu, Qi Zhang, Xuanjing Huang
While neural network-based models have achieved impressive performance on a large body of NLP tasks, the generalization behavior of different models remains poorly understood: Does this excellent performance imply a perfect generalization model, or are there still some limitations?
1 code implementation • 17 Dec 2019 • Yi Zhou, Xiaoqing Zheng, Xuanjing Huang
Inspired by a concept of content-addressable retrieval from cognitive science, we propose a novel fragment-based model augmented with a lexicon-based memory for Chinese NER, in which both the character-level and word-level features are combined to generate better feature representations for possible name candidates.
Chinese Named Entity Recognition named-entity-recognition +4
1 code implementation • 18 Nov 2019 • Tao Gui, Lizhi Qing, Qi Zhang, Jiacheng Ye, HangYan, Zichu Fei, Xuanjing Huang
In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task.
1 code implementation • 12 Nov 2019 • Tianxiang Sun, Yunfan Shao, Xiaonan Li, PengFei Liu, Hang Yan, Xipeng Qiu, Xuanjing Huang
Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing.
no code implementations • COLING 2020 • Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically.
Ranked #9 on Visual Storytelling on VIST
1 code implementation • NAACL 2021 • Lu Ji, Zhongyu Wei, Jing Li, Qi Zhang, Xuanjing Huang
In this paper, we focus on extracting interactive argument pairs from two posts with opposite stances to a certain topic.
no code implementations • IJCNLP 2019 • Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, Xuanjing Huang
Recurrent neural networks (RNN) used for Chinese named entity recognition (NER) that sequentially track character and word information have achieved great success.
Ranked #13 on Chinese Named Entity Recognition on OntoNotes 4
Chinese Named Entity Recognition named-entity-recognition +3
no code implementations • IJCNLP 2019 • Di Liang, Fubao Zhang, Qi Zhang, Xuanjing Huang
However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora.
no code implementations • WS 2019 • Ming Zhong, Danqing Wang, PengFei Liu, Xipeng Qiu, Xuanjing Huang
In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models.
no code implementations • 25 Sep 2019 • Jinlan Fu, PengFei Liu, Xuanjing Huang
With the proliferation of models for natural language processing (NLP) tasks, it is even harder to understand the differences between models and their relative merits.
no code implementations • COLING 2020 • Minlong Peng, Qi Zhang, Xuanjing Huang
To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework.
no code implementations • 30 Aug 2019 • Danqing Wang, PengFei Liu, Ming Zhong, Jie Fu, Xipeng Qiu, Xuanjing Huang
Although domain shift has been well explored in many NLP applications, it still has received little attention in the domain of extractive text summarization.
3 code implementations • IJCNLP 2019 • Luyao Huang, Chi Sun, Xipeng Qiu, Xuanjing Huang
Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a particular context.
Ranked #3 on Word Sense Disambiguation on WiC-TSV
2 code implementations • ACL 2020 • Ruotian Ma, Minlong Peng, Qi Zhang, Xuanjing Huang
This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information.
Ranked #8 on Chinese Named Entity Recognition on Resume NER
Chinese Named Entity Recognition named-entity-recognition +2
no code implementations • 25 Jul 2019 • Lin Zehui, PengFei Liu, Luyao Huang, Junkun Chen, Xipeng Qiu, Xuanjing Huang
Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting.
2 code implementations • ACL 2019 • Ming Zhong, PengFei Liu, Danqing Wang, Xipeng Qiu, Xuanjing Huang
The recent years have seen remarkable success in the use of deep neural networks on text summarization.
Ranked #6 on Extractive Text Summarization on CNN / Daily Mail
1 code implementation • ACL 2019 • Zhihao Fan, Zhongyu Wei, Siyuan Wang, Xuanjing Huang
Existing research usually employs the architecture of CNN-RNN that views the generation as a sequential decision-making process and the entire dataset vocabulary is used as decoding space.
no code implementations • ACL 2019 • Zhenqiao Song, Xiaoqing Zheng, Lu Liu, Mu Xu, Xuanjing Huang
It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Xipeng Qiu, Hengzhi Pei, Hang Yan, Xuanjing Huang
Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion.
1 code implementation • ACL 2019 • Minlong Peng, Xiaoyu Xing, Qi Zhang, Jinlan Fu, Xuanjing Huang
In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries.
1 code implementation • 29 May 2019 • Minlong Peng, Qi Zhang, Xiaoyu Xing, Tao Gui, Jinlan Fu, Xuanjing Huang
However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance.
16 code implementations • 14 May 2019 • Chi Sun, Xipeng Qiu, Yige Xu, Xuanjing Huang
Language model pre-training has proven to be useful in learning universal language representations.
Ranked #1 on Text Classification on Yahoo! Answers
4 code implementations • ACL 2019 • Ning Dai, Jianze Liang, Xipeng Qiu, Xuanjing Huang
Disentangling the content and style in the latent space is prevalent in unpaired text style transfer.
1 code implementation • TACL 2020 • Hang Yan, Xipeng Qiu, Xuanjing Huang
Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing.
1 code implementation • NAACL 2019 • Chi Sun, Xipeng Qiu, Xuanjing Huang
Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information.
no code implementations • 21 Nov 2018 • Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi Kit Cheung
Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention.
1 code implementation • 9 Nov 2018 • Tao Gui, Qi Zhang, Lujun Zhao, Yaosong Lin, Minlong Peng, Jingjing Gong, Xuanjing Huang
In recent years, long short-term memory (LSTM) has been successfully used to model sequential data of variable length.
Ranked #34 on Sentiment Analysis on IMDb
no code implementations • WS 2018 • Yunfan Gu, Zhongyu Wei, Maoran Xu, Hao Fu, Yang Liu, Xuanjing Huang
In this paper, we propose to incorporate topic aspects information for online comments convincingness evaluation.
no code implementations • 23 Oct 2018 • Pengfei Liu, Xuanjing Huang
In this paper, we describe a general framework: Parameters Read-Write Networks (PRaWNs) to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks.
no code implementations • EMNLP 2018 • Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang
However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles.
Ranked #2 on Part-Of-Speech Tagging on Ritter
no code implementations • EMNLP 2018 • Jingjing Gong, Xipeng Qiu, Xinchi Chen, Dong Liang, Xuanjing Huang
Attention-based neural models have achieved great success in natural language inference (NLI).
no code implementations • EMNLP 2018 • Yucheng Wang, Zhongyu Wei, Yaqian Zhou, Xuanjing Huang
Automatic essay scoring (AES) is the task of assigning grades to essays without human interference.