no code implementations • COLING 2022 • Kailin Zhao, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng
For the meta learner, it requires a good generalization ability so as to quickly adapt to new tasks.
no code implementations • 2 Apr 2024 • Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng
Therefore, this paper proposes a new task, called class-incremental few-shot event detection.
no code implementations • 2 Apr 2024 • Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
However, limiting perturbations to a single level of granularity may reduce the flexibility of adversarial examples, thereby diminishing the potential threat of the attack.
no code implementations • 2 Apr 2024 • Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng
Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently.
1 code implementation • 28 Mar 2024 • Hengran Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
Retrieval-augmented generation (RAG) is considered to be a promising approach to alleviate the hallucination issue of large language models (LLMs), and it has received widespread attention from researchers recently.
no code implementations • 19 Mar 2024 • Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng
Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the $i$-th docid given the (preceding) top $i-1$ docids.
no code implementations • 12 Mar 2024 • Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Xiang Li, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to $\textbf{12. 5%}$ and $\textbf{21. 9%}$, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively.
no code implementations • 26 Feb 2024 • Jiafeng Guo, Changjiang Zhou, Ruqing Zhang, Jiangui Chen, Maarten de Rijke, Yixing Fan, Xueqi Cheng
Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance.
no code implementations • 21 Feb 2024 • Wanqing Cui, Keping Bi, Jiafeng Guo, Xueqi Cheng
Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge.
1 code implementation • 18 Feb 2024 • Shiyu Ni, Keping Bi, Jiafeng Guo, Xueqi Cheng
This motivates us to enhance the LLMs' ability to perceive their knowledge boundaries to help RA.
no code implementations • 9 Feb 2024 • Lu Chen, Wei Huang, Ruqing Zhang, Wei Chen, Jiafeng Guo, Xueqi Cheng
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
1 code implementation • 8 Jan 2024 • Keping Bi, Xiaojie Sun, Jiafeng Guo, Xueqi Cheng
MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets.
1 code implementation • 16 Dec 2023 • Run-Ze Fan, Yixing Fan, Jiangui Chen, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication.
no code implementations • 16 Dec 2023 • Yu-An Liu, Ruqing Zhang, Mingkun Zhang, Wei Chen, Maarten de Rijke, Jiafeng Guo, Xueqi Cheng
We decompose the robust ranking error into two components, i. e., a natural ranking error for effectiveness evaluation and a boundary ranking error for assessing adversarial robustness.
1 code implementation • 5 Dec 2023 • Xiaojie Sun, Keping Bi, Jiafeng Guo, Sihui Yang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Xueqi Cheng
Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e. g., products with aspects such as category and brand.
no code implementations • 6 Nov 2023 • Yucan Guo, Zixuan Li, Xiaolong Jin, Yantao Liu, Yutao Zeng, Wenxuan Liu, Xiang Li, Pan Yang, Long Bai, Jiafeng Guo, Xueqi Cheng
Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks.
no code implementations • 6 Nov 2023 • Yinqiong Cai, Yixing Fan, Keping Bi, Jiafeng Guo, Wei Chen, Ruqing Zhang, Xueqi Cheng
The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently.
no code implementations • 22 Oct 2023 • Yantao Liu, Zixuan Li, Xiaolong Jin, Yucan Guo, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng
The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base.
1 code implementation • 18 Oct 2023 • Hengran Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.
no code implementations • 18 Oct 2023 • Lulu Yu, Keping Bi, Jiafeng Guo, Xueqi Cheng
The Chinese academy of sciences Information Retrieval team (CIR) has participated in the NTCIR-17 ULTRE-2 task.
1 code implementation • 1 Oct 2023 • Shiyu Ni, Keping Bi, Jiafeng Guo, Xueqi Cheng
In this paper, we aim to conduct a systematic comparative study of various types of training objectives, with different properties of not only whether it is permutation-invariant but also whether it conducts sequential prediction and whether it can control the count of output facets.
no code implementations • 22 Sep 2023 • Zhilei Hu, Zixuan Li, Daozhu Xu, Long Bai, Cheng Jin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations.
1 code implementation • 22 Sep 2023 • Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng
Since existing NEE datasets (e. g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest.
no code implementations • 29 Aug 2023 • Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng
We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds; and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents.
1 code implementation • 24 Aug 2023 • Lu Chen, Ruqing Zhang, Wei Huang, Wei Chen, Jiafeng Guo, Xueqi Cheng
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
1 code implementation • 22 Aug 2023 • Xiaojie Sun, Keping Bi, Jiafeng Guo, Xinyu Ma, Fan Yixing, Hongyu Shan, Qishen Zhang, Zhongyi Liu
Extensive experiments on two real-world datasets (product and mini-program search) show that our approach can outperform competitive baselines both treating aspect values as classes and conducting the same MLM for aspect and content strings.
1 code implementation • 22 Aug 2023 • Yinqiong Cai, Keping Bi, Yixing Fan, Jiafeng Guo, Wei Chen, Xueqi Cheng
First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection.
no code implementations • 19 Aug 2023 • Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng
The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query.
no code implementations • 19 Jul 2023 • Qingyao Ai, Ting Bai, Zhao Cao, Yi Chang, Jiawei Chen, Zhumin Chen, Zhiyong Cheng, Shoubin Dong, Zhicheng Dou, Fuli Feng, Shen Gao, Jiafeng Guo, Xiangnan He, Yanyan Lan, Chenliang Li, Yiqun Liu, Ziyu Lyu, Weizhi Ma, Jun Ma, Zhaochun Ren, Pengjie Ren, Zhiqiang Wang, Mingwen Wang, Ji-Rong Wen, Le Wu, Xin Xin, Jun Xu, Dawei Yin, Peng Zhang, Fan Zhang, Weinan Zhang, Min Zhang, Xiaofei Zhu
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
no code implementations • 22 Jun 2023 • Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Xueqi Cheng
Recently, we have witnessed generative retrieval increasingly gaining attention in the information retrieval (IR) field, which retrieves documents by directly generating their identifiers.
no code implementations • 24 May 2023 • Yubao Tang, Ruqing Zhang, Jiafeng Guo, Jiangui Chen, Zuowei Zhu, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning.
no code implementations • 22 May 2023 • Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng
This is a very challenging task, because causal relations are usually expressed by implicit associations between events.
no code implementations • 10 May 2023 • Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs).
no code implementations • 3 May 2023 • Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
In this paper, we propose a new visual reasoning task, called Visual Transformation Telling (VTT).
1 code implementation • 2 May 2023 • Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
Such \textbf{state driven} visual reasoning has limitations in reflecting the ability to infer the dynamics between different states, which has shown to be equally important for human cognition in Piaget's theory.
1 code implementation • 28 Apr 2023 • Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng
In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.
1 code implementation • 28 Apr 2023 • Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yiqun Liu, Yixing Fan, Xueqi Cheng
Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task.
no code implementations • 18 Feb 2023 • Xiaojie Sun, Lulu Yu, Yiting Wang, Keping Bi, Jiafeng Guo
Then we fine-tune several pre-trained models and train an ensemble model to aggregate all the predictions from various pre-trained models with human-annotation data in the fine-tuning stage.
no code implementations • 15 Feb 2023 • Lulu Yu, Yiting Wang, Xiaojie Sun, Keping Bi, Jiafeng Guo
Unbiased learning to rank (ULTR) aims to mitigate various biases existing in user clicks, such as position bias, trust bias, presentation bias, and learn an effective ranker.
1 code implementation • 16 Dec 2022 • Long Bai, Saiping Guan, Zixuan Li, Jiafeng Guo, Xiaolong Jin, Xueqi Cheng
Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants.
1 code implementation • 9 Nov 2022 • Wenxiang Sun, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng
Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i. e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL).
no code implementations • 28 Oct 2022 • Sihao Yu, Fei Sun, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng
However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance.
no code implementations • 18 Oct 2022 • Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng
This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps.
1 code implementation • COLING 2022 • Yequan Wang, Xiang Li, Aixin Sun, Xuying Meng, Huaming Liao, Jiafeng Guo
CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.
1 code implementation • 14 Sep 2022 • Chen Wu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Yixing Fan, Maarten de Rijke, Xueqi Cheng
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
no code implementations • 12 Sep 2022 • Yinqiong Cai, Jiafeng Guo, Yixing Fan, Qingyao Ai, Ruqing Zhang, Xueqi Cheng
When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the learned NRM becomes even worse.
no code implementations • 21 Aug 2022 • Xinyu Ma, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng
Empirical results show that our method can significantly outperform the state-of-the-art autoencoder-based language models and other pre-trained models for dense retrieval.
no code implementations • 21 Aug 2022 • Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xueqi Cheng
Unlike the promising results in NLP, we find that these methods cannot achieve comparable performance to full fine-tuning at both stages when updating less than 1\% of the original model parameters.
1 code implementation • 16 Aug 2022 • Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Yiqun Liu, Yixing Fan, Xueqi Cheng
We show that a strong generative retrieval model can be learned with a set of adequately designed pre-training tasks, and be adopted to improve a variety of downstream KILT tasks with further fine-tuning.
1 code implementation • 25 Apr 2022 • Jingtao Zhan, Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
1 code implementation • 22 Apr 2022 • Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xueqi Cheng
% Therefore, in this work, we propose to drop out the decoder and introduce a novel contrastive span prediction task to pre-train the encoder alone.
1 code implementation • 12 Apr 2022 • Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng
This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead; ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking; iii) a fixed number of sentences are selected to form the final evidence set.
no code implementations • 4 Apr 2022 • Chen Wu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng
We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list.
1 code implementation • ACL 2022 • Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng
Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.
no code implementations • CVPR 2022 • Sihao Yu, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Zizhen Wang, Xueqi Cheng
By reducing the weights of the majority classes, such instances would become more difficult to learn and hurt the overall performance consequently.
1 code implementation • 31 Dec 2021 • Saiping Guan, Xueqi Cheng, Long Bai, Fujun Zhang, Zixuan Li, Yutao Zeng, Xiaolong Jin, Jiafeng Guo
Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG).
no code implementations • 27 Nov 2021 • Yixing Fan, Xiaohui Xie, Yinqiong Cai, Jia Chen, Xinyu Ma, Xiangsheng Li, Ruqing Zhang, Jiafeng Guo
The core of information retrieval (IR) is to identify relevant information from large-scale resources and return it as a ranked list to respond to the user's information need.
no code implementations • 27 Nov 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
4 code implementations • 12 Oct 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
no code implementations • 29 Sep 2021 • Jingwei Liu, Yi Gu, Shentong Mo, Zhun Sun, Shumin Han, Jiafeng Guo, Xueqi Cheng
In self-supervised learning frameworks, deep networks are optimized to align different views of an instance that contains the similar visual semantic information.
1 code implementation • EMNLP 2021 • Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng
In this paper, we propose a Transformer-based model, called MCPredictor, which integrates deep event-level and script-level information for script event prediction.
1 code implementation • Findings (NAACL) 2022 • Yiyi Liu, Yequan Wang, Aixin Sun, Xuying Meng, Jing Li, Jiafeng Guo
Based on this dual-channel framework, we design the Dual-Channel Network~(DC-Net) to recognize sentiment conflict.
no code implementations • 16 Aug 2021 • Lijuan Chen, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models.
no code implementations • 11 Aug 2021 • Chen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng
So we raise the question in this work: Are neural ranking models robust?
2 code implementations • 11 Aug 2021 • Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng
A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets.
5 code implementations • 2 Aug 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
no code implementations • 18 Jul 2021 • Yinqiong Cai, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Yanyan Lan, Xueqi Cheng
However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance.
no code implementations • ACL 2021 • Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng
Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.
1 code implementation • 21 Apr 2021 • Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, HuaWei Shen, Yuanzhuo Wang, Xueqi Cheng
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
1 code implementation • 21 Apr 2021 • Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng
However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity).
1 code implementation • 20 Apr 2021 • Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Yingyan Li, Xueqi Cheng
The basic idea of PROP is to construct the \textit{representative words prediction} (ROP) task for pre-training inspired by the query likelihood model.
4 code implementations • 16 Apr 2021 • Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
1 code implementation • 2 Apr 2021 • Changying Hao, Liang Pang, Yanyan Lan, Yan Wang, Jiafeng Guo, Xueqi Cheng
In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.
1 code implementation • 8 Mar 2021 • Jiafeng Guo, Yinqiong Cai, Yixing Fan, Fei Sun, Ruqing Zhang, Xueqi Cheng
We believe it is the right time to survey current status, learn from existing methods, and gain some insights for future development.
no code implementations • 1 Mar 2021 • Yixing Fan, Jiafeng Guo, Xinyu Ma, Ruqing Zhang, Yanyan Lan, Xueqi Cheng
We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question.
no code implementations • 25 Feb 2021 • Chen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xueqi Cheng
One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search.
no code implementations • 25 Dec 2020 • Yan Gao, Jiafeng Guo, Yanyan Lan, Huaming Liao
The ranking objective is the same as existing methods, i. e., to create a ranking list of items according to users' interests.
no code implementations • COLING 2020 • Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng
To resolve event coreference, existing methods usually calculate the similarities between event mentions and between specific kinds of event arguments.
1 code implementation • CVPR 2021 • Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i. e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views).
1 code implementation • 20 Oct 2020 • Xinyu Ma, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Xiang Ji, Xueqi Cheng
Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR).
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP.
1 code implementation • 25 Aug 2020 • Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng
To address this new task, we propose a novel Contrastive Generation model, namely CtrsGen for short, to generate the intent description by contrasting the relevant documents with the irrelevant documents given a query.
no code implementations • 25 Aug 2020 • Lixin Su, Jiafeng Guo, Ruqing Zhang, Yixing Fan, Yanyan Lan, Xue-Qi Cheng
To tackle such a challenge, in this work, we introduce the \textit{Continual Domain Adaptation} (CDA) task for MRC.
no code implementations • 13 Aug 2020 • Changying Hao, Liang Pang, Yanyan Lan, Fei Sun, Jiafeng Guo, Xue-Qi Cheng
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
no code implementations • ICML 2020 • Jianing Li, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng
We prove that under certain conditions, a linear combination of quality and diversity constitutes a divergence metric between the generated distribution and the real distribution.
no code implementations • ACL 2020 • Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, Xue-Qi Cheng
It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s).
no code implementations • 21 Jun 2020 • Zizhen Wang, Yixing Fan, Jiafeng Guo, Liu Yang, Ruqing Zhang, Yanyan Lan, Xue-Qi Cheng, Hui Jiang, Xiaozhao Wang
However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i. e., there could be different ways to ask a same question or different questions sharing similar expressions.
1 code implementation • 3 Feb 2020 • Liu Yang, Minghui Qiu, Chen Qu, Cen Chen, Jiafeng Guo, Yongfeng Zhang, W. Bruce Croft, Haiqing Chen
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
no code implementations • IJCNLP 2019 • Haoran Yan, Xiaolong Jin, Xiangbin Meng, Jiafeng Guo, Xue-Qi Cheng
Syntactic relations are broadly used in many NLP tasks.
2 code implementations • ACL 2019 • Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, Xue-Qi Cheng
Then, the self-attention mechanism is utilized to update both the context and masked response representation.
no code implementations • 9 Jul 2019 • Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng
Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications.
no code implementations • 24 May 2019 • Lixin Su, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng
Web question answering (QA) has become an indispensable component in modern search systems, which can significantly improve users' search experience by providing a direct answer to users' information need.
no code implementations • 24 May 2019 • Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xue-Qi Cheng
To generate a sound outline, an ideal OG model should be able to capture three levels of coherence, namely the coherence between context paragraphs, that between a section and its heading, and that between context headings.
1 code implementation • 24 May 2019 • Jiafeng Guo, Yixing Fan, Xiang Ji, Xue-Qi Cheng
Text matching is the core problem in many natural language processing (NLP) tasks, such as information retrieval, question answering, and conversation.
no code implementations • 16 Mar 2019 • Jiafeng Guo, Yixing Fan, Liang Pang, Liu Yang, Qingyao Ai, Hamed Zamani, Chen Wu, W. Bruce Croft, Xue-Qi Cheng
Ranking models lie at the heart of research on information retrieval (IR).
no code implementations • 12 Jan 2019 • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Lixin Su, Xue-Qi Cheng
However, the performances of such models are not so good as that in the RC task.
no code implementations • ACL 2018 • Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng
In this paper, we propose two tailored optimization criteria for Seq2Seq to different conversation scenarios, i. e., the maximum generated likelihood for specific-requirement scenario, and the conditional value-at-risk for diverse-requirement scenario.
no code implementations • ACL 2018 • Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Jun Xu, Xue-Qi Cheng
In conversation, a general response (e. g., {``}I don{'}t know{''}) could correspond to a large variety of input utterances.
2 code implementations • SIGIR '18 2018 • Yixing Fan, Jiafeng Guo, Yanyan Lan, Jun Xu, ChengXiang Zhai, Xue-Qi Cheng
The local matching layer focuses on producing a set of local relevance signals by modeling the semantic matching between a query and each passage of a document.
1 code implementation • 1 May 2018 • Liu Yang, Minghui Qiu, Chen Qu, Jiafeng Guo, Yongfeng Zhang, W. Bruce Croft, Jun Huang, Haiqing Chen
Our models and research findings provide new insights on how to utilize external knowledge with deep neural models for response selection and have implications for the design of the next generation of information-seeking conversation systems.
1 code implementation • 29 Apr 2018 • Yadi Lao, Jun Xu, Yanyan Lan, Jiafeng Guo, Sheng Gao, Xue-Qi Cheng
Inspired by the success and methodology of the AlphaGo Zero, MM-Tag formalizes the problem of sequence tagging with a Monte Carlo tree search (MCTS) enhanced Markov decision process (MDP) model, in which the time steps correspond to the positions of words in a sentence from left to right, and each action corresponds to assign a tag to a word.
no code implementations • 22 Apr 2018 • Guoxin Cui, Jun Xu, Wei Zeng, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng
One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations.
1 code implementation • 16 Apr 2018 • Qingyao Ai, Keping Bi, Cheng Luo, Jiafeng Guo, W. Bruce Croft
We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank.
1 code implementation • 16 Apr 2018 • Qingyao Ai, Keping Bi, Jiafeng Guo, W. Bruce Croft
Specifically, we employ a recurrent neural network to sequentially encode the top results using their feature vectors, learn a local context model and use it to re-rank the top results.
1 code implementation • 5 Jan 2018 • Liu Yang, Qingyao Ai, Jiafeng Guo, W. Bruce Croft
As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching of questions and answers.
Ranked #12 on Question Answering on TrecQA
3 code implementations • 23 Nov 2017 • Jiafeng Guo, Yixing Fan, Qingyao Ai, W. Bruce Croft
Specifically, our model employs a joint deep architecture at the query term level for relevance matching.
Ranked #14 on Ad-Hoc Information Retrieval on TREC Robust04
1 code implementation • 22 Nov 2017 • Liang Pang, Yanyan Lan, Jun Xu, Jiafeng Guo, Xue-Qi Cheng
The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields.
2 code implementations • 26th ACM International Conference on Information and Knowledge Management (CIKM '17) 2017 • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Jingfang Xu, Xue-Qi Cheng
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR).
no code implementations • 24 Jul 2017 • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng
Therefore, it is necessary to identify the difference between automatically learned features by deep IR models and hand-crafted features used in traditional learning to rank approaches.
1 code implementation • 23 Jul 2017 • Yixing Fan, Liang Pang, Jianpeng Hou, Jiafeng Guo, Yanyan Lan, Xue-Qi Cheng
In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods.
no code implementations • 18 Jul 2017 • Ruqing Zhang, Jiafeng Guo, Yanyan Lan, Jun Xu, Xue-Qi Cheng
Representing texts as fixed-length vectors is central to many language processing tasks.
no code implementations • 17 Jul 2017 • Liu Yang, Hamed Zamani, Yongfeng Zhang, Jiafeng Guo, W. Bruce Croft
We further evaluate the neural matching models in the next question prediction task in conversations.
1 code implementation • 15 Jun 2016 • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng
Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.
1 code implementation • 15 Apr 2016 • Shengxian Wan, Yanyan Lan, Jun Xu, Jiafeng Guo, Liang Pang, Xue-Qi Cheng
In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i. e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position.
no code implementations • 24 Mar 2016 • Fei Sun, Jiafeng Guo, Yanyan Lan, Jun Xu, Xue-Qi Cheng
Recent work exhibited that distributed word representations are good at capturing linguistic regularities in language.
7 code implementations • 20 Feb 2016 • Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Shengxian Wan, Xue-Qi Cheng
An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.
1 code implementation • 26 Nov 2015 • Shengxian Wan, Yanyan Lan, Jiafeng Guo, Jun Xu, Liang Pang, Xue-Qi Cheng
Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.
no code implementations • 26 Sep 2013 • Shuzi Niu, Yanyan Lan, Jiafeng Guo, Xue-Qi Cheng
Traditional rank aggregation methods are deterministic, and can be categorized into explicit and implicit methods depending on whether rank information is explicitly or implicitly utilized.
no code implementations • NeurIPS 2012 • Yanyan Lan, Jiafeng Guo, Xueqi Cheng, Tie-Yan Liu
This paper is concerned with the statistical consistency of ranking methods.