1 code implementation • EMNLP 2021 • Xianming Li, Xiaotian Luo, Chenghao Dong, Daichuan Yang, Beidi Luan, Zhen He
To address such a problem, this paper proposes a novel efficient entities and relations extraction model called TDEER, which stands for Translating Decoding Schema for Joint Extraction of Entities and Relations.
Ranked #1 on Joint Entity and Relation Extraction on NYT
1 code implementation • 22 Feb 2024 • Xianming Li, Zongxi Li, Jing Li, Haoran Xie, Qing Li
High-quality sentence embeddings are fundamental in many natural language processing (NLP) tasks, such as semantic textual similarity (STS) and retrieval-augmented generation (RAG).
no code implementations • 11 Jan 2024 • Xianming Li, Jing Li
By doing so, it can improve social media language understanding performance and save training time.
2 code implementations • 9 Nov 2023 • Xianming Li, Jing Li
Most recent studies employed large language models (LLMs) to learn sentence embeddings.
2 code implementations • 2 Oct 2023 • Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, Xiaoqin Zhong
We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU.
Ranked #1 on Named Entity Recognition (NER) on CoNLL03 (F1 (micro) metric)
2 code implementations • 22 Sep 2023 • Xianming Li, Jing Li
This novel approach effectively mitigates the adverse effects of the saturation zone in the cosine function, which can impede gradient and hinder optimization processes.
Ranked #1 on Semantic Textual Similarity on STS16
1 code implementation • 12 Jun 2023 • Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li
Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention.
no code implementations • 14 Dec 2020 • Xianming Li, Yongwei Huang, Wing-Kin Ma
The minimization problem is accordingly turned into a QMI problem, and the problem is solved by a restricted linear matrix inequality relaxation with additional valid convex constraints.
no code implementations • 22 Feb 2020 • Xianming Li, Zongxi Li, Yingbin Zhao, Haoran Xie, Qing Li
The dominant text classification studies focus on training classifiers using textual instances only or introducing external knowledge (e. g., hand-craft features and domain expert knowledge).