no code implementations • EMNLP 2021 • Xingwu Sun, Yanling Cui, Hongyin Tang, Fuzheng Zhang, Beihong Jin, Shi Wang
In this paper, we propose a new ranking model DR-BERT, which improves the Document Retrieval (DR) task by a task-adaptive training process and a Segmented Token Recovery Mechanism (STRM).
no code implementations • 6 Dec 2024 • Hongyin Tang, Di Xiu, Lanrui Wang, Xiurui Geng, Jingang Wang, Xunliang Cai
The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive.
1 code implementation • 26 Nov 2023 • Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang
Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in multi-turn conversations.
1 code implementation • 11 Jun 2023 • Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Yang Yang, Hongyin Tang, Keqing He, Jiahao Liu, Jingang Wang, Shu Zhao, Peng Zhang, Jie Tang
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
no code implementations • 20 Mar 2023 • Ying Mo, Hongyin Tang, Jiahao Liu, Qifan Wang, Zenglin Xu, Jingang Wang, Wei Wu, Zhoujun Li
There are three types of NER tasks, including flat, nested and discontinuous entity recognition.
no code implementations • 1 Jan 2023 • Xingwu Sun, Hongyin Tang, Chengzhong Xu
Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type.
no code implementations • COLING 2022 • Borun Chen, Hongyin Tang, Jiahao Bu, Kai Zhang, Jingang Wang, Qifan Wang, Hai-Tao Zheng, Wei Wu, Liqian Yu
However, most current models use Chinese characters as inputs and are not able to encode semantic information contained in Chinese words.
no code implementations • 8 Dec 2021 • Dan Li, Yang Yang, Hongyin Tang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching.
1 code implementation • NeurIPS 2021 • Yang Zhang, Bo Tang, Qingyu Yang, Dou An, Hongyin Tang, Chenyang Xi, Xueying Li, Feiyu Xiong
Further, a novel offline reinforcement learning method and an off-policy evaluation algorithm are proposed for policy learning and policy evaluation, respectively.
no code implementations • NAACL 2021 • Xingwu Sun, Yanling Cui, Hongyin Tang, Qiuyu Zhu, Fuzheng Zhang, Beihong Jin
To tackle this problem, we define a three-level relevance in keyword-document matching task: topic-aware relevance, partially-relevance and irrelevance.
no code implementations • ACL 2021 • Hongyin Tang, Xingwu Sun, Beihong Jin, Jingang Wang, Fuzheng Zhang, Wei Wu
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models.
no code implementations • IJCNLP 2019 • Hongyin Tang, Miao Li, Beihong Jin
This model captures structural features by a sequential variational autoencoder component and leverages a topic modeling component based on Gaussian distribution to enhance the recognition of text semantics.