no code implementations • SemEval (NAACL) 2022 • Zihang Liu, Yancheng He, Feiqing Zhuang, Bing Xu
Respectively, for subtask 1, that is, to judge whether a sentence is PCL, the method of retraining the model with specific task data is adopted, and the method of splicing [CLS] and the keyword representation of the last three layers as the representation of the sentence; for subtask 2, that is, to judge the PCL type of the sentence, in addition to using the same method as task1, the method of selecting a special loss for Multi-label text classification is applied.
Multi Label Text Classification Multi-Label Text Classification +2
no code implementations • 29 Mar 2024 • Hanyu Li, Weizhi Ma, Peijie Sun, Jiayu Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Min Zhang, Shaoping Ma
In CUT, user similarity in the target domain is adopted as a constraint for user transformation learning to filter the user collaborative information from the source domain.
no code implementations • 22 Feb 2024 • Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, Wanli Ouyang
By conducting a detailed analysis of real multi-turn dialogue data, we construct a three-tier hierarchical ability taxonomy comprising 4208 turns across 1388 multi-turn dialogues in 13 distinct tasks.
no code implementations • 27 Feb 2023 • Dekai Sun, Yancheng He, Jiqing Han
For the difficulty of multimodal fusion, we use a K-layer multi-head attention mechanism as a downstream fusion module.
1 code implementation • 5 Sep 2022 • Yuncong Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Jing Cai, Leeven Luo, Sheng-hua Zhong
In this paper, we concentrate on recommending online novels to new users of an online novel reading platform, whose first visits to the platform occurred in the last seven days.
1 code implementation • 14 Oct 2021 • Fang Wang, Yuncong Li, Sheng-hua Zhong, Cunxiang Yin, Yancheng He
Aspect Sentiment Triplet Extraction (ASTE) aims to extract aspect term (aspect), sentiment and opinion term (opinion) triplets from sentences and can tell a complete story, i. e., the discussed aspect, the sentiment toward the aspect, and the cause of the sentiment.
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.
5 code implementations • 29 Mar 2021 • Yuncong Li, Fang Wang, Wenjun Zhang, Sheng-hua Zhong, Cunxiang Yin, Yancheng He
Aspect Sentiment Triplet Extraction (ASTE) aims to extract aspect term, sentiment and opinion term triplets from sentences and tries to provide a complete solution for aspect-based sentiment analysis (ABSA).
Ranked #1 on Aspect-Sentiment-Opinion Triplet Extraction on Res14
Aspect-Based Sentiment Analysis Aspect-Sentiment-Opinion Triplet Extraction +2
1 code implementation • 14 Apr 2020 • Siyu Duan, Wei Li, Cai Jing, Yancheng He, Yunfang Wu, Xu sun
In this paper, we propose the query-variant advertisement text generation task that aims to generate candidate advertisement texts for different web search queries with various needs based on queries and item keywords.
2 code implementations • 27 Jan 2020 • Bang Liu, Haojie Wei, Di Niu, Haolan Chen, Yancheng He
In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions.
no code implementations • 18 Sep 2019 • Wei Li, Shuheng Li, Shuming Ma, Yancheng He, Deli Chen, Xu sun
Graph is a natural structure to describe the complicated relation between tokens.
1 code implementation • ACL 2019 • Wei Li, Jingjing Xu, Yancheng He, ShengLi Yan, Yunfang Wu, Xu sun
In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph.
1 code implementation • 4 Jun 2019 • Wei Li, Jingjing Xu, Yancheng He, ShengLi Yan, Yunfang Wu, Xu sun
In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph.
no code implementations • 27 Feb 2019 • Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu
In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation.
1 code implementation • ACL 2019 • Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu
Identifying the relationship between two articles, e. g., whether two articles published from different sources describe the same breaking news, is critical to many document understanding tasks.