Zobrazeno 1 - 10
of 783
pro vyhledávání: '"Li, Jingye"'
Few-shot named entity recognition (NER) exploits limited annotated instances to identify named mentions. Effectively transferring the internal or external resources thus becomes the key to few-shot NER. While the existing prompt tuning methods have s
Externí odkaz:
http://arxiv.org/abs/2306.03974
Autor:
Zheng, Li, Ji, Donghong, Li, Fei, Fei, Hao, Wu, Shengqiong, Li, Jingye, Li, Bobo, Teng, Chong
The existing emotion-cause pair extraction (ECPE) task, unfortunately, ignores extracting the emotion type and cause type, while these fine-grained meta-information can be practically useful in real-world applications, i.e., chat robots and empathic
Externí odkaz:
http://arxiv.org/abs/2306.03969
Autor:
Fei, Hao, Wu, Shengqiong, Li, Jingye, Li, Bobo, Li, Fei, Qin, Libo, Zhang, Meishan, Zhang, Min, Chua, Tat-Seng
Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE predictions are unified into a linearized hierarchical expression under a
Externí odkaz:
http://arxiv.org/abs/2304.06248
Autor:
Li, Bobo, Fei, Hao, Li, Fei, Wu, Yuhan, Zhang, Jinsong, Wu, Shengqiong, Li, Jingye, Liu, Yijiang, Liao, Lizi, Chua, Tat-Seng, Ji, Donghong
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades shows great potential for real-world society. The current ABSA works, however, are mostly limited to the scenario of a single text piece, leaving the study in dialo
Externí odkaz:
http://arxiv.org/abs/2211.05705
So far, discontinuous named entity recognition (NER) has received increasing research attention and many related methods have surged such as hypergraph-based methods, span-based methods, and sequence-to-sequence (Seq2Seq) methods, etc. However, these
Externí odkaz:
http://arxiv.org/abs/2211.00684
Autor:
Wang, Fengqi, Li, Fei, Fei, Hao, Li, Jingye, Wu, Shengqiong, Su, Fangfang, Shi, Wenxuan, Ji, Donghong, Cai, Bo
Relation Extraction (RE) is a fundamental task of information extraction, which has attracted a large amount of research attention. Previous studies focus on extracting the relations within a sentence or document, while currently researchers begin to
Externí odkaz:
http://arxiv.org/abs/2210.16541
Emotion cause pair extraction (ECPE), as one of the derived subtasks of emotion cause analysis (ECA), shares rich inter-related features with emotion extraction (EE) and cause extraction (CE). Therefore EE and CE are frequently utilized as auxiliary
Externí odkaz:
http://arxiv.org/abs/2209.04112
Autor:
Cao, Hu, Li, Jingye, Su, Fangfang, Li, Fei, Fei, Hao, Wu, Shengqiong, Li, Bobo, Zhao, Liang, Ji, Donghong
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text. Most prior work focuses on extracting flat events while neglecting overlapped or nested ones. A few model
Externí odkaz:
http://arxiv.org/abs/2209.02693
The state-of-the-art model for structured sentiment analysis casts the task as a dependency parsing problem, which has some limitations: (1) The label proportions for span prediction and span relation prediction are imbalanced. (2) The span lengths o
Externí odkaz:
http://arxiv.org/abs/2203.10796
Publikováno v:
In Applied Surface Science 12 November 2024 673
