Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Xianpei Han"'
Autor:
Tianshu Wang, Hongyu Lin, Cheng Fu, Xianpei Han, Le Sun, Feiyu Xiong, Hui Chen, Minlong Lu, Xiuwen Zhu
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Entity matching (EM) is the most critical step for entity resolution (ER). While current deep learning-based methods achieve very impressive performance on standard EM benchmarks, their real-world application performance is much frustrating. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a37499e607380c52e6971f3dc66eaa3a
https://doi.org/10.24963/ijcai.2022/552
https://doi.org/10.24963/ijcai.2022/552
Publikováno v:
Journal of Artificial Intelligence Research. 70:545-566
As an important text coherence modeling task, sentence ordering aims to coherently organize a given set of unordered sentences. To achieve this goal, the most important step is to effectively capture and exploit global dependencies among these senten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2bb6d1e9da725618e033381c8e588f4f
https://doi.org/10.1613/jair.1.12078
https://doi.org/10.1613/jair.1.12078
Publikováno v:
AAAI
Neural semantic parsers usually generate meaning representation tokens from natural language tokens via an encoder-decoder model. However, there is often a vocabulary-mismatch problem between natural language utterances and logical forms. That is, on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65c04cc58648e3fd6a0e3fa1f3ae2fbc
https://doi.org/10.1609/aaai.v34i05.6253
https://doi.org/10.1609/aaai.v34i05.6253
Publikováno v:
AAAI
Bootstrapping for entity set expansion (ESE) has long been modeled as a multi-step pipelined process. Such a paradigm, unfortunately, often suffers from two main challenges: 1) the entities are expanded in multiple separate steps, which tends to intr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3114dd4721f8c065e3aa7b628e833bf7
https://doi.org/10.1609/aaai.v34i05.6482
https://doi.org/10.1609/aaai.v34i05.6482
Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f354713898ad91f020debfcd34f3a24c
http://arxiv.org/abs/2203.12252
http://arxiv.org/abs/2203.12252
Publikováno v:
Findings of the Association for Computational Linguistics: ACL 2022.
Events are considered as the fundamental building blocks of the world. Mining event-centric opinions can benefit decision making, people communication, and social good. Unfortunately, there is little literature addressing event-centric opinion mining
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c7a0fc678ef0a7997aa43e29c65fadb
https://doi.org/10.18653/v1/2022.findings-acl.216
https://doi.org/10.18653/v1/2022.findings-acl.216
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030997359
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fdaaa0adf94d34bc093a5f245690ffd1
https://doi.org/10.1007/978-3-030-99736-6_8
https://doi.org/10.1007/978-3-030-99736-6_8
Publikováno v:
Neurocomputing. 367:144-151
The current dominant image captioning models are mostly based on a CNN-LSTM encoder-decoder framework. Although this architecture has achieved remarkable progress, it still has shortcomings for not fully capturing the encoded image information. Speci
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49c2701281e8bae71bf8affe76c4d389
https://doi.org/10.1016/j.neucom.2019.08.012
https://doi.org/10.1016/j.neucom.2019.08.012
Autor:
Meng Liao, Chen Shaoyi, Jin Xu, Le Sun, Xianpei Han, Hongyu Lin, Annan Li, Yaojie Lu, Jialong Tang
Publikováno v:
ACL/IJCNLP (1)
Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple subtasks.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::357bdd1eca94f3b4da12a212b37ee060
http://arxiv.org/abs/2106.09232
http://arxiv.org/abs/2106.09232
Publikováno v:
ACL/IJCNLP (1)
Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::476b99226ebca4b5f49e616631aade7d
http://arxiv.org/abs/2106.09233
http://arxiv.org/abs/2106.09233