Zero-Shot Open Entity Typing as Type-Compatible Grounding

被引:0
|
作者
Zhou, Ben [1 ]
Khashabi, Daniel [2 ]
Tsai, Chen-Tse [3 ]
Roth, Dan [2 ]
机构
[1] Univ Illinois, Champaign, IL 61820 USA
[2] Univ Penn, Philadelphia, PA USA
[3] Bloomberg LP, New York, NY USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The problem of entity-typing has been studied predominantly in supervised learning fashion, mostly with task-specific annotations (for coarse types) and sometimes with distant supervision (for fine types). While such approaches have strong performance within datasets, they often lack the flexibility to transfer across text genres and to generalize to new type taxonomies. In this work we propose a zero-shot entity typing approach that requires no annotated data and can flexibly identify newly defined types. Given a type taxonomy defined as Boolean functions of FREEBASE "types", we ground a given mention to a set of type-compatible Wikipedia entries and then infer the target mention's types using an inference algorithm that makes use of the types of these entries. We evaluate our system on a broad range of datasets, including standard fine-grained and coarse-grained entity typing datasets, and also a dataset in the biological domain. Our system is shown to be competitive with state-of-the-art supervised NER systems and outperforms them on out-of-domain datasets. We also show that our system significantly outperforms other zero-shot fine typing systems.
引用
收藏
页码:2065 / 2076
页数:12
相关论文
共 50 条
  • [31] DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning
    Chen, Zhuo
    Huang, Yufeng
    Chen, Jiaoyan
    Geng, Yuxia
    Zhang, Wen
    Fang, Yin
    Pan, Jeff Z.
    Chen, Huajun
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 1, 2023, : 405 - 413
  • [32] Zero-shot visual grounding via coarse-to-fine representation learning
    Mi, Jinpeng
    Jin, Shaofei
    Chen, Zhiqian
    Liu, Dan
    Wei, Xian
    Zhang, Jianwei
    NEUROCOMPUTING, 2024, 610
  • [33] Counterfactual Zero-Shot and Open-Set Visual Recognition
    Yue, Zhongqi
    Wang, Tan
    Sun, Qianru
    Hua, Xian-Sheng
    Zhang, Hanwang
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 15399 - 15409
  • [34] A New Formalism, Method and Open Issues for Zero-Shot Coordination
    Treutlein, Johannes
    Dennis, Michael
    Oesterheld, Caspar
    Foerster, Jakob
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139 : 7423 - 7434
  • [35] A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking
    Sun, Kai
    Zhang, Richong
    Mensah, Samuel
    Mao, Yongyi
    Liu, Xudong
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 1449 - 1458
  • [36] Zero-shot evaluation of ChatGPT for food named-entity recognition and linking
    Ogrinc, Matevz
    Korousic Seljak, Barbara
    Eftimov, Tome
    FRONTIERS IN NUTRITION, 2024, 11
  • [37] Toward Zero-shot Entity Recognition in Task-oriented Conversational Agents
    Guerini, Marco
    Magnolini, Simone
    Balaraman, Vevake
    Magnini, Bernardo
    19TH ANNUAL MEETING OF THE SPECIAL INTEREST GROUP ON DISCOURSE AND DIALOGUE (SIGDIAL 2018), 2018, : 317 - 326
  • [38] A Bidirectional Multi-paragraph Reading Model for Zero-shot Entity Linking
    Tang, Hongyin
    Sun, Xingwu
    Jin, Beihong
    Zhang, Fuzheng
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 13889 - 13897
  • [39] Improving Zero-Shot Phrase Grounding via Reasoning on External Knowledge and Spatial Relations
    Shi, Zhan
    Shen, Yilin
    Jin, Hongxia
    Zhu, Xiaodan
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 2253 - 2261
  • [40] Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation
    Zhang, Hui
    Ding, Henghui
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 6954 - 6963