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
  • [21] Grounding Visual Concepts for Zero-Shot Event Detection and Event Captioning
    Li, Zhihui
    Chang, Xiaojun
    Yao, Lina
    Pan, Shirui
    Ge Zongyuan
    Zhang, Huaxiang
    KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 297 - 305
  • [22] IMPROVING NER IN SOCIAL MEDIA VIA ENTITY TYPE-COMPATIBLE UNKNOWN WORD SUBSTITUTION
    Xie, Jian
    Zhang, Kai
    Sun, Lin
    Su, Yindu
    Xu, Chenxiang
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 7693 - 7697
  • [23] Zero-Shot Neural Transfer for Cross-Lingual Entity Linking
    Rijhwani, Shruti
    Xie, Jiateng
    Neubig, Graham
    Carbonell, Jaime
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 6924 - 6931
  • [24] Towards zero-shot cross-lingual named entity disambiguation
    Barrena, Ander
    Soroa, Aitor
    Agirre, Eneko
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 184
  • [25] DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation Extraction
    Lv, Bo
    Liu, Xin
    Dai, Shaojie
    Liu, Nayu
    Yang, Fan
    Luo, Ping
    Yu, Yue
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, 2023, : 5491 - 5505
  • [26] Zero-shot Entity Linking with Efficient Long Range Sequence Modeling
    Yao, Zonghai
    Cao, Liangliang
    Pan, Huapu
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 2517 - 2522
  • [27] An Adaptive Mixup Hard Negative Sampling for Zero-Shot Entity Linking
    Cai, Shisen
    Wu, Xi
    Maimaiti, Maihemuti
    Chen, Yichang
    Wang, Zhixiang
    Zheng, Jiong
    MATHEMATICS, 2023, 11 (20)
  • [28] Chinese medical named entity recognition based on zero-shot learning
    Zhou, Menglin
    Gong, Kecun
    2022 5TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING, MLNLP 2022, 2022, : 190 - 195
  • [29] Zero-Shot Video Grounding for Automatic Video Understanding in Sustainable Smart Cities
    Wang, Ping
    Sun, Li
    Wang, Liuan
    Sun, Jun
    SUSTAINABILITY, 2023, 15 (01)
  • [30] Improving Zero-Shot Entity Retrieval through Effective Dense Representations
    Partalidou, Eleni
    Christou, Despina
    Tsoumakas, Grigorios
    PROCEEDINGS OF THE 12TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE, SETN 2022, 2022,