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
  • [41] Vocabulary-Informed Zero-Shot and Open-Set Learning
    Fu, Yanwei
    Wang, Xiaomei
    Dong, Hanze
    Jiang, Yu-Gang
    Wang, Meng
    Xue, Xiangyang
    Sigal, Leonid
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (12) : 3136 - 3152
  • [42] Open zero-shot learning via asymmetric VAE with dissimilarity space
    Zhai, Zhibo
    Li, Xiao
    Chang, Zhonghao
    INFORMATION SCIENCES, 2023, 647
  • [43] Learning adversarial semantic embeddings for zero-shot recognition in open worlds
    Li, Tianqi
    Pang, Guansong
    Bai, Xiao
    Zheng, Jin
    Zhou, Lei
    Ning, Xin
    PATTERN RECOGNITION, 2024, 149
  • [44] Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
    Mancini, Massimiliano
    Naeem, Muhammad Ferjad
    Xian, Yongqin
    Akata, Zeynep
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1545 - 1560
  • [45] KG-ZESHEL: Knowledge Graph-Enhanced Zero-Shot Entity Linking
    Ristoski, Petar
    Lin, Zhizhong
    Zhou, Qunzhi
    PROCEEDINGS OF THE 11TH KNOWLEDGE CAPTURE CONFERENCE (K-CAP '21), 2021, : 49 - 56
  • [46] Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking
    Schumacher, Elliot
    Mayfield, James
    Dredze, Mark
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 583 - 595
  • [47] VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
    Xu, Yifang
    Sun, Yunzhuo
    Xie, Zien
    Zhai, Benxiang
    Du, Sidan
    APPLIED SCIENCES-BASEL, 2024, 14 (05):
  • [48] LlmRe: A zero-shot entity relation extraction method based on the large language model
    Zhao, Wei
    Chen, Qinghui
    You, Junling
    PROCEEDINGS OF 2023 7TH INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING, EITCE 2023, 2023, : 475 - 480
  • [49] Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning
    Jarnac, Lucas
    Couceiro, Miguel
    Monnin, Pierre
    PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023, 2023, : 934 - 944
  • [50] GEM: Translation-Free Zero-Shot Global Entity Matcher for Global Catalogs
    Bouyarmane, Karim
    KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 2593 - 2600