Thumbnail Image
Item

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference

Li, Bangzheng
; 
Yin, Wenpeng
; 
Chen, Muhao
Citations
Altmetric:
Genre
Journal article
Date
2022-05-16
Advisor
Committee member
Group
Department
Computer and Information Sciences
Subject
Permanent link to this record
http://hdl.handle.net/20.500.12613/9697
Collections
Faculty/Researcher Works
Show all metadata
Files
Thumbnail Image
YinEtAl-JournalArticle-2022-05.pdf
Adobe PDF, 494.38 KB
Research Projects
Organizational Units
Journal Issue
DOI
http://dx.doi.org/10.1162/tacl_a_00479
Abstract
The task of ultra-fine entity typing (UFET) seeks to predict diverse and free-form words or phrases that describe the appropriate types of entities mentioned in sentences. A key challenge for this task lies in the large number of types and the scarcity of annotated data per type. Existing systems formulate the task as a multi-way classification problem and train directly or distantly supervised classifiers. This causes two issues: (i) the classifiers do not capture the type semantics because types are often converted into indices; (ii) systems developed in this way are limited to predicting within a pre-defined type set, and often fall short of generalizing to types that are rarely seen or unseen in training. This work presents LITE🍻, a new approach that formulates entity typing as a natural language inference (NLI) problem, making use of (i) the indirect supervision from NLI to infer type information meaningfully represented as textual hypotheses and alleviate the data scarcity issue, as well as (ii) a learning-to-rank objective to avoid the pre-defining of a type set. Experiments show that, with limited training data, LITE obtains state-of-the-art performance on the UFET task. In addition, LITE demonstrates its strong generalizability by not only yielding best results on other fine-grained entity typing benchmarks, more importantly, a pre-trained LITE system works well on new data containing unseen types.
Description
Citation
Bangzheng Li, Wenpeng Yin, Muhao Chen; Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference. Transactions of the Association for Computational Linguistics 2022; 10 607–622. doi: https://doi.org/10.1162/tacl_a_00479
Citation to related work
MIT Press
Has part
Transactions of the Association for Computational Linguistics, Vol. 10
ADA compliance
For Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu
Embedded videos