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

Bangzheng Li, Wenpeng Yin, Muhao Chen

Research output: Contribution to journalArticlepeer-review

22 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)607-622
Number of pages16
JournalTransactions of the Association for Computational Linguistics
Volume10
DOIs
StatePublished - May 16 2022

All Science Journal Classification (ASJC) codes

  • Communication
  • Human-Computer Interaction
  • Linguistics and Language
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference'. Together they form a unique fingerprint.

Cite this