Ontology-guided annotation-free fine-grained entity typing

Komarlu, Tanay Manjunath

Permalink

https://hdl.handle.net/2142/120357 Copy

Description

Title

Ontology-guided annotation-free fine-grained entity typing

Author(s)

Komarlu, Tanay Manjunath

Issue Date

2023-04-12

Director of Research (if dissertation) or Advisor (if thesis)

Han, Jiawei

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Fine-grained Entity Typing
• Annotation-free Entity Typing
• Zero-shot Entity Typing
• Information Extraction

Language

eng

Abstract

Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, will play an important role in natural language understanding. FET has been studied extensively in natural language processing and typically relies on human-annotated corpora for training, which is costly and difficult to scale. Recent studies leverage pre-trained language models (PLMs) to generate rich and context-aware weak supervision for FET. However, the weak supervision based on masked language model (MLM) prompting still has two challenges: (1) a prompt often generates a set of tokens unsuitable for typing, and includes a mixture of rough and fine-grained types or (2) it does not incorporate the rich structural information in a given fine-grained type ontology. In this study, we vision that an ontology provides a semantic-rich, hierarchical structure, which will help select the best results generated by multiple PLM models and head words. Specifically, we propose a novel annotation-free, ontology-guided FET method, OntoType, which follows a type ontological structure, from coarse to fine, ensembles multiple PLM prompting results to generate a set of type candidates, and refines its type resolution, under the local context with a natural language inference model. Our experiments on the Ontonotes, FIGER, and NYT datasets using their associated ontological structures demonstrate that our method outperforms the state-of-the-art zero-shot fine-grained entity typing methods. Our error analysis shows that refinement of the existing ontology structures will further improve fine-grained entity typing.

Graduation Semester

2023-05

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/120357

Copyright and License Information

Copyright 2023 Tanay Komarlu

Owning Collections