CNN-based framework for classifying temporal relations with question encoder

Temporal-relation classification plays an important role in the field of natural language processing. Various deep learning-based classifiers, which can generate better models using sentence embedding, have been proposed to address this challenging task. These approaches, however, do not work well d...

Full description

Saved in:
Bibliographic Details
Published in:International journal on digital libraries 2022-06, Vol.23 (2), p.167-177
Main Authors: Seki, Yohei, Zhao, Kangkang, Oguni, Masaki, Sugiyama, Kazunari
Format: Article
Language:English
Subjects:
Classification
Classifiers
Coders
Computer Science
Database Management
Deep learning
Embedding
Information Systems and Communication Service
Machine learning
Natural language processing
Questions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Temporal-relation classification plays an important role in the field of natural language processing. Various deep learning-based classifiers, which can generate better models using sentence embedding, have been proposed to address this challenging task. These approaches, however, do not work well due to the lack of task-related information. To overcome this problem, we propose a novel framework that incorporates prior information by employing awareness of events and time expressions (time–event entities) with various window sizes to focus on context words around the entities as a filter. We refer to this module as “question encoder.” In our approach, this kind of prior information can extract task-related information from simple sentence embedding. Our experimental results on a publicly available Timebank-Dense corpus demonstrate that our approach outperforms some state-of-the-art techniques, including CNN-, LSTM-, and BERT-based temporal relation classifiers.
ISSN:1432-5012
1432-1300
DOI:10.1007/s00799-021-00310-1