Conference proceeding
End-to-End Joint Opinion Role Labeling with BERT
2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp 2438-2446
24 Jan 2020
Abstract
Opinion mining has raised growing interest both in industry and academia in the past decade. Opinion role labeling (ORL) is a task to extract opinion holder and target from natural language to answer the question "who express what". Recent years, neural network based methods with additional lexical and syntactic features have achieved state-of-the-art performances in similar tasks. Moreover, Bidirectional Encoder Representations from Transformers (BERT) has shown impressive performances among a variety of natural language processing (NLP) tasks. To investigate BERT based end-to-end model in ORL, we propose models using BERT, Bidirectional Long short-term Memory (BILSTM) and Conditional Random Field (CRF) to jointly extract opinion roles (e.g., opinion holder and target). Experimental results show that our models achieve remarkable scores without using extra syntactic and/or semantic features. To our best knowledge, we are among the pioneers to successfully integrate BERT in this manner. Our work contributes to the improvement of state-of-the-art aspect-level opinion mining methods and providing strong baselines for future work.
Metrics
Details
- Title
- End-to-End Joint Opinion Role Labeling with BERT
- Creators
- Wei Quan - Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USAJinli Hang - Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R ChinaXiaohua Tony Hu - Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA
- Contributors
- C Baru (Editor)J Huan (Editor)L Khan (Editor)X H Hu (Editor)R Ak (Editor)Y Tian (Editor)R Barga (Editor)C Zaniolo (Editor)K Lee (Editor)Y F Ye (Editor)
- Publication Details
- 2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp 2438-2446
- Series
- IEEE International Conference on Big Data
- Publisher
- IEEE
- Number of pages
- 9
- Grant note
- IIS 1744661; IIS 1815256 / NSF; National Science Foundation (NSF)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:000554828702116
- Scopus ID
- 2-s2.0-85081338502
- Other Identifier
- 991019189191904721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Information Systems
- Computer Science, Theory & Methods