Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2018

Abstract

We explore the notion of subjectivity, and hypothesize that word embeddings learnt from input corpora of varying levels of subjectivity behave differently on natural language processing tasks such as classifying a sentence by sentiment, subjectivity, or topic. Through systematic comparative analyses, we establish this to be the case indeed. Moreover, based on the discovery of the outsized role that sentiment words play on subjectivity-sensitive tasks such as sentiment classification, we develop a novel word embedding SentiVec which is infused with sentiment information from a lexical resource, and is shown to outperform baselines on such tasks.

Keywords

Computational linguistics, Embeddings, Natural language processing systems

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 2018 July 15-20

First Page

1212

Last Page

1221

Identifier

10.18653/v1/P18-1112

Publisher

Association for Computational Linguistics

City or Country

Stroudsburg, PA

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.18653/v1/P18-1112

Share

COinS