Loading...
Enhancing unsupervised sentence similarity methods with deep contextualised word representations
Ranashinghe, Tharindu Orasan, Constantin Mitkov, Ruslan
Ranashinghe, Tharindu
Orasan, Constantin
Mitkov, Ruslan
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2019-09-02
Submitted date
Alternative
Abstract
Calculating Semantic Textual Similarity (STS) plays a significant role in many applications such as question answering, document summarisation, information retrieval and information extraction. All modern state of the art STS methods rely on word embeddings one way or another. The recently introduced contextualised word embeddings have proved more effective than standard word embeddings in many natural language processing tasks. This paper evaluates the impact of several contextualised word embeddings on unsupervised STS methods and compares it with the existing supervised/unsupervised STS methods for different datasets in different languages and different domains.
Citation
Ranashinghe, T., Orasan, C. and Mitkov, R. (2019) Enhancing unsupervised sentence similarity methods with deep contextualised word representations, RANLP 2019, 2nd-4th September, 2019, Varna, Bulgaria.
Publisher
Journal
Research Unit
DOI
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
1313-8502
EISSN
ISBN
9789544520557