Thumbnail Image
Item

Semantic textual similarity with siamese neural networks

; 
Mitkov, Ruslan
; 
Ranasinghe, Tharindu
Authors
Orasan, Constantin
 Mitkov, Ruslan
 Ranasinghe, Tharindu
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2019-09-02
Submitted date
Subjects
deep learning
 nlp
Show all metadata
Files
Thumbnail Image
PDFsam1_proceedings-ranlp-2019.pdf
Adobe PDF, 351.97 KB
Alternative
Abstract
Calculating the Semantic Textual Similarity (STS) is an important research area in natural language processing which plays a significant role in many applications such as question answering, document summarisation, information retrieval and information extraction. This paper evaluates Siamese recurrent architectures, a special type of neural networks, which are used here to measure STS. Several variants of the architecture are compared with existing methods
Citation
Orasan, C., Mitkov, R. and Ranasinghe, T. (2019) Semantic textual similarity with siamese neural networks, RANLP 2019, 2nd-4th September 2019, Varna, Bulgaria.
Publisher
RANLP
Journal
Research Unit
URI
http://hdl.handle.net/2436/622709
DOI
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
http://lml.bas.bg/ranlp2019/accepted.php
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
1313-8502
EISSN
ISBN
9789544520557
ISMN
Gov't Doc #
Sponsors
Rights
Research Projects
Organizational Units
Journal Issue
Embedded videos
Collections
Research Institute in Information and Language Processing