Intelligent Translation Memory Matching and Retrieval with Sentence Encoders

Tharindu Ranasinghe; Constantin Orǎsan; Ruslan Mitkov

Intelligent Translation Memory Matching and Retrieval with Sentence Encoders

Tharindu Ranasinghe, Constantin Orǎsan, Ruslan Mitkov

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Matching and retrieving previously translated segments from the Translation Memory is a key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based on edit distance which we have identified as a major drawback in Translation Memories systems. In this paper, we introduce sentence encoders to improve matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance-based algorithms.

Original language	English
Title of host publication	Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
Publisher	Association for Computational Linguistics (ACL)
Pages	175-184
Number of pages	10
Publication status	Published - Nov 2020

Bibliographical note

Copyright 2020 The authors. This article is licensed under a Creative
Commons 3.0 licence, no derivative works, attribution, CCBY-ND

Access to Document

Ranasingheetal_2020_VoR
Copyright 2020 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CCBY-ND
Final published version, 177 KBLicence: CC BY-ND 3.0

Cite this

@inproceedings{9e87d079b4e147ebb07fdd282ccff048,

title = "Intelligent Translation Memory Matching and Retrieval with Sentence Encoders",

abstract = "Matching and retrieving previously translated segments from the Translation Memory is a key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based on edit distance which we have identified as a major drawback in Translation Memories systems. In this paper, we introduce sentence encoders to improve matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance-based algorithms.",

author = "Tharindu Ranasinghe and Constantin Orǎsan and Ruslan Mitkov",

year = "2020",

month = nov,

language = "English",

pages = "175--184",

booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

}

Intelligent Translation Memory Matching and Retrieval with Sentence Encoders. / Ranasinghe, Tharindu; Orǎsan, Constantin; Mitkov, Ruslan.
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. Association for Computational Linguistics (ACL), 2020. p. 175-184.

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Intelligent Translation Memory Matching and Retrieval with Sentence Encoders

AU - Ranasinghe, Tharindu

AU - Orǎsan, Constantin

AU - Mitkov, Ruslan

PY - 2020/11

Y1 - 2020/11

N2 - Matching and retrieving previously translated segments from the Translation Memory is a key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based on edit distance which we have identified as a major drawback in Translation Memories systems. In this paper, we introduce sentence encoders to improve matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance-based algorithms.

AB - Matching and retrieving previously translated segments from the Translation Memory is a key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based on edit distance which we have identified as a major drawback in Translation Memories systems. In this paper, we introduce sentence encoders to improve matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance-based algorithms.

UR - https://www.aclweb.org/anthology/2020.eamt-1.19

M3 - Conference publication

SP - 175

EP - 184

BT - Proceedings of the 22nd Annual Conference of the European Association for Machine Translation

PB - Association for Computational Linguistics (ACL)

ER -

Intelligent Translation Memory Matching and Retrieval with Sentence Encoders

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this