Language selection

Government of Canada / Gouvernement du Canada

Search

Fully unsupervised crosslingual semantic textual similarity metric based on BERT for identifying parallel data

From National Research Council Canada

AuthorSearch for: 1; Search for: 1
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Article
Conference23rd Conference on Computational Natural Language Learning, CoNLL 2019, November 3-4, 2019, Hong Kong, China
Abstract
We present a fully unsupervised crosslingual semantic textual similarity (STS) metric, based on contextual embeddings extracted from BERT - Bidirectional Encoder Representations from Transformers (Devlin et al., 2019). The goal of crosslingual STS is to measure to what degree two segments of text in different languages express the same meaning. Not only is it a key task in crosslingual natural language understanding (XLU), it is also particularly useful for identifying parallel resources for training and evaluating downstream multilingual natural language processing (NLP) applications, such as machine translation. Most previous crosslingual STS methods relied heavily on existing parallel resources, thus leading to a circular dependency problem. With the advent of massively multilingual context representation models such as BERT, which are trained on the concatenation of non-parallel data from each language, we show that the deadlock around parallel resources can be broken. We perform intrinsic evaluations on crosslingual STS data sets and extrinsic evaluations on parallel corpus filtering and human translation equivalence assessment tasks. Our results show that the unsupervised crosslingual STS metric using BERT without fine-tuning achieves performance on par with supervised or weakly supervised approaches.
Publication date
PublisherAssociation for Computational Linguistics
In
  • CoNLL 2019: 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference: 206–215.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier042d0e4b-593d-40d8-8d93-2c984a9f0aa2
Record created2021-03-15
Record modified2021-03-15
Date modified: