Saved in:
Bibliographic Details
Main Authors: Fedorova, Inessa, Musatow, Aleksei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.15066
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910497486405632
author Fedorova, Inessa
Musatow, Aleksei
author_facet Fedorova, Inessa
Musatow, Aleksei
contents The paraphrase identification task involves measuring semantic similarity between two short sentences. It is a tricky task, and multilingual paraphrase identification is even more challenging. In this work, we train a bi-encoder model in a contrastive manner to detect hard paraphrases across multiple languages. This approach allows us to use model-produced embeddings for various tasks, such as semantic search. We evaluate our model on downstream tasks and also assess embedding space quality. Our performance is comparable to state-of-the-art cross-encoders, with only a minimal relative drop of 7-10% on the chosen dataset, while keeping decent quality of embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15066
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-lingual paraphrase identification
Fedorova, Inessa
Musatow, Aleksei
Computation and Language
The paraphrase identification task involves measuring semantic similarity between two short sentences. It is a tricky task, and multilingual paraphrase identification is even more challenging. In this work, we train a bi-encoder model in a contrastive manner to detect hard paraphrases across multiple languages. This approach allows us to use model-produced embeddings for various tasks, such as semantic search. We evaluate our model on downstream tasks and also assess embedding space quality. Our performance is comparable to state-of-the-art cross-encoders, with only a minimal relative drop of 7-10% on the chosen dataset, while keeping decent quality of embeddings.
title Cross-lingual paraphrase identification
topic Computation and Language
url https://arxiv.org/abs/2406.15066