Adaptative Bilingual Aligning Using Multilingual Sentence Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Kraif, Olivier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909139877232640
author Kraif, Olivier
author_facet Kraif, Olivier
contents In this paper, we present an adaptive bitextual alignment system called AIlign. This aligner relies on sentence embeddings to extract reliable anchor points that can guide the alignment path, even for texts whose parallelism is fragmentary and not strictly monotonic. In an experiment on several datasets, we show that AIlign achieves results equivalent to the state of the art, with quasi-linear complexity. In addition, AIlign is able to handle texts whose parallelism and monotonicity properties are only satisfied locally, unlike recent systems such as Vecalign or Bertalign.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11921
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptative Bilingual Aligning Using Multilingual Sentence Embedding
Kraif, Olivier
Computation and Language
In this paper, we present an adaptive bitextual alignment system called AIlign. This aligner relies on sentence embeddings to extract reliable anchor points that can guide the alignment path, even for texts whose parallelism is fragmentary and not strictly monotonic. In an experiment on several datasets, we show that AIlign achieves results equivalent to the state of the art, with quasi-linear complexity. In addition, AIlign is able to handle texts whose parallelism and monotonicity properties are only satisfied locally, unlike recent systems such as Vecalign or Bertalign.
title Adaptative Bilingual Aligning Using Multilingual Sentence Embedding
topic Computation and Language
url https://arxiv.org/abs/2403.11921