Sapienza NLP @ EACL 2024
CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts has been accepted at the main conference of EACL 2024!
Sapienza NLP is proud to present "CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts" at EACL 2024. This work presents a state-of-the-art cross-lingual approach for sentence alignment of long texts.
CroCoAlign: A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts
by F.M. Molfese, A.S. Bejgu, S. Tedeschi, S. Conia, R. Navigli
Sentence alignment – establishing links between corresponding sentences in two related documents – is an important NLP task with several downstream applications, such as machine translation (MT).Despite the fact that existing sentence alignment systems have achieved promising results, their effectiveness is based on auxiliary information such as document metadata or machine-generated translations, as well as hyperparameter-sensitive techniques. Moreover, these systems often overlook the crucial role that context plays in the alignment process.In this paper, we address the aforementioned issues and propose CroCoAlign: the first context-aware, end-to-end and fully-neural architecture for sentence alignment. Our system maps source and target sentences in long documents by contextualizing their sentence embeddings with respect to the other sentences in the document. We extensively evaluate CroCoAlign on a multilingual dataset consisting of 20 language pairs derived from the Opus project, and demonstrate that our model achieves state-of-the-art performance.