Vecalign: Improved Sentence Alignment in Linear Time and Space (D19-1)

Copied to clipboard

Challenge: Sentence-aligned bitext is used to train nearly all machine translation systems.
Approach: They propose a bilingual sentence alignment method which is linear in time and space with respect to the number of sentences being aligned.
Outcome: The proposed method outperforms the existing method by 5 F1 points on a German–French test set and improves downstream MT quality by 1.7 and 1.6 BLEU in Sinhala-English and Nepali-English, respectively.

Similar Papers

Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents (2025.emnlp-main)

Copied to clipboard

Challenge: Speech Vecalign is a parallel speech document alignment method that monotonically aligns speech segment embeddings and does not depend on text transcriptions.
Approach: They propose a parallel speech document alignment method that monotonically aligns speech segment embeddings and does not depend on text transcriptions.
Outcome: The proposed method outperforms SpeechMatrix models on 3,000 hours of unlabeled speech documents and produces longer speech-to-speech alignments.
Neuralign: A Context-Aware, Cross-Lingual and Fully-Neural Sentence Alignment System for Long Texts (2024.eacl-long)

Copied to clipboard

Challenge: Existing sentence alignment systems focus on auxiliary information such as document metadata and hyperparameter-sensitive techniques, and neglect the crucial role that context plays in the alignment process.
Approach: They propose a context-aware, end-to-end and fully-neural architecture for sentence alignment that maps source and target sentences in long documents by contextualizing their sentence embeddings with respect to the other sentences in the document.
Outcome: The proposed system maps source and target sentences in long documents by contextualizing their sentence embeddings with respect to the other sentences in the document.
SentAlign: Accurate and Scalable Sentence Alignment (2023.emnlp-demo)

Copied to clipboard

Challenge: SentAlign is an automatic sentence alignment tool designed for large documents . it evaluates all possible alignment paths in documents of thousands of sentences .
Approach: They present a sentence alignment tool that evaluates all possible alignment paths in parallel documents of thousands of sentences and uses a divide-and-conquer approach to align documents containing tens of thousands.
Outcome: The proposed tool outperforms five other sentence alignment tools on two evaluation sets and on a downstream machine translation task.
Massively Multilingual Document Alignment with Cross-lingual Sentence-Mover’s Distance (2020.aacl-main)

Copied to clipboard

Challenge: Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other.
Approach: They propose an unsupervised scoring function that leverages cross-lingual sentence embeddings to compute the semantic distance between documents in different languages.
Outcome: The proposed scoring function outperforms baseline methods on high-resource language pairs, 15% on mid-resourced language pairs and 22% on low-resourcing language pairs.
Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast (2021.emnlp-main)

Copied to clipboard

Challenge: Existing work uses sentences within the same batch as negatives, which suffers from easy negatives.
Approach: They propose to align sentence representations from different languages into a unified embedding space . they adapt MoCo to further improve the quality of alignment .
Outcome: The proposed model achieves state-of-the-art on several tasks.
BinaryAlign: Word Alignment as Binary Sequence Labeling (2024.acl-long)

Copied to clipboard

Challenge: State-of-the-art word alignment training methods require a different class depending on the availability of gold data for a particular language pair.
Approach: They propose a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios.
Outcome: The proposed method outperforms existing models on non-English language pairs and performs stratified error analysis over alignment error type.
SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for automatic sentence alignment assume monotonic alignments, but they can handle non-monotonic alignments.
Approach: They propose a method to automatically extract parallel sentences from noisy parallel documents by embeddings and encoding each source and target sentence.
Outcome: The proposed method improves translation accuracy by 4.1 BLEU scores on English-Japanese . it can predict spans in target document from sentences in source document .
Understanding Cross-Lingual Alignment—A Survey (2024.findings-acl)

Copied to clipboard

Challenge: Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models.
Approach: They propose a taxonomy of methods to improve cross-lingual alignment . they argue that an effective trade-off between language-neutral and language-specific information is key .
Outcome: The proposed methods can be applied to encoder models and encoder-decoder-only models . they show that language-neutral and language-specific information is key .
A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space (2021.emnlp-main)

Copied to clipboard

Challenge: Cross-lingual language models house representations for many different languages in the same space.
Approach: They investigate linguistic and non-linguistic factors affecting sentence-level alignment in cross-lingual pretrained language models for 101 languages and 5,050 language pairs.
Outcome: The results show that word order agreement and agreement in morphological complexity are strongest predictors of cross-linguality.
Exploiting Sentence Order in Document Alignment (2020.emnlp-main)

Copied to clipboard

Challenge: a document alignment method that exploits sentence order information is beneficial even when the end goal is sentence-level bitext.
Approach: They propose a document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring.
Outcome: The proposed method outperforms the most recent document alignment method on Sinhala–English documents.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations