Exploiting Sentence Order in Document Alignment
Not on the map. Why?
Abstract (arXiv)
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative reduction in error compared to the best previously published result on the WMT16 document alignment shared task. Our method improves downstream MT performance on web-scraped Sinhala--English documents from ParaCrawl, outperforming the document alignment method used in the most recent ParaCrawl release. It also outperforms a comparable corpora method which uses the same multilingual embeddings, demonstrating that exploiting sentence order is beneficial even if the end goal is sentence-level bitext.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Apr 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 3; 2023: 5; 2024: 3; 2025: 1; 2026: 1.
13 papers.
Sort:
- 2022Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metriccited by 56
- 2024A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelismcited by 33
- 2022Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbingcited by 17
- 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplificationcited by 14
- 2024Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?cited by 9
- 2022Domain Adaptation of Machine Translation with Crowdworkerscited by 3
- 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrievalcited by 3
- 2023End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translationcited by 2
- 2025BiMax: Bidirectional MaxSim Score for Document-Level Alignmentcited by 2
- 2023Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?cited by 1
- 2023Speaker Diarization of Scripted Audiovisual Contentcited by 1
- 2026A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translationcited by 1
1 more
- 2024Smart Bilingual Focused Crawling of Parallel Documentscited by 0
- 2026A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation13 Jun 2026
- 2025BiMax: Bidirectional MaxSim Score for Document-Level Alignment17 Oct 2025
- 2024Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?12 Oct 2024
- 2024Smart Bilingual Focused Crawling of Parallel Documents23 May 2024
- 2024A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism11 Jan 2024
- 2023End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation1 Nov 2023
- 2023Speaker Diarization of Scripted Audiovisual Content4 Aug 2023
- 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification30 May 2023
- 2023Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?28 Apr 2023
- 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval3 Feb 2023
- 2022Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing23 Dec 2022
- 2022Domain Adaptation of Machine Translation with Crowdworkers28 Oct 2022
- 2022Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metriccited by 56
- 2024A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelismcited by 33
- 2022Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbingcited by 17
- 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplificationcited by 14
- 2024Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?cited by 9
- 2022Domain Adaptation of Machine Translation with Crowdworkerscited by 3
- 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrievalcited by 3
- 2023End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translationcited by 2
- 2025BiMax: Bidirectional MaxSim Score for Document-Level Alignmentcited by 2
- 2023Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?cited by 1
- 2023Speaker Diarization of Scripted Audiovisual Contentcited by 1
- 2026A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translationcited by 1
12 most cited of 13 All 13 (JSON)
- 2026A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation13 Jun 2026
- 2025BiMax: Bidirectional MaxSim Score for Document-Level Alignment17 Oct 2025
- 2024Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?12 Oct 2024
- 2024Smart Bilingual Focused Crawling of Parallel Documents23 May 2024
- 2024A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism11 Jan 2024
- 2023End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation1 Nov 2023
- 2023Speaker Diarization of Scripted Audiovisual Content4 Aug 2023
- 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification30 May 2023
- 2023Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?28 Apr 2023
- 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval3 Feb 2023
- 2022Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing23 Dec 2022
- 2022Domain Adaptation of Machine Translation with Crowdworkers28 Oct 2022
12 newest of 13 All 13 (JSON)