mlsanityData to 14 Oct 2026

Unbalanced Optimal Transport for Unbalanced Word Alignment

arXiv 2306.04116 ↗First posted 7 Jun 2023cs.CL cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 37 of its 84 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

37 of 84 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  5. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  6. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 834
  7. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  8. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 418
  9. 2015Learning with a Wasserstein Losscited by 196
  10. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  11. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 156
  12. 2020Neural CRF Model for Sentence Alignment in Text Simplificationcited by 106
25 more
  1. 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 97
  2. 2019Jointly Learning to Align and Translate with Transformer Modelscited by 75
  3. 2020Assessing Phrasal Representation and Composition in Transformerscited by 41
  4. 2016Scaling Algorithms for Unbalanced Transport Problemscited by 36
  5. 2021Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similaritycited by 35
  6. 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
  7. 2019Improving Sequence-to-Sequence Learning via Optimal Transportcited by 33
  8. 2020Word Rotator's Distancecited by 32
  9. 2017Structured Optimal Transportcited by 31
  10. 2021Unbalanced Optimal Transport through Non-negative Penalized Linear Regressioncited by 31
  11. 2020End-to-End Neural Word Alignment Outperforms GIZA++cited by 28
  12. 2020A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERTcited by 27
  13. 2020Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transportcited by 20
  14. 2021Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddingscited by 19
  15. 2021Neural semi-Markov CRF for Monolingual Word Alignmentcited by 16
  16. 2021QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositionscited by 16
  17. 2022Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learningcited by 13
  18. 2020Improving Text Generation with Student-Forcing Optimal Transportcited by 8
  19. 2020A Relaxed Matching Procedure for Unsupervised BLIcited by 8
  20. 2021iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Explorationcited by 8
  21. 2022OTExtSum: Extractive Text Summarisation with Optimal Transportcited by 8
  22. 2018Matching Natural Language Sentences with Hierarchical Sentence Factorizationcited by 5
  23. 2020Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distancecited by 5
  24. 2020Iterative Paraphrastic Augmentation with Discriminative Span Alignmentcited by 4
  25. 2022Unsupervised Sentence Textual Similarity with Compositional Phrase Semanticscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2024Submodular Framework for Structured-Sparse Optimal Transportcited by 5
  2. 2025Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judgecited by 1
  3. 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebookcited by 1
  4. 2026Grammatical Error Correction Evaluation by Optimally Transporting Edit Representationcited by 0
  5. 2026Hallucination Span Detection with Input-Side Evidence Alignmentcited by 0
  6. 2026Optimal transport meets speech: a tutorial reviewcited by 0