mlsanityData to 14 Oct 2026

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

arXiv 2204.13692 ↗First posted 28 Apr 2022cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation cross-likelihood, which has not been studied so far. We analyze these measures in the common framework of multilingual NMT, releasing the NMTScore library (available at https://github.com/ZurichNLP/nmtscore). Compared to baselines such as sentence embeddings, translation-based measures prove competitive in paraphrase identification and are more robust against adversarial or multilingual input, especially if proper normalization is applied. When used for reference-based evaluation of data-to-text generation in 2 tasks and 17 languages, translation-based measures show a relatively high correlation to human judgments.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

25 of 43 references.

References · 25

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  8. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  9. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
  10. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  11. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  12. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 264
13 more
  1. 2020Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasingcited by 115
  2. 2016Learning Distributed Representations of Sentences from Unlabelled Datacited by 91
  3. 2021A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methodscited by 72
  4. 2017Learning Joint Multilingual Sentence Representations with Neural Machine Translationcited by 52
  5. 2020Explicit Alignment Objectives for Multilingual Bidirectional Encoderscited by 50
  6. 2018Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corporacited by 40
  7. 2017Learning Paraphrastic Sentence Embeddings from Back-Translated Bitextcited by 27
  8. 2019Simple and Effective Paraphrastic Similarity from Parallel Translationscited by 25
  9. 2020SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metricscited by 18
  10. 2020Multilingual AMR-to-Text Generationcited by 12
  11. 2021Finnish Paraphrase Corpuscited by 10
  12. 2021Assessing Reference-Free Peer Evaluation for Machine Translationcited by 8
  13. 2018Are BLEU and Meaning Representation in Opposition?cited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 3; 2025: 1.

6 papers.

  1. 2022T-Projection: High Quality Annotation Projection for Sequence Labeling Taskscited by 14
  2. 2024Machine Translation Models are Zero-Shot Detectors of Translation Directioncited by 3
  3. 2023Multilingual Lexical Simplification via Paraphrase Generationcited by 1
  4. 2024EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translationcited by 1
  5. 2025Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languagescited by 1
  6. 2024Cogs in a Machine, Doing What They're Meant to Do -- The AMI Submission to the WMT24 General Translation Taskcited by 0