Lune

EMNLP Findings2022

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

Jannis Vamvas, Rico Sennrich

Abstract

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. 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation cites Unsupervised Cross-lingual Representation Learning at Scale
  • Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing cites BERTScore: Evaluating Text Generation with BERT
  • Multilingual AMR-to-Text Generation cites Unsupervised Cross-lingual Representation Learning at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine TranslationYuqiao Wen, Behzad Shayegh, Chenyang Huang, Yanshuai Cao et al.AAAI 2025 · 8 citations

Builds on5

  1. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  2. Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary et al.ACL 2020 · 539 citations
  3. Making Monolingual Sentence Embeddings Multilingual using Knowledge DistillationNils Reimers, Iryna GurevychEMNLP 2020 · 54 citations
  4. Multilingual AMR-to-Text GenerationAngela Fan, Claire GardentEMNLP 2020 · 25 citations
  5. Automatic Machine Translation Evaluation in Many Languages via Zero-Shot ParaphrasingBrian Thompson, Matt PostEMNLP 2020 · 7 citations

Related papers

  1. BLEU might be Guilty but References are not InnocentMarkus Freitag, David Grangier, Isaac CaswellEMNLP 2020 · 13 citations
  2. Towards Multiple References Era - Addressing Data Leakage and Limited Reference Diversity in Machine Translation EvaluationXianfeng Zeng, Yijin Liu, Fandong Meng, Jie ZhouACL Findings 2024 · 2 citations
  3. Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational LensDavid Stap, Vlad Niculae, Christof MonzEMNLP Findings 2023 · 4 citations
  4. Principled Paraphrase Generation with Parallel CorporaAitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka et al.ACL 2022 · 12 citations
  5. Robustness Tests for Automatic Machine Translation Metrics with Adversarial AttacksYichen Huang, Timothy BaldwinEMNLP Findings 2023
Dusk over the sea between two cliffs drawn in fine vertical lines