Challenge: Existing studies on document-level neural machine translation (NMT) assume that all repeated source words should be translated consistently.
Approach: They construct a test set of 310 bilingual news articles to evaluate lexical translation consistency.
Outcome: The proposed test sets show that translation consistency is consistent across multiple languages.

Similar Papers

Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Experimental results show document-level neural machine translation improves lexical consistency . inconsistent translations tend to confuse readers in some cases .
Approach: They propose to use a word link to obtain a document word link and an auxiliary loss function to constrain that their translation should be consistent.
Outcome: The proposed approach improves translation consistency on ChineseEnglish and EnglishFrench translation tasks.
Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that consistency preference for lexical chains reduces lexical translation inconsistency . Lexical translation consistency is a common discourse phenomenon .
Approach: They propose a consistency-aware model which captures consistency context . they then define consistency-tailored latent variables which guide translation of corresponding sentences .
Outcome: The proposed model significantly improves translation performance in ChineseEnglish and FrenchEnglish translation tasks.
Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective (2024.findings-emnlp)

Copied to clipboard

Challenge: a cognitive science research focus on aligning language spaces in their entirety . but, cognitive science has long focused on a local perspective . a new method for cross-lingual lexical alignment requires some methodology .
Approach: They propose a method for analyzing kinship domain kinematics and a new method for contextualization . they propose kin-level validations and contextualizations to validate the results .
Outcome: The proposed method analyzes synthetic validations and naturalistic validations using lexical gaps in the kinship domain.
Lexical Translation Inconsistency-Aware Document-Level Translation Repair (2023.findings-acl)

Copied to clipboard

Challenge: Experimental results show document-level translation repair improves translation consistency but still suffers from lexical translation inconsistency due to the lack of inter-sentence context.
Approach: They propose a document-level translation repair model to model translation inconsistency via automatic post-editing.
Outcome: The proposed model improves translation quality and lexical consistency on document-level translation datasets.
On Search Strategies for Document-Level Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Document-level neural machine translation models produce a more consistent output across a document . however, the exact decoding strategy is often not described and not mentioned at all.
Approach: They propose to use standard automatic metrics and specific linguistic phenomena to compare different decoding schemes.
Outcome: The proposed decoding strategies perform similar to each other on three standard document-level translation benchmarks.
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion (P19-1)

Copied to clipboard

Challenge: et al., 2018: translation errors due to the lack of extra-sentential context are becoming more and more noticeable among otherwise adequate translations.
Approach: They propose a context-aware translation model that uses sentence-level data to identify inconsistencies . standard metrics are not sensitive to improvements in consistency in document-level translations .
Outcome: The proposed model shows major gains over baseline without sacrificing performance . standard metrics are not sensitive to improvements in document-level translations .
Test Sets for Chinese Nonlocal Dependency Parsing (L18-1)

Copied to clipboard

Challenge: Chinese is a language rich in nonlocal dependencies.
Approach: They use trace annotations in the Penn Chinese Treebank to generate test sets of Chinese nonlocal dependencies which occur in different grammatical constructions.
Outcome: The proposed test sets can be used to evaluate nonlocal dependency recovery in Chinese.
Very Large-Scale Lexical Resources to Enhance Chinese and Japanese Machine Translation (L18-1)

Copied to clipboard

Challenge: A major issue in machine translation applications is the recognition and translation of named entities.
Approach: They propose to integrate Very Large-Scale Lexical Resources (VLSLR) with lexicons to improve machine translation accuracy.
Outcome: The proposed lexical resources can enhance the quality of MT in general and NMT systems, which currently don't use lexicons.
Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent? (2025.findings-emnlp)

Copied to clipboard

Challenge: Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain factuality of model knowledge across languages, and preserve parity of language model performance.
Approach: They examine pretrained and tuned models with code-mixed coreferential statements that convey identical knowledge across languages.
Outcome: The proposed model shows different levels of consistency in multilingual models, subject to language families, linguistic factors, scripts, and bottlenecks on a particular layer.
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for speech-to-text translation (ST) have achieved impressive supervised and zero-shot performance.
Approach: They propose to use consistency regularization methods to boost end-to-end (E2E) speech-totext translation (ST) by regularizing the intra-modal consistency instead of the modality gap.
Outcome: The proposed training strategies achieve state-of-the-art (SOTA) performance in most translation directions.

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