Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy

• URL: http://arxiv.org/abs/2606.29489v1
• Date: Sun, 28 Jun 2026 16:39:09 GMT
• Title: Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy
• Abstract summary: We propose a model-agnostic framework to quantify context sensitivity at lexical and syntactic levels.<n>We show that context selectively redistributes generative responsibility from source to context tokens without altering overall fertility.<n>Our framework provides a ground-truth characterisation of selective context usage in human translation, establishing a diagnostic baseline for evaluating machine translation models.
• Score: 28.838326003809176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When humans translate, not every word depends equally on the surrounding context. Some tokens, particularly function words like pronouns and auxiliaries, rely heavily on preceding or following sentences, while others, such as proper nouns, do not. Understanding this inherent context sensitivity is essential for evaluating whether machine translation systems use context in human-like ways. However, existing approaches to analysing context usage rely on discourse-specific test sets or model internals, making them narrow or model-dependent. We propose a post-hoc, model-agnostic framework to quantify context sensitivity at lexical and syntactic levels using two measures derived from word alignments: fertility (number of target tokens generated per source token) and entropy (stability of fertility patterns across contexts). Using reference translations for three language pairs (German $\leftrightarrow$ English, English $\rightarrow$ Hindi) under four context conditions, we show that context selectively redistributes generative responsibility from source to context tokens without altering overall fertility. Function words show the largest fertility reductions, while content words remain stable, suggesting that context resolves ambiguity rather than adding new information. Our framework provides a ground-truth characterisation of selective context usage in human translation, establishing a diagnostic baseline for evaluating machine translation models.

Related papers

• Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering [68.3400058037817]
  We introduce TREQA (Translation Evaluation via Question-Answering), a framework that extrinsically evaluates translation quality.<n>We show that TREQA is competitive with and, in some cases, outperforms state-of-the-art neural and LLM-based metrics in ranking alternative paragraph-level translations.
  arXiv  Detail & Related papers  (2025-04-10T09:24:54Z)
• Evaluating Distributed Representations for Multi-Level Lexical Semantics: A Research Proposal [3.3585951129432323]
  This thesis builds a bridge between computational models and lexical semantics, aiming to complement each other.<n>Modern neural networks (NNs) construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors.
  arXiv  Detail & Related papers  (2024-06-02T14:08:51Z)
• On Measuring Context Utilization in Document-Level MT Systems [12.02023514105999]
  We propose to complement accuracy-based evaluation with measures of context utilization. We show that automatically-annotated supporting context gives similar conclusions to human-annotated context.
  arXiv  Detail & Related papers  (2024-02-02T13:37:07Z)
• That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? [64.38544995251642]
  We study semantic ambiguities that exist in the source (English in this work) itself. We focus on idioms that are open to both literal and figurative interpretations. We find that current MT models consistently translate English idioms literally, even when the context suggests a figurative interpretation.
  arXiv  Detail & Related papers  (2023-10-23T06:38:49Z)
• Quantifying the Plausibility of Context Reliance in Neural Machine Translation [25.29330352252055]
  We introduce Plausibility Evaluation of Context Reliance (PECoRe) PECoRe is an end-to-end interpretability framework designed to quantify context usage in language models' generations. We use pecore to quantify the plausibility of context-aware machine translation models.
  arXiv  Detail & Related papers  (2023-10-02T13:26:43Z)
• HanoiT: Enhancing Context-aware Translation via Selective Context [95.93730812799798]
  Context-aware neural machine translation aims to use the document-level context to improve translation quality. The irrelevant or trivial words may bring some noise and distract the model from learning the relationship between the current sentence and the auxiliary context. We propose a novel end-to-end encoder-decoder model with a layer-wise selection mechanism to sift and refine the long document context.
  arXiv  Detail & Related papers  (2023-01-17T12:07:13Z)
• Language model acceptability judgements are not always robust to context [30.868765627701457]
  We investigate the stability of language models' performance on targeted syntactic evaluations. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts. We show that these changes in model performance are not explainable by simple features matching the context and the test inputs.
  arXiv  Detail & Related papers  (2022-12-18T00:11:06Z)
• Do Context-Aware Translation Models Pay the Right Attention? [61.25804242929533]
  Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. In this paper, we ask several questions: What contexts do human translators use to resolve ambiguous words? We introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context words for 14K translations. Using SCAT, we perform an in-depth analysis of the context used to disambiguate, examining positional and lexical characteristics of the supporting words.
  arXiv  Detail & Related papers  (2021-05-14T17:32:24Z)
• Measuring and Increasing Context Usage in Context-Aware Machine Translation [64.5726087590283]
  We introduce a new metric, conditional cross-mutual information, to quantify the usage of context by machine translation models. We then introduce a new, simple training method, context-aware word dropout, to increase the usage of context by context-aware models.
  arXiv  Detail & Related papers  (2021-05-07T19:55:35Z)
• Decontextualization: Making Sentences Stand-Alone [13.465459751619818]
  Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context. Taking excerpts of text can be problematic, as key pieces may not be explicit in a local window. We define the problem of sentence decontextualization: taking a sentence together with its context and rewriting it to be interpretable out of context.
  arXiv  Detail & Related papers  (2021-02-09T22:52:37Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.