A Context-aware Framework for Translation-mediated Conversations

• URL: http://arxiv.org/abs/2412.04205v1
• Date: Thu, 05 Dec 2024 14:41:05 GMT
• Title: A Context-aware Framework for Translation-mediated Conversations
• Authors: José Pombal, Sweta Agrawal, Patrick Fernandes, Emmanouil Zaranis, André F. T. Martins,
• Abstract summary: We present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings. We validate both components of our framework on two task-oriented domains: customer chat and user-assistant interaction. Our framework consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct.
• Score: 29.169155271343083
• License:
• Abstract: Effective communication is fundamental to any interaction, yet challenges arise when participants do not share a common language. Automatic translation systems offer a powerful solution to bridge language barriers in such scenarios, but they introduce errors that can lead to misunderstandings and conversation breakdown. A key issue is that current systems fail to incorporate the rich contextual information necessary to resolve ambiguities and omitted details, resulting in literal, inappropriate, or misaligned translations. In this work, we present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings. During training, we leverage context-augmented parallel data, which allows the model to generate translations sensitive to conversational history. During inference, we perform quality-aware decoding with context-aware metrics to select the optimal translation from a pool of candidates. We validate both components of our framework on two task-oriented domains: customer chat and user-assistant interaction. Across both settings, our framework consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct, as measured by multiple automatic translation quality metrics on several language pairs. We also show that the resulting model leverages context in an intended and interpretable way, improving consistency between the conveyed message and the generated translations.

Related papers

• Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History [10.596661157821462]
  We propose a context-aware LLM translation system for the English-Korean language pair. Our approach incorporates the two most recent dialogues as raw data and a summary of earlier conversations to manage context length effectively.
  arXiv  Detail & Related papers  (2024-10-22T07:45:18Z)
• Context-aware Neural Machine Translation for English-Japanese Business Scene Dialogues [14.043741721036543]
  This paper explores how context-awareness can improve the performance of the current Neural Machine Translation (NMT) models for English-Japanese business dialogues translation. We propose novel context tokens encoding extra-sentential information, such as speaker turn and scene type. We find that models leverage both preceding sentences and extra-sentential context (with CXMI increasing with context size) and we provide a more focused analysis on honorifics translation.
  arXiv  Detail & Related papers  (2023-11-20T18:06:03Z)
• Challenges in Context-Aware Neural Machine Translation [39.89082986080746]
  Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve discourse dependencies. Despite well-reasoned intuitions, most context-aware translation models show only modest improvements over sentence-level systems. We propose a more realistic setting for document-level translation, called paragraph-to-paragraph (para2para) translation.
  arXiv  Detail & Related papers  (2023-05-23T07:08:18Z)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation [70.81596088969378]
  Cross-lingual Outline-based Dialogue dataset (termed COD) enables natural language understanding. COD enables dialogue state tracking, and end-to-end dialogue modelling and evaluation in 4 diverse languages.
  arXiv  Detail & Related papers  (2022-01-31T18:11:21Z)
• When Does Translation Require Context? A Data-driven, Multilingual Exploration [71.43817945875433]
  proper handling of discourse significantly contributes to the quality of machine translation (MT) Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation. We develop the Multilingual Discourse-Aware benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena.
  arXiv  Detail & Related papers  (2021-09-15T17:29:30Z)
• Modeling Bilingual Conversational Characteristics for Neural Chat Translation [24.94474722693084]
  We aim to promote the translation quality of conversational text by modeling the above properties. We evaluate our approach on the benchmark dataset BConTrasT (English-German) and a self-collected bilingual dialogue corpus, named BMELD (English-Chinese) Our approach notably boosts the performance over strong baselines by a large margin and significantly surpasses some state-of-the-art context-aware NMT models in terms of BLEU and TER.
  arXiv  Detail & Related papers  (2021-07-23T12:23:34Z)
• Robustness Testing of Language Understanding in Dialog Systems [33.30143655553583]
  We conduct comprehensive evaluation and analysis with respect to the robustness of natural language understanding models. We introduce three important aspects related to language understanding in real-world dialog systems, namely, language variety, speech characteristics, and noise perturbation. We propose a model-agnostic toolkit LAUG to approximate natural perturbation for testing the robustness issues in dialog systems.
  arXiv  Detail & Related papers  (2020-12-30T18:18:47Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)
• Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation [59.38247587308604]
  We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation. We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T dataset. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models.
  arXiv  Detail & Related papers  (2020-03-30T21:35:09Z)

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.