2000 character limit reached
Rethinking Human-like Translation Strategy: Integrating Drift-Diffusion Model with Large Language Models for Machine Translation
Published 16 Feb 2024 in cs.CL | (2402.10699v1)
Abstract: LLMs have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation has mainly focused on better utilizing training data, demonstrations, or pre-defined and universal knowledge to improve performance, with a lack of consideration of decision-making like human translators. In this paper, we incorporate Thinker with the Drift-Diffusion Model (Thinker-DDM) to address this issue. We then redefine the Drift-Diffusion process to emulate human translators' dynamic decision-making under constrained resources. We conduct extensive experiments under the high-resource, low-resource, and commonsense translation settings using the WMT22 and CommonMT datasets, in which Thinker-DDM outperforms baselines in the first two scenarios. We also perform additional analysis and evaluation on commonsense translation to illustrate the high effectiveness and efficacy of the proposed method.
- In-context examples selection for machine translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics.
- The physics of optimal decision making: a formal analysis of models of performance in two-alternative forced-choice tasks. Psychological review, 113(4):700.
- Language models are few-shot learners.
- Language models show human-like content effects on reasoning tasks.
- The devil is in the errors: Leveraging large language models for fine-grained machine translation evaluation. In Proceedings of the Eighth Conference on Machine Translation, pages 1066–1083, Singapore. Association for Computational Linguistics.
- Apertium: A free/open-source platform for rule-based machine translation. Machine Translation, 25(2):127–144.
- Gptscore: Evaluate as you desire.
- Dictionary-based phrase-level prompting of large language models for machine translation.
- The box is in the pen: Evaluating commonsense reasoning in neural machine translation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3662–3672, Online. Association for Computational Linguistics.
- Exploring human-like translation strategy with large language models.
- How good are gpt models at machine translation? a comprehensive evaluation.
- Towards effective disambiguation for machine translation with large language models. In Proceedings of the Eighth Conference on Machine Translation, pages 482–495, Singapore. Association for Computational Linguistics.
- Mistral 7b.
- Daniel Kahneman. 2011. Thinking, fast and slow. macmillan.
- Findings of the 2022 conference on machine translation (WMT22). In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 1–45, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Moses: Open source toolkit for statistical machine translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pages 177–180, Prague, Czech Republic. Association for Computational Linguistics.
- Statistical phrase-based translation. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 127–133.
- Llm-powered hierarchical language agent for real-time human-ai coordination.
- Chain-of-dictionary prompting elicits translation in large language models.
- Enriching the transfer learning with pre-trained lexicon embedding for low-resource neural machine translation. Tsinghua Science and Technology, 27(1):150–163.
- Zhuoyuan Mao and Yen Yu. 2024. Tuning llms with contrastive alignment instructions for machine translation in unseen, low-resource languages.
- Domain-specific text generation for machine translation. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 14–30, Orlando, USA. Association for Machine Translation in the Americas.
- Adaptive machine translation with large language models. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 227–237, Tampere, Finland. European Association for Machine Translation.
- Fine-tuning large language models for adaptive machine translation.
- Domain terminology integration into machine translation: Leveraging large language models. In Proceedings of the Eighth Conference on Machine Translation, pages 902–911, Singapore. Association for Computational Linguistics.
- Introducing translation studies: Theories and applications. Routledge.
- Eugene Albert Nida. 1964. Toward a science of translating: with special reference to principles and procedures involved in Bible translating. Brill Archive.
- Gpt-4 technical report.
- Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
- When does in-context learning fall short and why? a study on specification-heavy tasks.
- Roger Ratcliff. 1978. A theory of memory retrieval. Psychological Review, 85:59–108.
- Diffusion decision model: Current issues and history. Trends in Cognitive Sciences, 20:260–281.
- Leveraging GPT-4 for automatic translation post-editing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12009–12024, Singapore. Association for Computational Linguistics.
- Prompting neural machine translation with translation memories. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11):13519–13527.
- COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 578–585, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- CometKiwi: IST-unbabel 2022 submission for the quality estimation shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 634–645, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Neural machine translation models can learn to be few-shot learners.
- Katharina Reiss. 1989. Text types, translation types and translation assessment. Readings in translation theory, 19771989.
- Katharina Reiß and Hans J Vermeer. 2010. Grundlegung einer allgemeinen Translationstheorie, volume 147. Walter de Gruyter.
- E. Rowland. 1946. Theory of games and economic behavior. Nature, 157:172–173.
- A critical review of translation: A look forward. International Journal of Education and Literacy Studies, 6(2):101–110.
- RAMP: Retrieval and attribute-marking enhanced prompting for attribute-controlled translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1476–1490, Toronto, Canada. Association for Computational Linguistics.
- BLEURT: Learning robust metrics for text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7881–7892, Online. Association for Computational Linguistics.
- Duma: a dual-mind conversational agent with fast and slow thinking.
- Llama: Open and efficient foundation language models.
- Llama 2: Open foundation and fine-tuned chat models.
- Prompting PaLM for translation: Assessing strategies and performance. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15406–15427, Toronto, Canada. Association for Computational Linguistics.
- Domino: A dual-system for multi-step visual language reasoning.
- Element-aware summarization with large language models: Expert-aligned evaluation and chain-of-thought method. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8640–8665, Toronto, Canada. Association for Computational Linguistics.
- Humanoid agents: Platform for simulating human-like generative agents.
- Generating valid and natural adversarial examples with large language models.
- Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
- Jason Weston and Sainbayar Sukhbaatar. 2023. System 2 attention (is something you might need too).
- Bigtranslate: Augmenting large language models with multilingual translation capability over 100 languages.
- Tree of Thoughts: Deliberate problem solving with large language models.
- GLM-130b: An open bilingual pre-trained model. In The Eleventh International Conference on Learning Representations.
- Bayling: Bridging cross-lingual alignment and instruction following through interactive translation for large language models.
- Opt: Open pre-trained transformer language models.
- Self-supervised quality estimation for machine translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3322–3334, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Multilingual machine translation with large language models: Empirical results and analysis.
- Extrapolating large language models to non-english by aligning languages.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
