Towards Effective Disambiguation for Machine Translation with Large Language Models
This addresses a central challenge in machine translation for users needing accurate translations of ambiguous sentences, representing an incremental improvement over existing methods.
The paper tackled the problem of semantic ambiguity in machine translation by improving large language models' disambiguation capabilities through in-context learning and fine-tuning on curated datasets, achieving results that match or outperform state-of-the-art systems like DeepL and NLLB in four out of five language directions.
Resolving semantic ambiguity has long been recognised as a central challenge in the field of Machine Translation. Recent work on benchmarking translation performance on ambiguous sentences has exposed the limitations of conventional Neural Machine Translation (NMT) systems, which fail to handle many such cases. Large language models (LLMs) have emerged as a promising alternative, demonstrating comparable performance to traditional NMT models while introducing new paradigms for controlling the target outputs. In this paper, we study the capabilities of LLMs to translate "ambiguous sentences" - i.e. those containing highly polysemous words and/or rare word senses. We also propose two ways to improve their disambiguation capabilities, through a) in-context learning and b) fine-tuning on carefully curated ambiguous datasets. Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions. Our research provides valuable insights into effectively adapting LLMs to become better disambiguators during Machine Translation. We release our curated disambiguation corpora and resources at https://data.statmt.org/ambiguous-europarl.