CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
Large language models have demonstrated the capability to perform on machine translation when the input is prompted with a few examples (in-context learning). Translation quality depends on various features of the selected examples, such as their quality and relevance, but previous work has predominantly focused on individual features in isolation. In this paper, we propose a general framework for combining different features influencing example selection. We learn a regression model, CTQ Scorer (Contextual Translation Quality), that selects examples based on multiple features in order to maximize the translation quality. On multiple language pairs and language models, we show that CTQ Scorer helps significantly outperform random selection as well as strong single-factor baselines reported in the literature. We also see an improvement of over 2.5 COMET points on average with respect to a strong BM25 retrieval-based baseline.
Code (1)
Tasks
In-Context LearningMachine TranslationRetrievalTranslationSimilar Papers 제목 키워드 기반
Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation
In-context learning (ICL) is the trending prompting strategy in the era of large language models (LLMs), where a few examples are demonstrated to evoke LLMs' power for a given task. How to select informative examples rem…
In-Context LearningMachine TranslationTranslationCombining Multiple Views for Visual Speech Recognition
Visual speech recognition is a challenging research problem with a particular practical application of aiding audio speech recognition in noisy scenarios. Multiple camera setups can be beneficial for the visual speech re…
Sentencespeech-recognitionSpeech RecognitionVisual Speech RecognitionImproving RAG for Personalization with Author Features and Contrastive Examples
Personalization with retrieval-augmented generation (RAG) often fails to capture fine-grained features of authors, making it hard to identify their unique traits. To enrich the RAG context, we propose providing Large Lan…
RAGRetrieval-augmented GenerationText GenerationEfficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
Many-shot in-context learning has recently shown promise as an alternative to finetuning, with the major advantage that the same model can be served for multiple tasks. However, this shifts the computational burden from …
In-Context LearningRetrievalNamed entity recognition architecture combining contextual and global features
Named entity recognition (NER) is an information extraction technique that aims to locate and classify named entities (e.g., organizations, locations,...) within a document into predefined categories. Correctly identifyi…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER