paper-with-me

홈 › Papers

CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation

2023-05-23 · Aswanth Kumar, Ratish Puduppully, Raj Dabre, Anoop Kunchukuttan

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.

📄 PDF Abstract BibTeX arXiv:2305.14105

Code (1)

ai4bharat/ctqscorer 공식 구현 pytorch

Tasks

In-Context LearningMachine TranslationRetrievalTranslation

Similar Papers 제목 키워드 기반

Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation

2024-03-28 · Chenming Tang, Zhixiang Wang, Yunfang Wu

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 TranslationTranslation

Combining Multiple Views for Visual Speech Recognition

2017-10-19 · Marina Zimmermann, Mostafa Mehdipour Ghazi, Hazim Kemal Ekenel, Jean-Philippe Thiran

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 Recognition

Improving RAG for Personalization with Author Features and Contrastive Examples

2025-03-24 · Mert Yazan, Suzan Verberne, Frederik Situmeang

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 Generation

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention

2025-03-11 · Emily Xiao, Chin-Jou Li, Yilin Zhang, Graham Neubig 외

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 LearningRetrieval

Named entity recognition architecture combining contextual and global features

2021-12-15 · Tran Thi Hong Hanh, Antoine Doucet, Nicolas Sidere, Jose G. Moreno 외

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