SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation
In-context learning (ICL) greatly improves the performance of large language models (LLMs) on various down-stream tasks, where the improvement highly depends on the quality of demonstrations. In this work, we introduce syntactic knowledge to select better in-context examples for machine translation (MT). We propose a new strategy, namely Syntax-augmented COverage-based In-context example selection (SCOI), leveraging the deep syntactic structure beyond conventional word matching. Specifically, we measure the set-level syntactic coverage by computing the coverage of polynomial terms with the help of a simplified tree-to-polynomial algorithm, and lexical coverage using word overlap. Furthermore, we devise an alternate selection approach to combine both coverage measures, taking advantage of syntactic and lexical information. We conduct experiments with two multi-lingual LLMs on six translation directions. Empirical results show that our proposed SCOI obtains the highest average COMET score among all learning-free methods, indicating that combining syntactic and lexical coverage successfully helps to select better in-context examples for MT. Our code is available at https://github.com/JamyDon/SCOI.
Code (1)
Tasks
In-Context LearningMachine TranslationTranslationSimilar Papers 제목 키워드 기반
A Note on Structural Controllability and Observability Indices
In this note, we investigate the structural controllability and observability indices of structured systems. We provide counter-examples showing that an existing graph-theoretic characterization for the structural contro…
Knowledge Graphs, the Missing Link in Agentic AI-based Formal Verification
Recent advances in Large Language Models (LLMs) have enabled workflows that generate SystemVerilog Assertions (SVAs) from natural-language specifications, with the potential to accelerate Formal Verification (FV). Howeve…
Arithmetic ReasoningKnowledge GraphsGoing 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 TranslationTranslationExemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers
The exemplar-free class incremental learning requires classification models to learn new class knowledge incrementally without retaining any old samples. Recently, the framework based on parallel one-class classifiers (P…
class-incremental learningClass Incremental LearningExemplar-FreeExemplar-Free Counting+2Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning
The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution …
Reinforcement Learning