Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction

ACL ARR 2026 January Submission5655 Authors

Keywords: Low-resource languages, Distant Supervision, LLMs

Abstract:

Distantly Supervised Relation Extraction (DSRE) remains a long-standing challenge in NLP, where models must learn from noisy bag-level annotations while making sentence-level predictions. While existing state-of-the-art (SoTA) DSRE models rely on task-specific training, their integration with in-context learning (ICL) using large language models (LLMs) remains underexplored. A key challenge is that the LLM may not learn relation semantics correctly, due to noisy annotation.

In response, we propose $HYDRE$ - $HY$brid $D$istantly Supervised $R$elation $E$xtraction framework. It first uses a trained DSRE model to identify the top-$k$ candidate relations for a given test sentence, then uses a novel dynamic exemplar retrieval strategy that extracts reliable, sentence-level exemplars from training data, which are then provided in LLM prompt for outputting the final relation(s).

We further extend $HYDRE$ to cross-lingual settings for RE in low-resource languages. Using available English DSRE training data, we evaluate all methods on English as well as a newly curated benchmark covering four diverse low-resource Indic languages - Oriya, Santali, Manipuri, and Tulu. $HYDRE$ achieves up to 20 F1 point gains in English and, on average, 17 F1 points on Indic languages over prior SoTA DSRE models and naive prompting baselines. Detailed ablations exhibit $HYDRE$'s efficacy compared to other prompting strategies.

Paper Type: Long

Research Area: Multilinguality and Language Diversity

Research Area Keywords: Multilingualism and Cross-Lingual NLP, Information Extraction

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Data resources

Languages Studied: English, Santali, Manipuri, Tulu, Oriya

Submission Number: 5655