Are Large Language Models Robust Coreference Resolvers?
Recent work on extending coreference resolution across domains and languages relies on annotated data in both the target domain and language. At the same time, pre-trained large language models (LMs) have been reported to exhibit strong zero- and few-shot learning abilities across a wide range of NLP tasks. However, prior work mostly studied this ability using artificial sentence-level datasets such as the Winograd Schema Challenge. In this paper, we assess the feasibility of prompt-based coreference resolution by evaluating instruction-tuned language models on difficult, linguistically-complex coreference benchmarks (e.g., CoNLL-2012). We show that prompting for coreference can outperform current unsupervised coreference systems, although this approach appears to be reliant on high-quality mention detectors. Further investigations reveal that instruction-tuned LMs generalize surprisingly well across domains, languages, and time periods; yet continued fine-tuning of neural models should still be preferred if small amounts of annotated examples are available.
Code (1)
Tasks
coreference-resolutionCoreference ResolutionDomain AdaptationFew-Shot LearningSentenceZero-Shot LearningSimilar Papers 제목 키워드 기반
Rewarding Coreference Resolvers for Being Consistent with World Knowledge
Unresolved coreference is a bottleneck for relation extraction, and high-quality coreference resolvers may produce an output that makes it a lot easier to extract knowledge triples. We show how to improve coreference res…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Relation+2Lexical Features in Coreference Resolution: To be Used With Caution
Lexical features are a major source of information in state-of-the-art coreference resolvers. Lexical features implicitly model some of the linguistic phenomena at a fine granularity level. They are especially useful for…
coreference-resolutionCoreference ResolutionEvaluation of Coreference Resolution Systems Under Adversarial Attacks
A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution. This is because the CoNLL benchmark fails to evaluate the ability of coreference resolvers that r…
coreference-resolutionCoreference ResolutionEvaluating Coreference Resolvers on Community-based Question Answering: From Rule-based to State of the Art
Coreference resolution is a key step in natural language understanding. Developments in coreference resolution are mainly focused on improving the performance on standard datasets annotated for coreference resolution. Ho…
Answer Selectioncoreference-resolutionCoreference ResolutionNatural Language Understanding+1Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers
Coreference resolution is an intermediate step for text understanding. It is used in tasks and domains for which we do not necessarily have coreference annotated corpora. Therefore, generalization is of special importanc…
coreference-resolutionCoreference Resolution