LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation
Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundational step in tasks such as knowledge graph construction, question-answering, and information extraction. Our method, LELA, is a modular coarse-to-fine approach that leverages the capabilities of large language models (LLMs), and works with different target domains, knowledge bases and LLMs, without any fine-tuning phase. Our experiments across various entity linking settings show that LELA is highly competitive with fine-tuned approaches, and substantially outperforms the non-fine-tuned ones.
Code (0)
등록된 구현이 없습니다.
Tasks
Information ExtractionDomain AdaptationEntity LinkingSimilar Papers 제목 키워드 기반
LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
Entity linking is a key component of many downstream NLP systems, yet existing approaches are often tied to the specific target knowledge bases and domains, limiting their real world application. In this paper, we extend…
Entity DisambiguationDomain AdaptationEntity LinkingImproving Zero-Shot Entity Linking Candidate Generation with Ultra-Fine Entity Type Information
Entity linking, which aims at aligning ambiguous entity mentions to their referent entities in a knowledge base, plays a key role in multiple natural language processing tasks. Recently, zero-shot entity linking task has…
Entity LinkingEntity TypingVocal Bursts Type PredictionA Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking
Recent interest in entity linking has focused in the zero-shot scenario, where at test time the entity mention to be labelled is never seen during training, or may belong to a different domain from the source domain. Cur…
Entity LinkingTrainX -- Named Entity Linking with Active Sampling and Bi-Encoders
We demonstrate TrainX, a system for Named Entity Linking for medical experts. It combines state-of-the-art entity recognition and linking architectures, such as Flair and fine-tuned Bi-Encoders based on BERT, with an eas…
Entity LinkingReal World Conversational Entity Linking Requires More Than Zeroshots
Entity linking (EL) in conversations faces notable challenges in practical applications, primarily due to the scarcity of entity-annotated conversational datasets and sparse knowledge bases (KB) containing domain-specifi…
Entity Linking