Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. First, as recent improvements in entity linking suggest learning mention detection explicitly could increase performance, we train mention detection as an auxiliary task. Second, previous work suggests that re-ranking could help correct prediction errors. We add a new, auxiliary task, match prediction, to learn re-ranking. Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain. We show through ablation studies that each of the two auxiliary tasks increases performance, and that re-ranking is an important factor to the increase. Finally, our low-resource experimental results suggest that performance on the main task benefits from the knowledge learned by the auxiliary tasks, and not just from the additional training data.
Code (0)
등록된 구현이 없습니다.
Tasks
Entity LinkingRe-RankingSimilar Papers 제목 키워드 기반
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. Fir…
DecoderEntity LinkingRe-RankingHighly Parallel Autoregressive Entity Linking with Discriminative Correction
Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the previously proposed autoregressive formula…
DecoderEntity DisambiguationEntity LinkingNeural Entity Linking: A Survey of Models Based on Deep Learning
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing. Its goal is to systemize de…
Deep LearningEntity EmbeddingsEntity LinkingSurveyEntity Linking with a Paraphrase Flavor
The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions. Ambiguous, misspelled, and incomplete entity mention names are the mai…
ClusteringDiagnosticEntity DisambiguationEntity LinkingContextualized End-to-End Neural Entity Linking
We propose yet another entity linking model (YELM) which links words to entities instead of spans. This overcomes any difficulties associated with the selection of good candidate mention spans and makes the joint trainin…
Entity DisambiguationEntity LinkingWord Embeddings