Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Anonymous

Abstract: 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.