ExtEnD: Extractive Entity Disambiguation

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 2478 - 2488 May 22-27, 2022 c⃝2022 Association for Computational Linguistics ExtEnD: Extractive Entity Disambiguation Edoardo Barba∗and Luigi Procopio∗and Roberto Navigli Sapienza NLP Group, Sapienza University of Rome {edoardo.barba, luigi.procopio, roberto.navigli}@uniroma1.it Abstract Local models for Entity Disambiguation (ED) have today become extremely powerful, in most part thanks to the advent of large pre- trained language models. However, despite their significant performance achievements, most of these approaches frame ED through classification formulations that have intrinsic limitations, both computationally and from a modeling perspective. In contrast with this trend, here we propose EXTEND, a novel lo- cal formulation for ED where we frame this task as a text extraction problem, and present two Transformer-based architectures that im- plement it. Based on experiments in and out of domain, and training over two different data regimes, we find our approach surpasses all its competitors in terms of both data efficiency and raw performance. EXTEND outperforms its al- ternatives by as few as 6 F1 points on the more constrained of the two data regimes and, when moving to the other higher-resourced regime, sets a new state of the art on 4 out of 6 bench- marks under consideration, with average im- provements of 0.7 F1 points overall and 1.1 F1 points out of domain. In addition, to gain better insights from our results, we also perform a fine-grained evaluation of our performances on different classes of label frequency, along with an ablation study of our architectural choices and an error analysis. We release our code and models for research purposes at https:// github.com/SapienzaNLP/extend. 1 Introduction Being able to associate entity mentions in a given text with the correct entity they refer to is a crucial task in Natural Language Processing (NLP). For- mally referred to as Entity Disambiguation (ED), this task entails, given a mention m occurring in a text cm, identifying the correct entity e∗ out of a set of candidates e1, . . . , en, coming from a reference knowledge base (KB). First introduced by Bunescu ∗ Equal contribution. and Pa¸sca (2006), ED aims to identify the actors in- volved in human language and, as such, has shown potential in downstream applications like Question Answering (Yin et al., 2016), Information Extrac- tion (Ji and Grishman, 2011; Guo et al., 2013), Text Generation (Puduppully et al., 2019) and Semantic Parsing (Bevilacqua et al., 2021; Procopio et al., 2021). Since the advent of Deep Learning within the NLP community, this task has mostly been framed as a multi-label classification problem (Shahbazi et al., 2019; Broscheit, 2019), especially lever- aging the bi-encoder paradigm (Humeau et al., 2020; Wu et al., 2020). However, although sim- ple and yet powerful enough to push scores past 90% inKB Micro F1 on standard benchmarks, this formulation suffers from a number of downsides. First, the actual disambiguation is only modeled through a dot product between independent men- tion and entity vectors, which …

Content truncated to 500 words