PNEL: Pointer Network Based End-To-End Entity Linking over Knowledge Graphs

Abstract

Question Answering systems are generally modelled as a pipeline consisting of a sequence of steps. In such a pipeline, Entity Linking (EL) is often the first step. Several EL models first perform span detection and then entity disambiguation. In such models errors from the span detection phase cascade to later steps and result in a drop of overall accuracy. Moreover, lack of gold entity spans in training data is a limiting factor for span detector training. Hence the movement towards end-to-end EL models began where no separate span detection step is involved. In this work we present a novel approach to end-to-end EL by applying the popular Pointer Network model, which achieves competitive performance. We demonstrate this in our evaluation over three datasets on the Wikidata Knowledge Graph.

Survey on English Entity Linking on Wikidata: Datasets and approaches

“…In comparison to other similar KGs, the Wikidata dumps are updated most frequently (Table 3). But note that this only applies to the dumps, if one considers direct access via the Website or a SPARQL endpoint, both, Wikidata 6,7 and DBpedia 8,9 provide continuously updated knowledge.…”

“…Many of the ambiguous mentions reference the most popular one, while also many exact unique matches exist. T-REx, the Kensho Derived ISTEX-1000 [24] 2 [ 24,77] LC-QuAD 2.0 [27] 2 [ 8,100] Knowledge Net [23] 1 [ 69] KORE50DYWC [80] 0…”

“…The vast majority of methods is using machine learning to solve the EL task [8,15,16,18,24,53,60,65,77,78,86,89,105]. Some of those approaches solve the ER and EL jointly as an end-to-end task.…”

“…PNEL [8] is an end-to-end (E2E) model jointly solving ER and EL focused on short texts. PNEL employs a Pointer network [118] working on a set of different features.…”

“…Of all approaches, only two algorithms [8,53] use descriptions explicitly. Others incorporate them through triples too, but more on the side [77].…”