PNEL: Pointer Network based End-To-End Entity Linking over Knowledge Graphs
This work addresses a bottleneck in question answering systems by eliminating the need for separate span detection, which is incremental as it applies an existing model to a known problem.
The paper tackles the problem of error propagation in entity linking pipelines by proposing an end-to-end approach using Pointer Networks, achieving competitive performance on three Wikidata datasets.
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.