Generative Relation Linking for Question Answering over Knowledge Bases
This addresses a bottleneck in knowledge base question answering by enhancing relation linking performance, which is incremental but with strong gains.
The paper tackles relation linking for question answering over knowledge bases by proposing a generative approach using pre-trained sequence-to-sequence models infused with structured data, reporting large improvements over state-of-the-art methods on four datasets from DBpedia and Wikidata.
Relation linking is essential to enable question answering over knowledge bases. Although there are various efforts to improve relation linking performance, the current state-of-the-art methods do not achieve optimal results, therefore, negatively impacting the overall end-to-end question answering performance. In this work, we propose a novel approach for relation linking framing it as a generative problem facilitating the use of pre-trained sequence-to-sequence models. We extend such sequence-to-sequence models with the idea of infusing structured data from the target knowledge base, primarily to enable these models to handle the nuances of the knowledge base. Moreover, we train the model with the aim to generate a structured output consisting of a list of argument-relation pairs, enabling a knowledge validation step. We compared our method against the existing relation linking systems on four different datasets derived from DBpedia and Wikidata. Our method reports large improvements over the state-of-the-art while using a much simpler model that can be easily adapted to different knowledge bases.