Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs

TL;DR

This paper introduces a Multi-Sense LSTM model that effectively maps natural language to knowledge graph entities by addressing polysemy and leveraging semantic bridges, achieving state-of-the-art results in large-scale text-to-entity tasks.

Contribution

It proposes a novel Multi-Sense LSTM with dynamic disambiguation for improved text-to-entity mapping in knowledge graphs.

Findings

Achieves state-of-the-art performance on large-scale text-to-entity mapping.

Effectively handles polysemy with dynamic disambiguation.

Utilizes semantic bridges from graph walks to enhance mapping accuracy.

Abstract

This paper addresses the problem of mapping natural language text to knowledge base entities. The mapping process is approached as a composition of a phrase or a sentence into a point in a multi-dimensional entity space obtained from a knowledge graph. The compositional model is an LSTM equipped with a dynamic disambiguation mechanism on the input word embeddings (a Multi-Sense LSTM), addressing polysemy issues. Further, the knowledge base space is prepared by collecting random walks from a graph enhanced with textual features, which act as a set of semantic bridges between text and knowledge base entities. The ideas of this work are demonstrated on large-scale text-to-entity mapping and entity classification tasks, with state of the art results.