Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

TL;DR

This paper introduces CARTON, a novel neural framework combining context transformers and stacked pointer networks for conversational question answering over large knowledge graphs, improving accuracy on complex queries.

Contribution

CARTON is a new multi-task semantic parsing framework that enhances conversational QA over knowledge graphs by integrating stacked pointer networks with context transformers.

Findings

Outperforms all baselines on a standard dataset for complex sequential QA.

Achieves an 11-point absolute improvement in logical reasoning questions.

Shows significant F1-score improvements in 8 out of 10 question types.

Abstract

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with complex queries and a large number of entities. In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph. Our framework consists of a stack of pointer networks as an extension of a context transformer model for parsing the input question and the dialog history. The framework generates a sequence of actions that can be executed on the knowledge graph. We evaluate CARTON on a standard dataset for complex sequential question answering on which CARTON outperforms all baselines. Specifically, we observe performance improvements in F1-score on eight out of ten question types compared to the previous state of the art. For logical reasoning questions, an improvement of 11 absolute points is reached.