The reviewed record of science sign in
Pith

arxiv: 2312.17269 · v2 · pith:RGJ3BUUM · submitted 2023-12-27 · cs.CL · cs.AI

Conversational Question Answering with Reformulations over Knowledge Graph

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RGJ3BUUMrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords convqamodelquestionreformulationsansweringcornnetconversationalgenerated
0
0 comments X
read the original abstract

Conversational question answering (convQA) over knowledge graphs (KGs) involves answering multi-turn natural language questions about information contained in a KG. State-of-the-art methods of ConvQA often struggle with inexplicit question-answer pairs. These inputs are easy for human beings to understand given a conversation history, but hard for a machine to interpret, which can degrade ConvQA performance. To address this problem, we propose a reinforcement learning (RL) based model, CornNet, which utilizes question reformulations generated by large language models (LLMs) to improve ConvQA performance. CornNet adopts a teacher-student architecture where a teacher model learns question representations using human writing reformulations, and a student model to mimic the teacher model's output via reformulations generated by LLMs. The learned question representation is then used by an RL model to locate the correct answer in a KG. Extensive experimental results show that CornNet outperforms state-of-the-art convQA models.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.