Task Oriented Conversational Modelling With Subjective Knowledge

Raja Kumar
3/30/2023
cs.CLcs.IRcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Existing conversational models are handled by a database(DB) and API based systems. However, very often users' questions require information that cannot be handled by such systems. Nonetheless, answers to these questions are available in the form of customer reviews and FAQs. DSTC-11 proposes a three stage pipeline consisting of knowledge seeking turn detection, knowledge selection and response generation to create a conversational model grounded on this subjective knowledge. In this paper, we focus on improving the knowledge selection module to enhance the overall system performance. In particular, we propose entity retrieval methods which result in an accurate and faster knowledge search. Our proposed Named Entity Recognition (NER) based entity retrieval method results in 7X faster search compared to the baseline model. Additionally, we also explore a potential keyword extraction method which can improve the accuracy of knowledge selection. Preliminary results show a 4 \% improvement in exact match score on knowledge selection task. The code is available https://github.com/raja-kumar/knowledge-grounded-TODS

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog

81% match1 repo92023

Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision

81% match2023

UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems

80% match2024

Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring

80% match2023

UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval

79% match2024

Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models

79% match2025

Cite this paper

@article{kumar2023task,
  title  = {Task Oriented Conversational Modelling With Subjective Knowledge},
  author = {Raja Kumar},
  year   = {2023},
  eprint = {2303.17695},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.17695v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.17695.svg)](https://codeofpaper.com/paper/2303.17695)

Discussion