Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?

Seyed Mahed Mousavi, Simone Caldarella, Giuseppe Riccardi
5/25/2023
cs.CL

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.

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. 5 weaker matches are 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

Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation

87% match2023

PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems

86% match1 repo22023

Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements

86% match1 repo82023

DialogBench: Evaluating LLMs as Human-like Dialogue Systems

85% match1 repo122023

Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues

85% match2023

WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue

85% match2023

Cite this paper

@article{mousavi2023response,
  title  = {Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?},
  author = {Seyed Mahed Mousavi and Simone Caldarella and Giuseppe Riccardi},
  year   = {2023},
  eprint = {2305.15908},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.15908v1}
}

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/2305.15908.svg)](https://codeofpaper.com/paper/2305.15908)

Discussion