Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods

Min Sik Oh, Min Sang Kim
7/28/2022
cs.CLcs.IR

No confident code implementation found for this paper.

Abstract

Persona and Knowledge dual context open-domain chat is a novel dialogue generation task introduced recently. While Persona and Knowledge is each interesting context of open-domain dialogue, the combination of both has not been well studied. We tackle Persona-Knowledge identification and response generation tasks in this paper. We design an informed data augmentation strategy that is compatible with neural Q&A retrieval models. With the augmented data, we perform permutative Persona-Knowledge evaluation and successive Persona search fine-tuning. Furthermore, we perform dialogue generation with various decoding techniques and illustrate crucial elements. We achieve SOTA across official metrics with 93.99% Grounding accuracy average and 23.62 SacreBLEU score.

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. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

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

Similar Papers

Promoting Open-domain Dialogue Generation through Learning Pattern Information between Contexts and Responses

85% match2023

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

83% match2023

A Transformer-based Response Evaluator for Open-Domain Spoken Conversation

82% match2023

Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations

81% match1 repo1092023

A Systematic Evaluation of Response Selection for Open Domain Dialogue

81% match2022

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

81% match2023

Cite this paper

@article{oh2022personaknowledge,
  title  = {Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods},
  author = {Min Sik Oh and Min Sang Kim},
  year   = {2022},
  eprint = {2207.13919},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.13919v1}
}

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/2207.13919.svg)](https://codeofpaper.com/paper/2207.13919)

Discussion