Global-Selector: A New Benchmark Dataset and Model Architecture for Multi-turn Response Selection

06/02/2021
by   Chiyu Song, et al.
0

As an essential component of dialogue systems, multi-turn response selection aims to pick out the optimal response among a set of candidates to improve the dialogue fluency. In this paper, we investigate three problems of current response selection approaches, especially for generation-based conversational agents: (i) Existing approaches are often formulated as a sentence scoring problem, which does not consider relationships between responses. (ii) Existing models tend to select undesirable candidates that have large overlaps with the dialogue history. (iii) Negative instances in training are mainly constructed by random sampling from the corpus, whereas generated candidates in practice typically have a closer distribution. To address the above problems, we create a new dataset called ConvAI2+ and propose a new response selector called Global-Selector. Experimental results show that Global-Selector trained on ConvAI2+ have noticeable improvements in both accuracy and inference speed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/14/2021

Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training

Retrieval-based chatbot selects the appropriate response from candidates...
research
10/31/2022

Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task

In retrieval-based dialogue systems, a response selection model acts as ...
research
10/04/2020

Multi-turn Response Selection using Dialogue Dependency Relations

Multi-turn response selection is a task designed for developing dialogue...
research
06/24/2019

Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding

We propose a novel method for selecting coherent and diverse responses f...
research
10/13/2021

Exploring Dense Retrieval for Dialogue Response Selection

Recent research on dialogue response selection has been mainly focused o...
research
04/04/2023

Dialogue-Contextualized Re-ranking for Medical History-Taking

AI-driven medical history-taking is an important component in symptom ch...
research
05/04/2023

Strategic flip-flopping in political competition

We study candidates' positioning when adjustments are possible in respon...

Please sign up or login with your details

Forgot password? Click here to reset