← Search

Julia Reinspach

1 accepted papers

2022

DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling

COLING 2022main

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context limits the ability of a model to learn representations that gen…