Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding

TL;DR

This paper introduces Cross Convolution Networks and Multi Frequency Word Embeddings to improve response selection in multi-turn dialogues, effectively capturing rare keywords and handling long input sequences, leading to state-of-the-art results.

Contribution

The paper presents novel CCN and multi-frequency embeddings that enhance dialogue modeling by addressing keyword rarity and sequence length issues.

Findings

Achieved state-of-the-art performance on the Ubuntu Dialogue dataset.

Ensemble models further improved response selection accuracy.

Significant improvements over previous methods in multi-turn dialogue modeling.

Abstract

To build a satisfying chatbot that has the ability of managing a goal-oriented multi-turn dialogue, accurate modeling of human conversation is crucial. In this paper we concentrate on the task of response selection for multi-turn human-computer conversation with a given context. Previous approaches show weakness in capturing information of rare keywords that appear in either or both context and correct response, and struggle with long input sequences. We propose Cross Convolution Network (CCN) and Multi Frequency word embedding to address both problems. We train several models using the Ubuntu Dialogue dataset which is the largest freely available multi-turn based dialogue corpus. We further build an ensemble model by averaging predictions of multiple models. We achieve a new state-of-the-art on this dataset with considerable improvements compared to previous best results.