Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations

TL;DR

This paper presents a neural model for automatic quotation generation in online conversations, emphasizing the importance of contextual consistency across topics, interactions, and queries to improve relevance and coherence.

Contribution

It introduces a novel encoder-decoder framework that incorporates latent topic, interaction, and query coherence to enhance quotation relevance in conversational AI.

Findings

Outperforms state-of-the-art models on large-scale datasets in English and Chinese.

Shows that topic, interaction, and query consistency improve quotation relevance.

Demonstrates the importance of contextual factors in automatic quotation generation.

Abstract

Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation generation in an online conversation and explores how language consistency affects whether a quotation fits the given context. Here, we capture the contextual consistency of a quotation in terms of latent topics, interactions with the dialogue history, and coherence to the query turn's existing content. Further, an encoder-decoder neural framework is employed to continue the context with a quotation via language generation. Experiment results on two large-scale datasets in English and Chinese demonstrate that our quotation generation model outperforms the state-of-the-art models. Further analysis shows that topic, interaction, and query consistency are all helpful to learn how to quote in online conversations.