Topic Spotting using Hierarchical Networks with Self Attention

04/04/2019
by   Pooja Chitkara, et al.
0

Success of deep learning techniques have renewed the interest in development of dialogue systems. However, current systems struggle to have consistent long term conversations with the users and fail to build rapport. Topic spotting, the task of automatically inferring the topic of a conversation, has been shown to be helpful in making a dialog system more engaging and efficient. We propose a hierarchical model with self attention for topic spotting. Experiments on the Switchboard corpus show the superior performance of our model over previously proposed techniques for topic spotting and deep models for text classification. Additionally, in contrast to offline processing of dialog, we also analyze the performance of our model in a more realistic setting i.e. in an online setting where the topic is identified in real time as the dialog progresses. Results show that our model is able to generalize even with limited information in the online setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/12/2020

Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition

Dialogue act recognition is a fundamental task for an intelligent dialog...
research
09/09/2021

TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

Human conversations naturally evolve around different topics and fluentl...
research
11/28/2021

An Empirical Study of Topic Transition in Dialogue

Transitioning between topics is a natural component of human-human dialo...
research
01/11/2018

Topic-based Evaluation for Conversational Bots

Dialog evaluation is a challenging problem, especially for non task-orie...
research
03/10/2020

Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog

Stickers with vivid and engaging expressions are becoming increasingly p...
research
05/30/2019

Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention

Semantically controlled neural response generation on limited-domain has...
research
10/07/2020

Improving Context Modeling in Neural Topic Segmentation

Topic segmentation is critical in key NLP tasks and recent works favor h...

Please sign up or login with your details

Forgot password? Click here to reset