Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/105468
Title: Modeling speech acts in asynchronous conversations : a neural-CRF approach
Authors: Shafiq Joty
Tasnim Mohiuddin
Keywords: DRNTU::Engineering::Computer science and engineering
Asynchronous Conversations
Modeling Speech
Issue Date: 2018
Source: Shafiq Joty, & Tasnim Mohiuddin. (2018). Modeling speech acts in asynchronous conversations : a neural-CRF approach. Computational Linguistics, 44(4), 859-894. doi:10.1162/coli_a_00339
Series/Report no.: Computational Linguistics
Abstract: Participants in an asynchronous conversation (e.g., forum, e-mail) interact with each other at different times, performing certain communicative acts, called speech acts (e.g., question, request). In this article, we propose a hybrid approach to speech act recognition in asynchronous conversations. Our approach works in two main steps: a long short-term memory recurrent neural network (LSTM-RNN) first encodes each sentence separately into a task-specific distributed representation, and this is then used in a conditional random field (CRF) model to capture the conversational dependencies between sentences. The LSTM-RNN model uses pretrained word embeddings learned from a large conversational corpus and is trained to classify sentences into speech act types. The CRF model can consider arbitrary graph structures to model conversational dependencies in an asynchronous conversation. In addition, to mitigate the problem of limited annotated data in the asynchronous domains, we adapt the LSTM-RNN model to learn from synchronous conversations (e.g., meetings), using domain adversarial training of neural networks. Empirical evaluation shows the effectiveness of our approach over existing ones: (i) LSTM-RNNs provide better task-specific representations, (ii) conversational word embeddings benefit the LSTM-RNNs more than the off-the-shelf ones, (iii) adversarial training gives better domain-invariant representations, and (iv) the global CRF model improves over local models.
URI: https://hdl.handle.net/10356/105468
http://hdl.handle.net/10220/48696
ISSN: 0891-2017
DOI: 10.1162/coli_a_00339
Rights: © 2018 Association for Computational Linguistics. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits you to copy and redistribute in any medium or format, for non-commercial use only, provided that the original work is not remixed, transformed, or built upon, and that appropriate credit to the original source is given. For a full description of the license, please visit https://creativecommons.org/licenses/by/4.0/legalcode.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Modeling speech acts in asynchronous conversations a neural-CRF approach.pdf931.5 kBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 50

4
Updated on Feb 6, 2023

Web of ScienceTM
Citations 50

1
Updated on Jan 29, 2023

Page view(s)

127
Updated on Feb 7, 2023

Download(s) 50

54
Updated on Feb 7, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.