Modeling speech acts in asynchronous conversations: A neural-CRF approach

8Citations
Citations of this article
87Readers
Mendeley users who have this article in their library.

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.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Joty, S., & Mohiuddin, T. (2018). Modeling speech acts in asynchronous conversations: A neural-CRF approach. Computational Linguistics, 44(4), 859–894. https://doi.org/10.1162/coli_a_00339

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 32

78%

Researcher 6

15%

Lecturer / Post doc 2

5%

Professor / Associate Prof. 1

2%

Readers' Discipline

Tooltip

Computer Science 30

65%

Linguistics 9

20%

Engineering 4

9%

Social Sciences 3

7%

Save time finding and organizing research with Mendeley

Sign up for free