RNN Based Language Generation Models for a Hindi Dialogue System

被引：2

作者：

Singh, Sumit ^{[1
]}

Malviya, Shrikant ^{[1
]}

Mishra, Rohit ^{[1
]}

Barnwal, Santosh Kumar ^{[1
]}

Tiwary, Uma Shanker ^{[1
]}

机构：

[1] Indian Inst Informat Technol Allahabad, Allahabad, Uttar Pradesh, India

来源：

INTELLIGENT HUMAN COMPUTER INTERACTION (IHCI 2019) | 2020年 / 11886卷

关键词：

Dialogue systems; Natural Language Generation; Recurrent neural network; Delexicalisation; Re-ranking;

D O I：

10.1007/978-3-030-44689-5_12

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Natural Language Generation (NLG) is a crucial component of a Spoken Dialogue System. Its task is to generate utterances with intended attributes like fluency, variation, readability, scalability and adequacy. As the handcrafted models are rigid and tedious to build, people have proposed many statistical and deep-learning based models to bring about more suitable options for generating utterance on a given Dialogue-Act (DA). This paper presents some Recurrent Neural Network Language Generation (RNNLG) framework based models along with their analysis of how they extract intended meaning in terms of content planning (modelling semantic input) and surface realization (final sentence generation) on a proposed unaligned Hindi dataset. The models have shown consistent performance on our natively developed dataset where the Modified-Semantically-Controlled LSTM (MSC-LSTM) performs better than all in terms of total slot-error (T-Error).

引用

页码：124 / 137

页数：14

共 20 条

[11] Mairesse F, 2010, ACL 2010: 48TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, P1552
[12] Mairesse F, 2014, COMPUT LINGUIST, V40, P763, DOI [10.1162/coli_a_00199, 10.1162/COLI_a_00199]
[13] Knowledge Based Summarization and Document Generation using Bayesian Network
Malviya, Shrikant
Tiwary, Uma Shanker
[J]. TWELFTH INTERNATIONAL CONFERENCE ON COMMUNICATION NETWORKS, ICCN 2016 / TWELFTH INTERNATIONAL CONFERENCE ON DATA MINING AND WAREHOUSING, ICDMW 2016 / TWELFTH INTERNATIONAL CONFERENCE ON IMAGE AND SIGNAL PROCESSING, ICISP 2016, 2016, 89 : 333 - 340
[14] Mikolov T, 2010, 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, P1045
[15] Oh A.H., 2000, ANLP NAACL 2000 WORK
[16] Stent A, 2004, P 42 ANN M ASS COMPU
[17] Training a sentence planner for spoken dialogue using boosting
Walker, MA
Rambow, OC
Rogati, M
[J]. COMPUTER SPEECH AND LANGUAGE, 2002, 16 (3-4) : 409 - 433
[18] Recurrent neural network language generation for spoken dialogue systems
Wen, Tsung-Hsien
Young, Steve
[J]. COMPUTER SPEECH AND LANGUAGE, 2020, 63
[19] Wen Tsung-Hsien, 2015, P 2015 C EMP METH NA, P1711, DOI [DOI 10.18653/V1/D15-1199, 10.18653]
[20] Wu YH, 2016, Arxiv, DOI arXiv:1609.08144

← 1 2 →