Hierarchical latent words language models for robust modeling to out-of domain tasks

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

This paper focuses on language modeling with adequate robustness to support different domain tasks. To this end, we propose a hierarchical latent word language model (h-LWLM). The proposed model can be regarded as a generalized form of the standard LWLMs. The key advance is introducing a multiple latent variable space with hierarchical structure. The structure can flexibly take account of linguistic phenomena not present in the training data. This paper details the definition as well as a training method based on layer-wise inference and a practical usage in natural language processing tasks with an approximation technique. Experiments on speech recognition show the effectiveness of h-LWLM in out-of domain tasks.

Original languageEnglish
Title of host publicationConference Proceedings - EMNLP 2015
Subtitle of host publicationConference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics (ACL)
Pages1896-1901
Number of pages6
ISBN (Electronic)9781941643327
DOIs
Publication statusPublished - 2015
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
Duration: 2015 Sept 172015 Sept 21

Publication series

NameConference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

Conference

ConferenceConference on Empirical Methods in Natural Language Processing, EMNLP 2015
Country/TerritoryPortugal
CityLisbon
Period15/9/1715/9/21

Fingerprint

Dive into the research topics of 'Hierarchical latent words language models for robust modeling to out-of domain tasks'. Together they form a unique fingerprint.

Cite this