On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43951550" target="_blank" >RIV/49777513:23520/18:43951550 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.csl.2017.07.009" target="_blank" >http://dx.doi.org/10.1016/j.csl.2017.07.009</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2017.07.009" target="_blank" >10.1016/j.csl.2017.07.009</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition

Popis výsledku v původním jazyce

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings. We propose in this work a new deep neural network that explores recurrent models to capture word sequences within sentences, and further study the impact of pretrained word embeddings. We validate this model on three languages: English, French and Czech. The performance of the proposed approach is consistent across these languages and it is comparable to the state-of-the-art results in English. However, and this is more surprising, we also found that standard word2vec embeddings do not seem to bring valuable information for this task and the proposed model.

Název v anglickém jazyce

On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition

Popis výsledku anglicky

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings. We propose in this work a new deep neural network that explores recurrent models to capture word sequences within sentences, and further study the impact of pretrained word embeddings. We validate this model on three languages: English, French and Czech. The performance of the proposed approach is consistent across these languages and it is comparable to the state-of-the-art results in English. However, and this is more surprising, we also found that standard word2vec embeddings do not seem to bring valuable information for this task and the proposed model.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computer Speech and Language

ISSN

0885-2308

e-ISSN

—

Svazek periodika

47

Číslo periodika v rámci svazku

JAN 2018

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

19

Strana od-do

175-193

Kód UT WoS článku

000411903700011

EID výsledku v databázi Scopus

—