Titlebook: Computational Linguistics; 14th International C Kôiti Hasida,Ayu Purwarianti Conference proceedings 2016 Springer Science+Business Media Si

规范就好

Filled Pause Detection in Indonesian Spontaneous Speechnd 2082 non-filled pause words were employed as training data. Using 25 sentences as testing data, Naïve Bayes gave best detection correctness, 74.35 % on a closed data set and 71.43 % on an open data set.

Pelago

Favorable

Incorporating Tweet Relationships into Topic Derivationbetween tweets. We have conducted experiments on a Twitter dataset and evaluated the performance in terms of both topic coherence and tweet-topic accuracy. Our experiments show that . outperforms methods that do not use relationship information.

Indolent

1865-0929 on for Computational Linguistics, PACLING 2015, held in Bali,Indonesia, in May 2015...The 18revised full papers presented were carefully reviewed and selected from 45papers. The papers are organized around the following topics: syntax andsyntactic analysis; semantics and semantic analysis; spoken la

分解

savage

Context Representation with Word Embeddings for WSDr word sense disambiguation (WSD) that employs word embeddings as local context features. Our experiments show the usefulness of word embeddings in the WSD task. We also compare the methods with different vector representations and reveal their effects on the WSD task.

心神不宁

Aids209

laparoscopy

Ibd810