2017 International Conference on Asian Language Processing (IALP)最新文献_第3页

Hybrid answer selection model for non-factoid question answering 非因素问答的混合答案选择模型

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300620

R. Ma, Jian Zhang, Miao Li, Lei Chen, Jingyang Gao

引用次数: 7

Embedding wikipedia title based on its wikipedia text and categories 基于维基百科文本和分类嵌入维基百科标题

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300566

Chi-Yen Chen, Wei-Yun Ma

引用次数: 1

A simple yet effective method for summarizing microblogging users with their representative tweets 一个简单而有效的方法来总结微博用户的代表性tweets

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300605

Shuangyong Song, Yao Meng, Zhiwei Shi, Zhongguang Zheng, Haiqing Chen

引用次数: 3

The automatic extraction of common-used adverbs for teaching Chinese as second language 汉语第二语言教学中常用副词的自动提取

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300568

Zhimin Wang, Mei-Chu Wang

引用次数: 0

Investigating multi-task learning for automatic speech recognition with code-switching between mandarin and english 中文与英文语码转换自动语音识别的多任务学习研究

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300538

Xiao Song, Yuexian Zou, Shilei Huang, Shaobin Chen, Yi Y. Liu

{"title":"Investigating multi-task learning for automatic speech recognition with code-switching between mandarin and english","authors":"Xiao Song, Yuexian Zou, Shilei Huang, Shaobin Chen, Yi Y. Liu","doi":"10.1109/IALP.2017.8300538","DOIUrl":"https://doi.org/10.1109/IALP.2017.8300538","url":null,"abstract":"This work investigates a Multi-task Learning (MTL-DNN) approach to enhance the performance of Mandarin-English code-switching conversational speech recognition (MECS-CSR). The approach aims at getting a better acoustic model for the primary task by jointly learning two auxiliary tasks together. To overcome the effect of co-articulation at code-switch points, under MTL-DNN, we propose to jointly train two types of Mandarin-English acoustic models according to the choice of acoustic units that describe the salient acoustic and phonetic information for Mandarin. To further make use of language information, we jointly train another acoustic model for language identification (LID) with the two acoustic models under the MTL-DNN. To evaluate the effectiveness of our developed MECS-CSR system, extensive experiments are carried out on a public dataset LDC2015S04. It is noted that our approach does not require other language resources. Compared with the first basic MECS-CSR system [1], Mixed Error Rate (MER) of our proposed approach is relatively reduced by 12.49%. The performance improvement benefits from multi-task learning where the common internal representation is obtained from the auxiliary tasks learning.","PeriodicalId":183586,"journal":{"name":"2017 International Conference on Asian Language Processing (IALP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A light-weight method of building an LSTM-RNN-based bilingual tts system 基于lstm - rnn的双语tts系统轻量级构建方法

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300579

Huaiping Ming, Yanfeng Lu, Zhengchen Zhang, M. Dong

{"title":"A light-weight method of building an LSTM-RNN-based bilingual tts system","authors":"Huaiping Ming, Yanfeng Lu, Zhengchen Zhang, M. Dong","doi":"10.1109/IALP.2017.8300579","DOIUrl":"https://doi.org/10.1109/IALP.2017.8300579","url":null,"abstract":"For a long time, text-to-speech (TTS) synthesis systems could only handle one language. Early bilingual TTS systems were constructed by directly combining two monolingual systems, with language switching. The bilingual speech generated by such systems normally contained two different voices, therefore causing unnatural, sometimes disturbing effects. A genuine bilingual TTS system should use a single voice and avoid switching between two independent monolingual systems. Accordingly, the difficulties of building genuine bilingual speech synthesizers lie in merging two different languages into the same system and preparing bilingual speech data with the same speaker. Various methods have been proposed to overcome these difficulties, including soft prosody prediction, phone, state and frame mapping, and most recently speaker and language factorization. Professional speakers who can speak two languages fluently are hard to find. In many cases a speaker can speak one language well, but the second only fairly. In this paper we propose an easy linguistic feature concatenation method to build a bilingual TTS system with data created by such a speaker, using an LSTM-RNN-based speech synthesizer. Both objective and subjective evaluations show the effectiveness of this method.","PeriodicalId":183586,"journal":{"name":"2017 International Conference on Asian Language Processing (IALP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121534992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 20

Controlling byte pair encoding for neural machine translation 控制字节对编码的神经机器翻译

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300571

Alfred John Tacorda, Marvin John Ignacio, Nathaniel Oco, R. Roxas

{"title":"Controlling byte pair encoding for neural machine translation","authors":"Alfred John Tacorda, Marvin John Ignacio, Nathaniel Oco, R. Roxas","doi":"10.1109/IALP.2017.8300571","DOIUrl":"https://doi.org/10.1109/IALP.2017.8300571","url":null,"abstract":"Byte pair encoding(BPE) is an approach that segments the corpus in such a way that frequent sequence of characters are combined; it results to having word surface forms divided into its' root word and affix. It alone handles out-of-vocabulary words, but tends to not consistently segment inflected words. Controlled byte pair encoding (CBPE) allowed our word-level neural machine translation (NMT) model to easily recognize inflected words which are prevalent in morphologically-rich languages. It prevented BPE from merging affixes in a word to other characters in the word. Our resulting NMT models from CBPE consistently evaluates affixes that could've been segmented with variations in BPE. In our experiments, we considered 119,969 English-Filipino parallel language pairs from an existing dataset, with Filipino as a morphologically-rich language. The results show that BPE and CBPE both showed improvements in the BLEU scores from 38.31 to 44.82 and 44.07 for English→Filipino, and from 32.17 to 35.25 and 35.98 for Filipino→English, respectively. The lower scores in the Filipino→English can be attributed to other language characteristics of Filipino such as free word order, one-to-many relationship in translating from English to Filipino, and some transliterations in the parallel corpus. CBPE also performed slightly better for English→Filipino than for Filipino→English.","PeriodicalId":183586,"journal":{"name":"2017 International Conference on Asian Language Processing (IALP)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129044774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Dynamic topic mining for microblog fused with user's behavior and time window 微博动态主题挖掘融合了用户行为和时间窗口

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300535

Fei Wu, Zhuo Wang, Zhengtao Yu, Liren Wang, Feng Zhou

引用次数: 1

Neural machine translation for sinhala and tamil languages 神经机器翻译僧伽罗语和泰米尔语

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300576

Pasindu Tennage, Prabath Sandaruwan, Malith Thilakarathne, Achini Herath, Surangika Ranathunga, Sanath Jayasena, G. Dias

引用次数: 17

Improving air traffic control speech intelligibility by reducing speaking rate effectively 有效降低话音率，提高空管语音清晰度

2017 International Conference on Asian Language Processing (IALP) Pub Date : 2017-12-01 DOI: 10.1109/IALP.2017.8300578

Nana Hou, Xiaohai Tian, Chng Eng Siong, B. Ma, Haizhou Li

引用次数: 2