Pub Date : 2014-12-04DOI: 10.1109/IALP.2014.6973480
Hao Zhao, Shuqin Shi
A comprehensive perception of the essence of human imperative behaviors and a thorough study of imperative sentences require researchers to shift their views from imperative sentences to imperative sentence combining. This research treats the linking patterns and manners between or among sentences within imperative sentence combining. The linking patterns refer to the linking between imperative sentences and other kinds of sentences and the linking within imperative sentences. The former is achieved through logical semantic relations and in simple manner while the latter involves marked linking and unmarked linking, the manners of which are varied.
{"title":"The formation of modern Chinese imperative sentence combining","authors":"Hao Zhao, Shuqin Shi","doi":"10.1109/IALP.2014.6973480","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973480","url":null,"abstract":"A comprehensive perception of the essence of human imperative behaviors and a thorough study of imperative sentences require researchers to shift their views from imperative sentences to imperative sentence combining. This research treats the linking patterns and manners between or among sentences within imperative sentence combining. The linking patterns refer to the linking between imperative sentences and other kinds of sentences and the linking within imperative sentences. The former is achieved through logical semantic relations and in simple manner while the latter involves marked linking and unmarked linking, the manners of which are varied.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125463992","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}
Pub Date : 2014-12-04DOI: 10.1109/IALP.2014.6973495
Shourong An, Hui Feng, Huixia Wang, J. Dang
This paper, under the framework of Flege's(1995) Speech Learning Model, investigates the acoustic features of English monophthongs produced by college students who speak Tibetan (Lhasa). Acoustic features of English monophthongs produced by Tibetan speakers are compared with those of British news broadcasters (Deterding, 1997). The study found that: 1. Under the influence of Tibetan vowel system, English vowel space for Tibetan is centralized and smaller than that of RP(Received Pronunciation). 2. Female Tibetan cannot distinguish vowel contrast /e/and /æ/ very well. For English vowels produced by female Tibetan, /i:/ is lower than that of RP, /i/ and /a:/ are fronter than RP /i/ and /a:/, what's more, /u:/ is less fronter than RP/u:/; male Tibetan differentiate vowels /e/ and /æ/ successfully. For English vowels produced by male Tibetan, /i:/ is less fronter than RP /i:/, /a:/ is much fronter than RP/a:/ and /u:/ is less fronter and lower than RP/u:/.
{"title":"An acoustic analysis of English monophthongs by Tibetan speakers","authors":"Shourong An, Hui Feng, Huixia Wang, J. Dang","doi":"10.1109/IALP.2014.6973495","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973495","url":null,"abstract":"This paper, under the framework of Flege's(1995) Speech Learning Model, investigates the acoustic features of English monophthongs produced by college students who speak Tibetan (Lhasa). Acoustic features of English monophthongs produced by Tibetan speakers are compared with those of British news broadcasters (Deterding, 1997). The study found that: 1. Under the influence of Tibetan vowel system, English vowel space for Tibetan is centralized and smaller than that of RP(Received Pronunciation). 2. Female Tibetan cannot distinguish vowel contrast /e/and /æ/ very well. For English vowels produced by female Tibetan, /i:/ is lower than that of RP, /i/ and /a:/ are fronter than RP /i/ and /a:/, what's more, /u:/ is less fronter than RP/u:/; male Tibetan differentiate vowels /e/ and /æ/ successfully. For English vowels produced by male Tibetan, /i:/ is less fronter than RP /i:/, /a:/ is much fronter than RP/a:/ and /u:/ is less fronter and lower than RP/u:/.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124530230","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}
Pub Date : 2014-12-03DOI: 10.1109/IALP.2014.6973515
Wei Zhang
This paper examines the prosodic cues of a particular type of self-repair, namely, insertion repair at transition place in Mandarin Chinese. Studies on the prosodic cues of self-repair mostly examined repair types such as repetition and replacement initiated before a turn unit's completion. Studies on further talk past a turn unit's completion observed different prosodic packaging for further talk constructed as a new separate unit and further talk constructed as syntactic extension of the preceding unit. Our study of the insertion repair produced past a turn unit's completion examined the prosodic cues such as speech rate, F0 and intensity of the repair-target unit, the repairing unit and the inserted material in the repair unit. The results show a general pattern for the repairing unit to be produced with quickened tempo, reduced pitch and amplitude and less energy. The results also show that the inserted materials in the repairing unit tend to receive prominence in terms of intensity.
{"title":"A prosodic analysis of insertion repair at transition space in Chinese conversation","authors":"Wei Zhang","doi":"10.1109/IALP.2014.6973515","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973515","url":null,"abstract":"This paper examines the prosodic cues of a particular type of self-repair, namely, insertion repair at transition place in Mandarin Chinese. Studies on the prosodic cues of self-repair mostly examined repair types such as repetition and replacement initiated before a turn unit's completion. Studies on further talk past a turn unit's completion observed different prosodic packaging for further talk constructed as a new separate unit and further talk constructed as syntactic extension of the preceding unit. Our study of the insertion repair produced past a turn unit's completion examined the prosodic cues such as speech rate, F0 and intensity of the repair-target unit, the repairing unit and the inserted material in the repair unit. The results show a general pattern for the repairing unit to be produced with quickened tempo, reduced pitch and amplitude and less energy. The results also show that the inserted materials in the repairing unit tend to receive prominence in terms of intensity.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132292178","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973486
Yiyi Zhao
Ba-construction is a special syntactic structure in modern Chinese. This paper gives a short summary on these topics and extracts 500 sentences including Ba-construction from CCRL. After detail analysis of the samples' phrase structure, the author builds the rules for computer based on CFG. These rules are tested by CTT - a parsing tree tracer. The author also points out the problems existed in the rules of CFG and the direction of further improvement.
{"title":"Automatic processing of Chinese special structure ‘Ba-construction’","authors":"Yiyi Zhao","doi":"10.1109/IALP.2014.6973486","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973486","url":null,"abstract":"Ba-construction is a special syntactic structure in modern Chinese. This paper gives a short summary on these topics and extracts 500 sentences including Ba-construction from CCRL. After detail analysis of the samples' phrase structure, the author builds the rules for computer based on CFG. These rules are tested by CTT - a parsing tree tracer. The author also points out the problems existed in the rules of CFG and the direction of further improvement.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126301458","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973505
Anshu Chittora, H. Patil
In this paper, feature derived from the glottal inverse filtering of the speech signal is used for classification of pathological infant cries. Glottal inverse filtering is used to estimate the glottal volume velocity waveform (i.e., the source of voicing for infant cry). Here, GIF is used to separate the glottal source and vocal tract filter. The source and the filter features are used for pathological cries classification. Through the experimental results, importance of both the features in cry classification is investigated. State-of-the-art feature set, viz., Mel Frequency Cepstral Coefficients (MFCC) is also used to compare performance of the proposed feature set. Experimental results show classification accuracy of 76.28 % with the proposed features as opposed to state-of-the-art, MFCC feature which shows classification accuracy of 71.13 %. Fusion of the proposed feature set with MFCC gives classification accuracy of 78.35 % indicating that proposed feature captures the complimentary information in infant cry signal. All experiments were conducted with SVM classifier with radial basis function kernel.
{"title":"Use of glottal inverse filtering for asthma and HIE infant cries classification","authors":"Anshu Chittora, H. Patil","doi":"10.1109/IALP.2014.6973505","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973505","url":null,"abstract":"In this paper, feature derived from the glottal inverse filtering of the speech signal is used for classification of pathological infant cries. Glottal inverse filtering is used to estimate the glottal volume velocity waveform (i.e., the source of voicing for infant cry). Here, GIF is used to separate the glottal source and vocal tract filter. The source and the filter features are used for pathological cries classification. Through the experimental results, importance of both the features in cry classification is investigated. State-of-the-art feature set, viz., Mel Frequency Cepstral Coefficients (MFCC) is also used to compare performance of the proposed feature set. Experimental results show classification accuracy of 76.28 % with the proposed features as opposed to state-of-the-art, MFCC feature which shows classification accuracy of 71.13 %. Fusion of the proposed feature set with MFCC gives classification accuracy of 78.35 % indicating that proposed feature captures the complimentary information in infant cry signal. All experiments were conducted with SVM classifier with radial basis function kernel.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"99 30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131020232","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973522
Bali Ranaivo-Malançon, Suhaila Saee, Jennifer Fiona Wilfred Busu
The goal of the project presented in this paper is to explore the linguistic knowledge hidden in printed dictionaries of minority languages. Firstly, the printed dictionary has to be converted into a machine readable dictionary. The second step is to make use of existing language processing tools to discover the hidden knowledge. To illustrate the proposed idea, a version of an English-Penan dictionary is used as the case-study. It appears that even with a small amount of data, some interesting information, like the first list of functional words, some collocations, and an insight of the morphological structure of the Penan language can be discovered.
{"title":"Discovering linguistic knowledge by converting printed dictionaries of minority languages into machine readable dictionaries","authors":"Bali Ranaivo-Malançon, Suhaila Saee, Jennifer Fiona Wilfred Busu","doi":"10.1109/IALP.2014.6973522","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973522","url":null,"abstract":"The goal of the project presented in this paper is to explore the linguistic knowledge hidden in printed dictionaries of minority languages. Firstly, the printed dictionary has to be converted into a machine readable dictionary. The second step is to make use of existing language processing tools to discover the hidden knowledge. To illustrate the proposed idea, a version of an English-Penan dictionary is used as the case-study. It appears that even with a small amount of data, some interesting information, like the first list of functional words, some collocations, and an insight of the morphological structure of the Penan language can be discovered.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124357809","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973469
Shuzhen Shi, Pu Li
This paper discuses concessive compact construction “wanyi···ye···” from Chinese Information Processing. The simple sentence with “Wanyi” and “Ye” and the concessive compact construction of “wanyi···ye···” are similar in syntax, which have been distinguished at first. The semantic feature of concessive compact construction “wanyi···ye···” is subjective, which has been betrayed in different ways.
{"title":"“Wanyi···Ye···”","authors":"Shuzhen Shi, Pu Li","doi":"10.1109/IALP.2014.6973469","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973469","url":null,"abstract":"This paper discuses concessive compact construction “wanyi···ye···” from Chinese Information Processing. The simple sentence with “Wanyi” and “Ye” and the concessive compact construction of “wanyi···ye···” are similar in syntax, which have been distinguished at first. The semantic feature of concessive compact construction “wanyi···ye···” is subjective, which has been betrayed in different ways.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124031065","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973497
Jian Zhang, Huaqiang Yuan
We carry out a comprehensive study of acous-tic/prosodic, linguistic and structural features for speech summarization, contrasting two genres of speech, namely Mandarin Broadcast News and Cantonese Parliamentary Speech. We find that structural features are superior to acoustic and lexical features when summarizing broadcast news because of the fact that in the same Mandarin broadcast program, the distribution and flow of summary utterances are relatively consistent. We use different machine learning algorithms to construct the binary-class summarizers to select the best features for extractive summarization, and obtain state-of-the-art performances: ROUGE-L F-measure of 0.682 for Mandarin Broadcast News, and 0.737 for Cantonese Parliamentary Meeting Speech. In the case of Parliamentary Meeting Speech summarization, we show that our summarizer performed surprisingly well ROUGE-L F-measure of 0.729 by using ASR transcription despite the character error rate of 27%. We also discover that the different choices of algorithms almost do not affect the consistency of our findings.
{"title":"A comparative study on extractive speech summarization of broadcast news and parliamentary meeting speech","authors":"Jian Zhang, Huaqiang Yuan","doi":"10.1109/IALP.2014.6973497","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973497","url":null,"abstract":"We carry out a comprehensive study of acous-tic/prosodic, linguistic and structural features for speech summarization, contrasting two genres of speech, namely Mandarin Broadcast News and Cantonese Parliamentary Speech. We find that structural features are superior to acoustic and lexical features when summarizing broadcast news because of the fact that in the same Mandarin broadcast program, the distribution and flow of summary utterances are relatively consistent. We use different machine learning algorithms to construct the binary-class summarizers to select the best features for extractive summarization, and obtain state-of-the-art performances: ROUGE-L F-measure of 0.682 for Mandarin Broadcast News, and 0.737 for Cantonese Parliamentary Meeting Speech. In the case of Parliamentary Meeting Speech summarization, we show that our summarizer performed surprisingly well ROUGE-L F-measure of 0.729 by using ASR transcription despite the character error rate of 27%. We also discover that the different choices of algorithms almost do not affect the consistency of our findings.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134535834","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973500
Thinh D. Bui, Quoc B. Ho
Recognizing the structures of legal texts is significant to understand texts in this domain. In this paper, we describe a task of automatically structuring Vietnamese legal documents based on our study of this domain in several aspects: their linguistic features and patterns of recognition with trigger sets. The task focuses on the recognition of the logical structures of the documents stored in law database of Vietnam Ministry of Justice. A rule-based approach in association with some patterns is applied and is verified on a manually built corpus. Experimental result got 64.37% on assumption annotation, 64.15% on provision annotation and 75.76% on sanction annotation in the Fβ=1 score on the corpus of Vietnamese Enterprise Law articles.
{"title":"An approach for automatically structuring Vietnamese legal text","authors":"Thinh D. Bui, Quoc B. Ho","doi":"10.1109/IALP.2014.6973500","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973500","url":null,"abstract":"Recognizing the structures of legal texts is significant to understand texts in this domain. In this paper, we describe a task of automatically structuring Vietnamese legal documents based on our study of this domain in several aspects: their linguistic features and patterns of recognition with trigger sets. The task focuses on the recognition of the logical structures of the documents stored in law database of Vietnam Ministry of Justice. A rule-based approach in association with some patterns is applied and is verified on a manually built corpus. Experimental result got 64.37% on assumption annotation, 64.15% on provision annotation and 75.76% on sanction annotation in the Fβ=1 score on the corpus of Vietnamese Enterprise Law articles.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127025275","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}
Pub Date : 2014-10-01DOI: 10.1109/IALP.2014.6973498
Padmaja Sharma, U. Sharma, J. Kalita
Named Entity Recognition (NER) is an important task in all Natural Language Processing (NLP) applications. It is the process of identifying and classifying the proper noun into classes such as person, location, organization and miscellaneous. Substantial work has been done in English and other European languages, achieving greater accuracy compared to the Indian Languages. Although NER in Indian languages is a difficult and challenging task and suffers from scarcity of resources, such work has started to appear recently. This paper discusses work on NER in Assamese using both Conditional Random Fields and a Rule-Based approach which gives an F-measure of 90-95% accuracy.
{"title":"Named entity recognition in Assamese using CRFS and rules","authors":"Padmaja Sharma, U. Sharma, J. Kalita","doi":"10.1109/IALP.2014.6973498","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973498","url":null,"abstract":"Named Entity Recognition (NER) is an important task in all Natural Language Processing (NLP) applications. It is the process of identifying and classifying the proper noun into classes such as person, location, organization and miscellaneous. Substantial work has been done in English and other European languages, achieving greater accuracy compared to the Indian Languages. Although NER in Indian languages is a difficult and challenging task and suffers from scarcity of resources, such work has started to appear recently. This paper discusses work on NER in Assamese using both Conditional Random Fields and a Rule-Based approach which gives an F-measure of 90-95% accuracy.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116887652","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：