Dang-Khoa Mac, E. Castelli, V. Aubergé, A. Rilliard
Prosodic attitudes, or social affects, are main part of face-to-face interaction and linked to the language through the culture. This paper presents a study on prosodic attitudes in Vietnamese, a tonal language. Perception experiments on 16 Vietnamese attitudes were carried out with Vietnamese and French participants. The results revealed perception differences between native and non-native listeners. As attitudinal expression are partially carried through speech prosody, an analysis was also carried out, in order to have a better understanding of why these attitudes are recognized or confused, and to bring out some prosodic characteristics of Vietnamese social affects.
{"title":"How Vietnamese Attitudes can be Recognized and Confused: Cross-Cultural Perception and Speech Prosody Analysis","authors":"Dang-Khoa Mac, E. Castelli, V. Aubergé, A. Rilliard","doi":"10.1109/IALP.2011.39","DOIUrl":"https://doi.org/10.1109/IALP.2011.39","url":null,"abstract":"Prosodic attitudes, or social affects, are main part of face-to-face interaction and linked to the language through the culture. This paper presents a study on prosodic attitudes in Vietnamese, a tonal language. Perception experiments on 16 Vietnamese attitudes were carried out with Vietnamese and French participants. The results revealed perception differences between native and non-native listeners. As attitudinal expression are partially carried through speech prosody, an analysis was also carried out, in order to have a better understanding of why these attitudes are recognized or confused, and to bring out some prosodic characteristics of Vietnamese social affects.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117272153","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}
The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.
{"title":"An Experimental Study on Vietnamese Speech Synthesis","authors":"Liping Kui, Jian Yang, Bin He, Enxing Hu","doi":"10.1109/IALP.2011.40","DOIUrl":"https://doi.org/10.1109/IALP.2011.40","url":null,"abstract":"The modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis units of this system are initials and finals. According to the characteristics of Vietnamese, we have conducted such works as collecting corpus, recording, labeling, determining the phonemes list, and designing context attributes and question set. Then Vietnamese speech synthesis system is constructed by using the STRAIGHT synthesizer under the HTS platform. At last, we conduct a subjective test to synthetic speech signals. The results of preliminary evaluation show that the intelligibility of the utterances is approximately 100%, and the quality of synthesis speech is from fair to good.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"16 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125625997","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}
Different from English, Chinese does not explicitly show grammatical number information by inflection. The Number information in a Chinese sentence is implied by the noun phrase itself and its surrounding context. In this paper, we explore diverse features, including both flat and structured, for number identification of Chinese personal noun phrase. The flat features explore the knowledge within the noun phrase while the structured features capture the surrounding context information of the noun phrase in the parse tree of the given sentence. These two kinds of features together with kernel-based SVM are utilized in this study. Evaluation on the ACE 2005 corpus shows that our method achieves 89.23% in accuracy, which significantly advances the state-of-the-art.
{"title":"Exploring Both Flat and Structured Features for Number Type Identification of Chinese Personal Noun Phrases","authors":"Jun Lang","doi":"10.1109/IALP.2011.69","DOIUrl":"https://doi.org/10.1109/IALP.2011.69","url":null,"abstract":"Different from English, Chinese does not explicitly show grammatical number information by inflection. The Number information in a Chinese sentence is implied by the noun phrase itself and its surrounding context. In this paper, we explore diverse features, including both flat and structured, for number identification of Chinese personal noun phrase. The flat features explore the knowledge within the noun phrase while the structured features capture the surrounding context information of the noun phrase in the parse tree of the given sentence. These two kinds of features together with kernel-based SVM are utilized in this study. Evaluation on the ACE 2005 corpus shows that our method achieves 89.23% in accuracy, which significantly advances the state-of-the-art.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126208612","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}
Likun Qiu, Lei Wu, Kai Zhao, Changjian Hu, Lingpeng Kong
To solve the data sparseness problem in dependency parsing, most previous studies used features constructed from large-scale auto-parsed data. Unlike previous work, we propose a new approach to improve dependency parsing with context-free dependency triples (CDT) extracted by using self-disambiguating patterns (SDP). The use of SDP makes it possible to avoid the dependency on a baseline parser and explore the influence of different types of substructures one by one. Additionally, taking the available CDTs as seeds, a label propagation process is used to tag a large number of unlabeled word pairs as CDTs. Experiments show that, when CDT features are integrated into a maximum spanning tree (MST) dependency parser, the new parser improves significantly over the baseline MST parser. Comparative results also show that CDTs with dependency relation labels perform much better than CDT without dependency relation label.
{"title":"Improving Chinese Dependency Parsing with Self-Disambiguating Patterns","authors":"Likun Qiu, Lei Wu, Kai Zhao, Changjian Hu, Lingpeng Kong","doi":"10.1109/IALP.2011.36","DOIUrl":"https://doi.org/10.1109/IALP.2011.36","url":null,"abstract":"To solve the data sparseness problem in dependency parsing, most previous studies used features constructed from large-scale auto-parsed data. Unlike previous work, we propose a new approach to improve dependency parsing with context-free dependency triples (CDT) extracted by using self-disambiguating patterns (SDP). The use of SDP makes it possible to avoid the dependency on a baseline parser and explore the influence of different types of substructures one by one. Additionally, taking the available CDTs as seeds, a label propagation process is used to tag a large number of unlabeled word pairs as CDTs. Experiments show that, when CDT features are integrated into a maximum spanning tree (MST) dependency parser, the new parser improves significantly over the baseline MST parser. Comparative results also show that CDTs with dependency relation labels perform much better than CDT without dependency relation label.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117113707","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}
Duc-Trong Le, Mai-Vu Tran, Tri-Thanh Nguyen, Quang-Thuy Ha
Co-reference resolution task still poses many challenges due to the complexity of the Vietnamese language, and the lack of standard Vietnamese linguistic resources. Based on the mention-pair model of Rahman and Ng. (2009) and the characteristics of Vietnamese, this paper proposes a model using support vector machines (SVM) to solve the co-reference in Vietnamese documents. The corpus used in experiments to evaluate the proposed model was constructed from 200 articles in cultural and social categories from vnexpress.net newspaper website. The results of the initial experiments of the proposed model achieved 76.51% accuracy in comparison with that of the baseline model of 73.79% with similar features.
{"title":"Co-reference Resolution in Vietnamese Documents Based on Support Vector Machines","authors":"Duc-Trong Le, Mai-Vu Tran, Tri-Thanh Nguyen, Quang-Thuy Ha","doi":"10.1109/IALP.2011.63","DOIUrl":"https://doi.org/10.1109/IALP.2011.63","url":null,"abstract":"Co-reference resolution task still poses many challenges due to the complexity of the Vietnamese language, and the lack of standard Vietnamese linguistic resources. Based on the mention-pair model of Rahman and Ng. (2009) and the characteristics of Vietnamese, this paper proposes a model using support vector machines (SVM) to solve the co-reference in Vietnamese documents. The corpus used in experiments to evaluate the proposed model was constructed from 200 articles in cultural and social categories from vnexpress.net newspaper website. The results of the initial experiments of the proposed model achieved 76.51% accuracy in comparison with that of the baseline model of 73.79% with similar features.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"64 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120982940","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}
Transliteration is the transformation of word in original language to another language based on its pronunciation. Back transliteration is the transformation of already transliterated word in another language back to its original form. This backward process is in nature more challenging than the forward direction because of more information lost. In many cases, the back transliteration can return almost exact result, which has a minor difference in spelling compared with the original word form. We propose in this work a lexical word similarity for dictionary matching in order to re-rank the candidates and enhance the performance of a grapheme-based location name back transliteration. This method is experimented on Vietnamese-English language pair and showed improvement.
{"title":"Lexical Word Similarity for Re-ranking in Vietnamese-English Named Entity Back Transliteration","authors":"Diem Thi Hoang Le, AiTi Aw","doi":"10.1109/IALP.2011.44","DOIUrl":"https://doi.org/10.1109/IALP.2011.44","url":null,"abstract":"Transliteration is the transformation of word in original language to another language based on its pronunciation. Back transliteration is the transformation of already transliterated word in another language back to its original form. This backward process is in nature more challenging than the forward direction because of more information lost. In many cases, the back transliteration can return almost exact result, which has a minor difference in spelling compared with the original word form. We propose in this work a lexical word similarity for dictionary matching in order to re-rank the candidates and enhance the performance of a grapheme-based location name back transliteration. This method is experimented on Vietnamese-English language pair and showed improvement.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134564636","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}
Summarization is a process of generating condensed form of a given text document, which retains its information and overall meaning. Document summarization approaches are broadly classified into two i.e. extractive summarization approach and abstractive summarization approach. In this paper, we performed single document summarization to generate summary of Telugu text document by using extractive summarization approach. Though there are many document surface features exists, we consider those features which can extensively cover original document and generates summary with less redundancy. We considered the features such as sentence position, sentence similarity with the title, centrality of the sentence and word frequency. To increase the strength of the features, we used a corpus which contains 3000 documents and performed various preprocessing steps like stop word elimination and stemming to retain more meaningful words within the sentence. Sentences are ranked by calculating the scores for each individual sentence by considering all four features simultaneously with optimum weights. The optimum weights to the feature are learned with the help human constructed summaries. The machine generated summaries are evaluated using F1 measure followed by human judgements.
{"title":"Corpus Based Extractive Document Summarization for Indic Script","authors":"P. Reddy, B. V. Vardhan, A. Govardhan","doi":"10.1109/IALP.2011.66","DOIUrl":"https://doi.org/10.1109/IALP.2011.66","url":null,"abstract":"Summarization is a process of generating condensed form of a given text document, which retains its information and overall meaning. Document summarization approaches are broadly classified into two i.e. extractive summarization approach and abstractive summarization approach. In this paper, we performed single document summarization to generate summary of Telugu text document by using extractive summarization approach. Though there are many document surface features exists, we consider those features which can extensively cover original document and generates summary with less redundancy. We considered the features such as sentence position, sentence similarity with the title, centrality of the sentence and word frequency. To increase the strength of the features, we used a corpus which contains 3000 documents and performed various preprocessing steps like stop word elimination and stemming to retain more meaningful words within the sentence. Sentences are ranked by calculating the scores for each individual sentence by considering all four features simultaneously with optimum weights. The optimum weights to the feature are learned with the help human constructed summaries. The machine generated summaries are evaluated using F1 measure followed by human judgements.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125013016","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}
In the processing of modern uygur corpus, it is necessary to make a word character mark study of the word level within the modern uygur language data. Since the classification of morpheme is to serve the mark of word character, the article classifies Uygur morphemes from their functions and lists their all classifications and arrangement rules.
{"title":"A Study of the Classification and Arrangement Rule of Uygur Morphemes for Information Processing","authors":"Pu Li, Shuzhen Shi","doi":"10.1109/IALP.2011.50","DOIUrl":"https://doi.org/10.1109/IALP.2011.50","url":null,"abstract":"In the processing of modern uygur corpus, it is necessary to make a word character mark study of the word level within the modern uygur language data. Since the classification of morpheme is to serve the mark of word character, the article classifies Uygur morphemes from their functions and lists their all classifications and arrangement rules.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"1047 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123141081","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}
Polarity shifting has been a challenge to automatic sentiment classification. In this paper, we create a corpus which consists of polarity-shifted sentences in various kinds of product reviews. In the corpus, both the sentimental words and shifting trigger words are annotated. Furthermore, we analyze all the polarity shifted sentences and categorize them into five categories: opinion-itself, holder, target, time and hypothesis. Experimental study shows the agreement of annotation and the distribution of the five categories of polarity shifting.
{"title":"Polarity Shifting: Corpus Construction and Analysis","authors":"Xiaoqian Zhang, Shoushan Li, Guodong Zhou, Hongxia Zhao","doi":"10.1109/IALP.2011.27","DOIUrl":"https://doi.org/10.1109/IALP.2011.27","url":null,"abstract":"Polarity shifting has been a challenge to automatic sentiment classification. In this paper, we create a corpus which consists of polarity-shifted sentences in various kinds of product reviews. In the corpus, both the sentimental words and shifting trigger words are annotated. Furthermore, we analyze all the polarity shifted sentences and categorize them into five categories: opinion-itself, holder, target, time and hypothesis. Experimental study shows the agreement of annotation and the distribution of the five categories of polarity shifting.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122669284","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}
A. Al-Subaihin, Hend Suliman Al-Khalifa, A. Al-Salman
Recently, natural language processing tasks are more frequently conducted over online content. This poses a special problem for applications over Arabic language. Online Arabic content is usually written in informal colloquial Arabic, which is characterized to be ill-structured and lacks specific linguistic standardization. In this paper, we investigate a preliminary step to conduct successful NLP processing which is the problem of sentence boundary detection. As informal Arabic lacks basic linguistic rules, we establish a list of commonly used punctuation marks after extensively studying a large amount of informal Arabic text. Moreover, we evaluated the correct usage of these punctuation marks as sentence delimiters; the result yielded a preliminary accuracy of 70%.
{"title":"Sentence Boundary Detection in Colloquial Arabic Text: A Preliminary Result","authors":"A. Al-Subaihin, Hend Suliman Al-Khalifa, A. Al-Salman","doi":"10.1109/IALP.2011.38","DOIUrl":"https://doi.org/10.1109/IALP.2011.38","url":null,"abstract":"Recently, natural language processing tasks are more frequently conducted over online content. This poses a special problem for applications over Arabic language. Online Arabic content is usually written in informal colloquial Arabic, which is characterized to be ill-structured and lacks specific linguistic standardization. In this paper, we investigate a preliminary step to conduct successful NLP processing which is the problem of sentence boundary detection. As informal Arabic lacks basic linguistic rules, we establish a list of commonly used punctuation marks after extensively studying a large amount of informal Arabic text. Moreover, we evaluated the correct usage of these punctuation marks as sentence delimiters; the result yielded a preliminary accuracy of 70%.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121480948","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：