This paper presents an approach to select appropriate translation rules to improve phrase-reordering of tree-based statistical machine translation. We propose new features with rich linguistic and contextual information. We give a new algorithm to extract features, use maximum entropy to combine rich linguistic and contextual information and integrate these features into the tree-based SMT model (Moses-chart). We obtain substantial improvements in performance for tree-based translation from Vietnamese to English.
{"title":"Using Rich Linguistic and Contextual Information for Tree-Based Statistical Machine Translation","authors":"Bui Thanh Hung, Minh Le Nguyen, Akira Shimazu","doi":"10.1109/IALP.2011.60","DOIUrl":"https://doi.org/10.1109/IALP.2011.60","url":null,"abstract":"This paper presents an approach to select appropriate translation rules to improve phrase-reordering of tree-based statistical machine translation. We propose new features with rich linguistic and contextual information. We give a new algorithm to extract features, use maximum entropy to combine rich linguistic and contextual information and integrate these features into the tree-based SMT model (Moses-chart). We obtain substantial improvements in performance for tree-based translation from Vietnamese to English.","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":"116220565","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 Sentence-level Semantic annotated Corpus (SSC) is directed by HNC (Hierarchical Network of Concepts) Theory in which the sentence is regarded as the basic unit and semantic and frame information are annotated. This paper introduces the building form of the semantic annotated corpus with XML, describes the content of semantic annotation on sentence level that the annotated contents can be classified three items: sentence category, which is the sentence semantic type; semantic chunks, which is the lower level semantic components in the sentence; sub-sentence (sentence ecdysis and chunk-extension-into-sentence) which is included in semantic chunks. SSC has been an important and valuable knowledge resource for language study and information processing.
句子级语义标注语料库是以句子为基本单位，对语义和框架信息进行标注的HNC (Hierarchical Network of Concepts)理论指导下的语料库。本文介绍了用XML构建语义标注语料库的形式，在句子层次上描述了语义标注的内容，标注的内容可分为三类:句子类别，即句子的语义类型;语义块是句子中较低层次的语义成分;语义块中包含的子句(句子分解和块扩展成句)。SSC已成为语言学习和信息处理的重要而宝贵的知识资源。
{"title":"A Sentence-Level Semantic Annotated Corpus Based on HNC Theory","authors":"Zhiying Liu, Yaohong Jin, Chuanjiang Miao","doi":"10.1109/IALP.2011.11","DOIUrl":"https://doi.org/10.1109/IALP.2011.11","url":null,"abstract":"The Sentence-level Semantic annotated Corpus (SSC) is directed by HNC (Hierarchical Network of Concepts) Theory in which the sentence is regarded as the basic unit and semantic and frame information are annotated. This paper introduces the building form of the semantic annotated corpus with XML, describes the content of semantic annotation on sentence level that the annotated contents can be classified three items: sentence category, which is the sentence semantic type; semantic chunks, which is the lower level semantic components in the sentence; sub-sentence (sentence ecdysis and chunk-extension-into-sentence) which is included in semantic chunks. SSC has been an important and valuable knowledge resource for language study and information processing.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"338 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":"115672136","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 query-by-humming (QBH) system deals with retrieving the original song or music from the knowledge of its humming tune. In this paper, we present a novel Derivative Dynamic Time Warping (DDTW) based method for querying desired songs in Hindi (an Indian language) from a database by humming the tune. The system presented here use both intuitive as well as performance-specific criterion to process the query humming. In this paper, pitch contour extracted from the humming signal is used as source feature for all the experiments. The approach presented here can be exploited for improving performance of QBH system to index the music for fast retrieval. The results obtained using proposed DDTW approach are compared with standard Dynamic Time Warping (DTW) approach and are found to be better for smaller window size.
{"title":"Design of a Query-by-Humming System for Hindi Songs Using DDTW Based Approach","authors":"P. Jain, Robin Jain, H. Patil, T. Basu","doi":"10.1109/IALP.2011.68","DOIUrl":"https://doi.org/10.1109/IALP.2011.68","url":null,"abstract":"A query-by-humming (QBH) system deals with retrieving the original song or music from the knowledge of its humming tune. In this paper, we present a novel Derivative Dynamic Time Warping (DDTW) based method for querying desired songs in Hindi (an Indian language) from a database by humming the tune. The system presented here use both intuitive as well as performance-specific criterion to process the query humming. In this paper, pitch contour extracted from the humming signal is used as source feature for all the experiments. The approach presented here can be exploited for improving performance of QBH system to index the music for fast retrieval. The results obtained using proposed DDTW approach are compared with standard Dynamic Time Warping (DTW) approach and are found to be better for smaller window size.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"1 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":"129568104","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}
According to the cognitive linguistics, metaphor and metonymy, as the two basic cognitive methods, are the main resource of meaning extension. Based on that, we attempted to explore the meaning extension modes through studying the concrete language materials of Kan and the visual verb group. The extensions of Kan, the basic level category word, are motivated by the two metaphorical modes of thinking-as-vision and mentality-as-vision, the three metonymic modes of "core behavior and its supportive acts", "the whole event and its parts" and "the behavioral result and its process". Most visual verbs have the metaphorical extensions and inherit the mind-as-vision and mentality-as-vision modes of Kan. It shows that the whole word group is affected by the same metaphorical and metonymic mechanisms. The extensions of word meanings in one group share the same modes. In order to improve the intelligent level of natural language processing, we should not only mark the existing meaning extensions into the machine readable dictionary, but, more important, turn the extension modes into executable programs that will make the machine have a certain capability of sense prediction. The extension modes should be explored with word group as unit and basic level category words as emphasis.
{"title":"An Exploration on the Modes of Word Meaning Extension Based on Metaphorical and Metonymic Mechanisms","authors":"Xiaofang Ouyang","doi":"10.1109/IALP.2011.20","DOIUrl":"https://doi.org/10.1109/IALP.2011.20","url":null,"abstract":"According to the cognitive linguistics, metaphor and metonymy, as the two basic cognitive methods, are the main resource of meaning extension. Based on that, we attempted to explore the meaning extension modes through studying the concrete language materials of Kan and the visual verb group. The extensions of Kan, the basic level category word, are motivated by the two metaphorical modes of thinking-as-vision and mentality-as-vision, the three metonymic modes of \"core behavior and its supportive acts\", \"the whole event and its parts\" and \"the behavioral result and its process\". Most visual verbs have the metaphorical extensions and inherit the mind-as-vision and mentality-as-vision modes of Kan. It shows that the whole word group is affected by the same metaphorical and metonymic mechanisms. The extensions of word meanings in one group share the same modes. In order to improve the intelligent level of natural language processing, we should not only mark the existing meaning extensions into the machine readable dictionary, but, more important, turn the extension modes into executable programs that will make the machine have a certain capability of sense prediction. The extension modes should be explored with word group as unit and basic level category words as emphasis.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"266 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":"133316866","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}
This paper describes the challenges faced in language learning and use, with a focus on domain-specific vocabulary learning. We focus on the architecture and the presentation model of domain-specific knowledge components. The paper first discusses the significance of assistive mechanisms for vocabulary learning in an academic domain and then outlines two architectures for the presentation model. We suggest how the design of this environment for vocabulary use and learning in the academic domain must adopt different presentations and search strategies to confront the specific challenges in the domain. As this problem can only be solved on a long term basis, we also briefly describe a set of games as a first step in the implementation of the assistive mechanisms.
{"title":"Games for Academic Vocabulary Learning through a Virtual Environment","authors":"K. Pala, Anil Kumar Singh, S. Gangashetty","doi":"10.1109/IALP.2011.67","DOIUrl":"https://doi.org/10.1109/IALP.2011.67","url":null,"abstract":"This paper describes the challenges faced in language learning and use, with a focus on domain-specific vocabulary learning. We focus on the architecture and the presentation model of domain-specific knowledge components. The paper first discusses the significance of assistive mechanisms for vocabulary learning in an academic domain and then outlines two architectures for the presentation model. We suggest how the design of this environment for vocabulary use and learning in the academic domain must adopt different presentations and search strategies to confront the specific challenges in the domain. As this problem can only be solved on a long term basis, we also briefly describe a set of games as a first step in the implementation of the assistive mechanisms.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"7 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":"128603428","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}
Singing voice synthesis is an interesting research due to its wide application in entertainment systems. The generation of singing voice normally replies on techniques of changing the fundamental frequency of existing vocal recording. When the fundamental frequency of vocal signal is changed to match the intended pitch contour of the song, the melody is correctly implemented. However, if there is a great change over the pitch of a vocal signal, the spectrum of the signal should also change accordingly so as to generate a natural singing voice. Unfortunately, currently the spectrum differences for singing voice at different pitch level are unclear. Therefore, the relationship between the spectrum and pitch needs to be examined. As formants are important elements of spectrum, therefore in this research we look at the relationship between formants and pitch. For a start, we first examine the sound of 'ah' at different pitch levels for both male and female voices.
{"title":"Analyzing the Relationship between Formants and Pitch for Singing Voice","authors":"Hwee Teng Tan, M. Dong","doi":"10.1109/IALP.2011.80","DOIUrl":"https://doi.org/10.1109/IALP.2011.80","url":null,"abstract":"Singing voice synthesis is an interesting research due to its wide application in entertainment systems. The generation of singing voice normally replies on techniques of changing the fundamental frequency of existing vocal recording. When the fundamental frequency of vocal signal is changed to match the intended pitch contour of the song, the melody is correctly implemented. However, if there is a great change over the pitch of a vocal signal, the spectrum of the signal should also change accordingly so as to generate a natural singing voice. Unfortunately, currently the spectrum differences for singing voice at different pitch level are unclear. Therefore, the relationship between the spectrum and pitch needs to be examined. As formants are important elements of spectrum, therefore in this research we look at the relationship between formants and pitch. For a start, we first examine the sound of 'ah' at different pitch levels for both male and female voices.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"16 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":"125063387","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}
This paper presents an pilot study that applies eye tracking technology to analyze the effect of Arabic language on reading English for Arab EFL learners. The outcome of this study reveals a strong relationship between the way Arabic is read and the reading of English text for EFL students.
{"title":"The Effect of Arabic Language on Reading English for Arab EFL Learners: An Eye Tracking Study","authors":"Kholod S. Al-Khalifah, Hend Suliman Al-Khalifa","doi":"10.1109/IALP.2011.18","DOIUrl":"https://doi.org/10.1109/IALP.2011.18","url":null,"abstract":"This paper presents an pilot study that applies eye tracking technology to analyze the effect of Arabic language on reading English for Arab EFL learners. The outcome of this study reveals a strong relationship between the way Arabic is read and the reading of English text for EFL students.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129432273","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 this paper, we present an in-car Chinese noise corpus that can be used in simulating complicated car environment for robust speech recognition research and experiment. The corpus was collected in mainland China in 2009 and 2010. The corpus includes a diversity of car conditions including different car speed, open/close windows, weather conditions as well as environment conditions. Specially, the rumble strips are also taken into account due to the typical noise generated as the car is passing on. In order to use the corpus efficiently, we performed some acoustic signal analyses on those noise data, mainly focused on stationary properties and energy distribution in the frequency domain. We also performed ASR experiments using selected noise data from the corpus, by adding noise data to clean speech to simulate the in-car environment. The corpus is the first of its kind for in-car Chinese noise corpus, providing abundant and diversified samples for car noise speech recognition task.
{"title":"An In-car Chinese Noise Corpus for Speech Recognition","authors":"Jue Hou, Yi Liu, Chao Zhang, Shilei Huang","doi":"10.1109/IALP.2011.74","DOIUrl":"https://doi.org/10.1109/IALP.2011.74","url":null,"abstract":"In this paper, we present an in-car Chinese noise corpus that can be used in simulating complicated car environment for robust speech recognition research and experiment. The corpus was collected in mainland China in 2009 and 2010. The corpus includes a diversity of car conditions including different car speed, open/close windows, weather conditions as well as environment conditions. Specially, the rumble strips are also taken into account due to the typical noise generated as the car is passing on. In order to use the corpus efficiently, we performed some acoustic signal analyses on those noise data, mainly focused on stationary properties and energy distribution in the frequency domain. We also performed ASR experiments using selected noise data from the corpus, by adding noise data to clean speech to simulate the in-car environment. The corpus is the first of its kind for in-car Chinese noise corpus, providing abundant and diversified samples for car noise speech recognition task.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126052937","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}
By comparing the eye movement data of Thai students reading Chinese texts with or without marks for word boundaries, the researcher has found that: (1) To Thai students, the Chinese words represent more Psychological reality than Chinese characters. (2) The reading efficiency of Thai students could be immensely improved by inserting word boundary marks. It is, therefore, suggested that when publishing Chinese textbooks intended for Thai students, we adjust the way we do typesetting today and insert word boundary marks into the text.
{"title":"A Study on Eye Movement of Thai Students Reading Chinese Texts with or without Marks for Word Boundaries","authors":"Y. Jiao, YU Peng","doi":"10.1109/IALP.2011.35","DOIUrl":"https://doi.org/10.1109/IALP.2011.35","url":null,"abstract":"By comparing the eye movement data of Thai students reading Chinese texts with or without marks for word boundaries, the researcher has found that: (1) To Thai students, the Chinese words represent more Psychological reality than Chinese characters. (2) The reading efficiency of Thai students could be immensely improved by inserting word boundary marks. It is, therefore, suggested that when publishing Chinese textbooks intended for Thai students, we adjust the way we do typesetting today and insert word boundary marks into the text.","PeriodicalId":297167,"journal":{"name":"2011 International Conference on Asian Language Processing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673182","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：