Pub Date : 2010-09-30DOI: 10.1109/NLPKE.2010.5587792
Xinxin Li, Xuan Wang, Lin Yao
This paper proposes how to convert projective dependency structures into flat phrase structures with language-independent syntactic categories, and use a head finder algorithm to convert these phrase structures back into dependency structures. The head finder algorithm is implemented by a maximum entropy approach with constraint information. The converted phrase structures can be parsed using a hierarchical coarse-to-fine method with latent variables. Experimental results show that the approach finds 98.8% heads of all phrases, and our algorithm achieves state-of-the-art dependency parsing performance in English Treebank.
{"title":"Conversion between dependency structures and phrase structures using a head finder algorithm","authors":"Xinxin Li, Xuan Wang, Lin Yao","doi":"10.1109/NLPKE.2010.5587792","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587792","url":null,"abstract":"This paper proposes how to convert projective dependency structures into flat phrase structures with language-independent syntactic categories, and use a head finder algorithm to convert these phrase structures back into dependency structures. The head finder algorithm is implemented by a maximum entropy approach with constraint information. The converted phrase structures can be parsed using a hierarchical coarse-to-fine method with latent variables. Experimental results show that the approach finds 98.8% heads of all phrases, and our algorithm achieves state-of-the-art dependency parsing performance in English Treebank.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127272336","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 : 2010-09-30DOI: 10.1109/NLPKE.2010.5587788
Hongying Zan, Kuizhong Kou, Jiale Tian
Sentiment categorization have been widely explored in many fields, such as government policy, information monitoring, product tracking, etc. This paper adopts k-NN, Naive Bayes and SVM classifiers to categorize sentiments contained in on-line Chinese reviews on digital products. Our experimental results show that combining the words and phrases with sentiment orientation as hybrid features, SWM classifier achieves an accuracy of 96,47%, which is words of all parts of speech as features.
{"title":"Application of Chinese sentiment categorization to digital products reviews","authors":"Hongying Zan, Kuizhong Kou, Jiale Tian","doi":"10.1109/NLPKE.2010.5587788","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587788","url":null,"abstract":"Sentiment categorization have been widely explored in many fields, such as government policy, information monitoring, product tracking, etc. This paper adopts k-NN, Naive Bayes and SVM classifiers to categorize sentiments contained in on-line Chinese reviews on digital products. Our experimental results show that combining the words and phrases with sentiment orientation as hybrid features, SWM classifier achieves an accuracy of 96,47%, which is words of all parts of speech as features.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127481383","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 : 2010-09-30DOI: 10.1109/NLPKE.2010.5587863
Jiang Yang, Min Hou, Ning Wang
We present an approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences. Considering the features of Chinese reviews, we firstly identify the topic of a review using an n-gram matching approach. To extract candidate topic sentiment sentences, we compute the semantic similarity between a given sentence and the ascertained topic and meanwhile determine whether the sentence is subjective. A certain number of these sentences are then selected as representatives according to their semantic similarity value with relation to the topic. The average value of the representative topic sentiment sentences is calculated and taken as the sentiment polarity of a review. Experiment results show that the proposed method is feasible and can achieve relatively high precision.
{"title":"Recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences","authors":"Jiang Yang, Min Hou, Ning Wang","doi":"10.1109/NLPKE.2010.5587863","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587863","url":null,"abstract":"We present an approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences. Considering the features of Chinese reviews, we firstly identify the topic of a review using an n-gram matching approach. To extract candidate topic sentiment sentences, we compute the semantic similarity between a given sentence and the ascertained topic and meanwhile determine whether the sentence is subjective. A certain number of these sentences are then selected as representatives according to their semantic similarity value with relation to the topic. The average value of the representative topic sentiment sentences is calculated and taken as the sentiment polarity of a review. Experiment results show that the proposed method is feasible and can achieve relatively high precision.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126734880","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 : 2010-09-30DOI: 10.1109/NLPKE.2010.5587796
Ying Huang, Wei Li
A new algorithm of fuzzy support vector machine based on niche is presented in this paper. In this algorithm, through comparing samples niche with class niche, the method of simply using Euclidean distance to measure the relationship of samples and class in the traditional support vector machine is changed by using the minimum radius in class niche, and the disadvantages of traditional support vector machine, which are sensitive to noise and outliers, and poor performance of differentiation of valid samples are overcome. Experimental data show that compared with the traditional support vector machine which only uses the distance between the sample and the center of class, this new algorithm can improve the convergence speed, and thus greatly enhance the discrimination between valid samples and noise samples.
{"title":"A new algorithm of fuzzy support vector machine based on niche","authors":"Ying Huang, Wei Li","doi":"10.1109/NLPKE.2010.5587796","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587796","url":null,"abstract":"A new algorithm of fuzzy support vector machine based on niche is presented in this paper. In this algorithm, through comparing samples niche with class niche, the method of simply using Euclidean distance to measure the relationship of samples and class in the traditional support vector machine is changed by using the minimum radius in class niche, and the disadvantages of traditional support vector machine, which are sensitive to noise and outliers, and poor performance of differentiation of valid samples are overcome. Experimental data show that compared with the traditional support vector machine which only uses the distance between the sample and the center of class, this new algorithm can improve the convergence speed, and thus greatly enhance the discrimination between valid samples and noise samples.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128718342","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 : 2010-09-30DOI: 10.1109/NLPKE.2010.5587809
Xing Zhang, Yan Song, A. Fang
A machine learning framework, Conditional Random fields (CRF), is constructed in this study, which exploits syntactic information to recognize biomedical terms. Features used in this CRF framework focus on syntactic information in different levels, including parent nodes, syntactic functions, syntactic paths and term ratios. A series of experiments have been done to study the effects of training sizes, general term recognition and novel term recognition. The experiment results show that features as syntactic paths and term ratios can achieve good precision of term recognition, including both general terms and novel terms. However, the recall of novel term recognition is still unsatisfactory, which calls for more effective features to be used. All in all, as this research studies in depth the uses of some unique syntactic features, it is innovative in respect of constructing machine learning based term recognition system.
本研究构建了一个机器学习框架条件随机场(Conditional Random fields, CRF)，该框架利用句法信息来识别生物医学术语。该CRF框架中使用的功能侧重于不同层次的语法信息，包括父节点、语法函数、语法路径和词比。通过一系列实验研究了训练大小、通用术语识别和新术语识别的影响。实验结果表明，句法路径特征和词项比例特征都能达到较好的词项识别精度，既包括通用词项，也包括新词项。然而，新语项识别的召回率仍然不理想，这需要使用更有效的特征。总而言之，由于本研究深入研究了一些独特的句法特征的使用，因此在构建基于机器学习的术语识别系统方面具有创新性。
{"title":"Term recognition using Conditional Random fields","authors":"Xing Zhang, Yan Song, A. Fang","doi":"10.1109/NLPKE.2010.5587809","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587809","url":null,"abstract":"A machine learning framework, Conditional Random fields (CRF), is constructed in this study, which exploits syntactic information to recognize biomedical terms. Features used in this CRF framework focus on syntactic information in different levels, including parent nodes, syntactic functions, syntactic paths and term ratios. A series of experiments have been done to study the effects of training sizes, general term recognition and novel term recognition. The experiment results show that features as syntactic paths and term ratios can achieve good precision of term recognition, including both general terms and novel terms. However, the recall of novel term recognition is still unsatisfactory, which calls for more effective features to be used. All in all, as this research studies in depth the uses of some unique syntactic features, it is innovative in respect of constructing machine learning based term recognition system.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116763361","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 : 2010-08-01DOI: 10.1109/NLPKE.2010.5587818
Guiping Zhang, Ying Sun, Baosheng Yin, Na Ye
How to evaluate the translation of a machine translation system is a very important research topic. The traditional method of translation evaluation without reference is used to evaluate the translation from the linguistic characteristics mostly. In this paper, the user cost of post-editing operation is considered, and a new method of evaluation translation based on user behavior model is proposed. First of all, track and record the process from the post-editing of machine translation to the forming of the final translation, and extract the decision knowledge of a user behavior; then use the knowledge as an indicator of translation evaluation, and evaluate the machine translation by combining with a language model. Experimental results show that in the absence of reference, the present method is much better than the method of using linguistic characteristics only, and the present method is close to BLEU method with one reference in Spearmen's rank order correlation coefficient with human evaluation.
{"title":"Translation evaluation without reference based on user behavior model","authors":"Guiping Zhang, Ying Sun, Baosheng Yin, Na Ye","doi":"10.1109/NLPKE.2010.5587818","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587818","url":null,"abstract":"How to evaluate the translation of a machine translation system is a very important research topic. The traditional method of translation evaluation without reference is used to evaluate the translation from the linguistic characteristics mostly. In this paper, the user cost of post-editing operation is considered, and a new method of evaluation translation based on user behavior model is proposed. First of all, track and record the process from the post-editing of machine translation to the forming of the final translation, and extract the decision knowledge of a user behavior; then use the knowledge as an indicator of translation evaluation, and evaluate the machine translation by combining with a language model. Experimental results show that in the absence of reference, the present method is much better than the method of using linguistic characteristics only, and the present method is close to BLEU method with one reference in Spearmen's rank order correlation coefficient with human evaluation.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134243175","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 : 2010-08-01DOI: 10.1109/NLPKE.2010.5587839
N. Ehsan, Heshaam Faili
With improvements in industry and information technology, large volumes of electronic texts such as newspapers, emails, weblogs, books and thesis are produced daily. Producing electrical documents has considerable benefits such as easy organizing and data management. Therefore, existence of automatic systems such as spell and grammar checker/corrector can help in reducing costs and increasing the electronic texts and it will improve the quality of electronic texts. You can input your text and the computer program will point out to you the spelling errors. It may also help with your grammar. Grammatical errors are described as wrong relation between words like subject-verb disagreement or wrong sequence of words like using plural noun where a single noun is needed. Grammar checking phase starts after spell checking is finished. This paper briefly describes the concepts and definition of grammar checkers in general followed by developing the first Persian (Farsi) grammar checker leading to an overview of the error types of Persian language. The proposed system detects and corrects about 20 frequent Persian grammar errors and tested on a sample dataset, retrieved about 70% and 83% accuracy respect to precision and recall metrics.
{"title":"Towards grammar checker development for Persian language","authors":"N. Ehsan, Heshaam Faili","doi":"10.1109/NLPKE.2010.5587839","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587839","url":null,"abstract":"With improvements in industry and information technology, large volumes of electronic texts such as newspapers, emails, weblogs, books and thesis are produced daily. Producing electrical documents has considerable benefits such as easy organizing and data management. Therefore, existence of automatic systems such as spell and grammar checker/corrector can help in reducing costs and increasing the electronic texts and it will improve the quality of electronic texts. You can input your text and the computer program will point out to you the spelling errors. It may also help with your grammar. Grammatical errors are described as wrong relation between words like subject-verb disagreement or wrong sequence of words like using plural noun where a single noun is needed. Grammar checking phase starts after spell checking is finished. This paper briefly describes the concepts and definition of grammar checkers in general followed by developing the first Persian (Farsi) grammar checker leading to an overview of the error types of Persian language. The proposed system detects and corrects about 20 frequent Persian grammar errors and tested on a sample dataset, retrieved about 70% and 83% accuracy respect to precision and recall metrics.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134301675","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 : 2010-08-01DOI: 10.1109/NLPKE.2010.5587790
Changqin Quan, Tingting He, F. Ren
Previous researches for emotional analysis of texts have included a variety of text contents: weblogs, stories, news, text messages, spoken dialogs, and so on. Compared with other text styles, the main characteristics of emotional expressions in blogs are as follows: (1) Highly personal, subjective writing style; (2) New words and expressions are constantly emerging; (3) The integrity and continuity of using language. Using a Chinese emotion corpus (Ren-CECps), in this study, we make an analysis on emotion expressions in blogs at sentence level. Firstly, we separate the sentences into two classes: simple sentences (sentences without negative words, conjunctions, or question mark) and complex sentences (sentences with negative words, conjunctions, or question mark). Then we compare the two classes of sentence on sentence emotion recognition based on emotional words. Furthermore we analysis the following factors for emotion change at sentence level: negative words, conjunctions, punctuation marks, and contextual emotions. At last, we make an hypothesis that the emotional focus of a sentence could be expressed by a certain clause in this sentence, and the experimental results have proved this hypothesis, which showed that selecting the clauses containing emotional focus of a sentence correctly would be helpful to recognize sentence emotions.
{"title":"Emotion analysis in blogs at sentence level using a Chinese emotion corpus","authors":"Changqin Quan, Tingting He, F. Ren","doi":"10.1109/NLPKE.2010.5587790","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587790","url":null,"abstract":"Previous researches for emotional analysis of texts have included a variety of text contents: weblogs, stories, news, text messages, spoken dialogs, and so on. Compared with other text styles, the main characteristics of emotional expressions in blogs are as follows: (1) Highly personal, subjective writing style; (2) New words and expressions are constantly emerging; (3) The integrity and continuity of using language. Using a Chinese emotion corpus (Ren-CECps), in this study, we make an analysis on emotion expressions in blogs at sentence level. Firstly, we separate the sentences into two classes: simple sentences (sentences without negative words, conjunctions, or question mark) and complex sentences (sentences with negative words, conjunctions, or question mark). Then we compare the two classes of sentence on sentence emotion recognition based on emotional words. Furthermore we analysis the following factors for emotion change at sentence level: negative words, conjunctions, punctuation marks, and contextual emotions. At last, we make an hypothesis that the emotional focus of a sentence could be expressed by a certain clause in this sentence, and the experimental results have proved this hypothesis, which showed that selecting the clauses containing emotional focus of a sentence correctly would be helpful to recognize sentence emotions.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124393457","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 : 2010-08-01DOI: 10.1109/NLPKE.2010.5587816
Suke Li, Jinmei Hao, Zhong Chen
This paper proposes a tagging method that can highlight important service aspects for users who browse online service reviews. Experiments on service aspect ranking and review tagging show that the proposed method is effective for finding important aspects and can generate useful and interesting tags for reviews.
{"title":"Tagging online service reviews","authors":"Suke Li, Jinmei Hao, Zhong Chen","doi":"10.1109/NLPKE.2010.5587816","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587816","url":null,"abstract":"This paper proposes a tagging method that can highlight important service aspects for users who browse online service reviews. Experiments on service aspect ranking and review tagging show that the proposed method is effective for finding important aspects and can generate useful and interesting tags for reviews.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124906707","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 : 2010-08-01DOI: 10.1109/NLPKE.2010.5587851
R. Niemeijer, B. Vries, J. Beetz
To facilitate mass customization in the building industry, an automated method is needed to check the validity of user-created designs. This check requires that numerous complex building codes and regulations, as well as architects' demands are formalized and captured by non-programming domain experts. This can be done via a natural language interface, as it reduces the required amount of training of users. In this paper we describe an algorithm for interpreting architectural constraints in such a system.
{"title":"Constraint Soup","authors":"R. Niemeijer, B. Vries, J. Beetz","doi":"10.1109/NLPKE.2010.5587851","DOIUrl":"https://doi.org/10.1109/NLPKE.2010.5587851","url":null,"abstract":"To facilitate mass customization in the building industry, an automated method is needed to check the validity of user-created designs. This check requires that numerous complex building codes and regulations, as well as architects' demands are formalized and captured by non-programming domain experts. This can be done via a natural language interface, as it reduces the required amount of training of users. In this paper we describe an algorithm for interpreting architectural constraints in such a system.","PeriodicalId":259975,"journal":{"name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132521102","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：