87 research outputs found
A statistical test spectrum: from robust to powerful
No full textThe concept of Scale Curve provides a graphical tool for analysis of multivariate data, with a broad range of statistical applications. Recent research in variants of Scale Curves have shown great promise, as they can be easily adapted to build robust non-parametric testing procedures under various scenarios, while preserving good power, and retaining the crucial virtues of easy computation and simple graphical representation.
This thesis investigates the properties of one such variant of Scale Curves, named the Determinant Scale Curve (dsc). It is shown that the dsc can be used to devise non-parametric exact tests for location of multivariate data with a special property (stated in next paragraph), under both one sample and multi-sample setups. Similar ideas are extended to tackle problems in linear regression, where the dsc is used to build tests for significance of the slope parameter.
For all the problems discussed, the dsc's actually provide a whole spectrum of tests. The tests at the rightmost end of the spectrum are shown to be Pitman equivalent to the benchmark most powerful tests for the given problem. As one moves towards the other end, the corresponding tests become progressively more and more robust, i.e. insensitive to outliers. Simulation results show that this robustification does not come with a serious loss of power under most situations.Ph.D.Includes bibliographical references (p. 61-63)by Somnath Mukherje
Code Mixed Cross Script Factoid Question Classification - A Deep Learning Approach
No full text[EN] Before the advent of the Internet era, code-mixing was mainly used in the spoken form. However, with the recent popular informal networking platforms such as Facebook, Twitter, Instagram, etc., in social media, code-mixing is being used more and more in written form. User-generated social media content is becoming an increasingly important resource in applied linguistics. Recent trends in social media usage have led to a proliferation of studies on social media content. Multilingual social media users often write native language content in non-native script (cross-script). Recently Banerjee et al. [9] introduced the code-mixed cross-script question answering research problem and reported that the ever increasing social media content could serve as a potential digital resource for less-computerized languages to build question answering systems. Question classification is a core task in question answering in which questions are assigned a class or a number of classes which denote the expected answer type(s). In this research work, we address the question classification task as part of the code-mixed cross-script question answering research problem. We combine deep learning framework with feature engineering to address the question classification task and enhance the state-of-the-art question classification accuracy by over 4% for code-mixed cross-script questions.The work of the third author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project.Banerjee, S.; Kumar Naskar, S.; Rosso, P.; Bandyopadhyay, S. (2018). Code Mixed Cross Script Factoid Question Classification - A Deep Learning Approach. Journal of Intelligent & Fuzzy Systems. 34(5):2959-2969. https://doi.org/10.3233/JIFS-169481S2959296934
MSIR@FIRE: A Comprehensive Report from 2013 to 2016
No full text[EN] India is a nation of geographical and cultural diversity where over 1600 dialects are spoken by the people. With the technological advancement, penetration of the internet and cheaper access to mobile data, India has recently seen a sudden growth
of internet users. These Indian internet users generate contents either in English or in other vernacular Indian languages.
To develop technological solutions for the contents generated by the Indian users using the Indian languages, the Forum
for Information Retrieval Evaluation (FIRE) was established and held for the first time in 2008. Although Indian languages
are written using indigenous scripts, often websites and user-generated content (such as tweets and blogs) in these Indian
languages are written using Roman script due to various socio-cultural and technological reasons. A challenge that search
engines face while processing transliterated queries and documents is that of extensive spelling variation. MSIR track was
first introduced in 2013 at FIRE and the aim of MSIR was to systematically formalize several research problems that one must
solve to tackle the code mixing in Web search for users of many languages around the world, develop related data sets, test
benches and most importantly, build a research community focusing on this important problem that has received very little attention. This document is a comprehensive report on the 4 years of MSIR track evaluated at FIRE between 2013 and 2016.Somnath Banerjee and Sudip Kumar Naskar are supported by Media Lab Asia, MeitY, Government of India, under the Visvesvaraya PhD Scheme for Electronics & IT. The work of Paolo Rosso was partially supported by the MISMIS research project PGC2018-096212-B-C31 funded by the Spanish MICINN.Banerjee, S.; Choudhury, M.; Chakma, K.; Kumar Naskar, S.; Das, A.; Bandyopadhyay, S.; Rosso, P. (2020). MSIR@FIRE: A Comprehensive Report from 2013 to 2016. SN Computer Science. 1(55):1-15. https://doi.org/10.1007/s42979-019-0058-0S115155Ahmed UZ, Bali K, Choudhury M, Sowmya VB. Challenges in designing input method editors for Indian languages: the role of word-origin and context. In: Advances in text input methods (WTIM 2011). 2011. pp. 1–9Banerjee S, Chakma K, Naskar SK, Das A, Rosso P, Bandyopadhyay S, Choudhury M. Overview of the mixed script information retrieval (MSIR) at fire-2016. In: Forum for information retrieval evaluation. Springer; 2016. pp. 39–49.Banerjee S, Kuila A, Roy A, Naskar SK, Rosso P, Bandyopadhyay S. A hybrid approach for transliterated word-level language identification: CRF with post-processing heuristics. In: Proceedings of the forum for information retrieval evaluation, ACM, 2014. pp. 54–59.Banerjee S, Naskar S, Rosso P, Bandyopadhyay S. Code mixed cross script factoid question classification—a deep learning approach. J Intell Fuzzy Syst. 2018;34(5):2959–69.Banerjee S, Naskar SK, Rosso P, Bandyopadhyay S. The first cross-script code-mixed question answering corpus. In: Proceedings of the workshop on modeling, learning and mining for cross/multilinguality (MultiLingMine 2016), co-located with the 38th European Conference on Information Retrieval (ECIR). 2016.Banerjee S, Naskar SK, Rosso P, Bandyopadhyay S. Named entity recognition on code-mixed cross-script social media content. Comput Sistemas. 2017;21(4):681–92.Barman U, Das A, Wagner J, Foster J. Code mixing: a challenge for language identification in the language of social media. In: Proceedings of the first workshop on computational approaches to code switching. 2014. pp. 13–23.Bhardwaj P, Pakray P, Bajpeyee V, Taneja A. Information retrieval on code-mixed Hindi–English tweets. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. 2016.Bhargava R, Khandelwal S, Bhatia A, Sharmai Y. Modeling classifier for code mixed cross script questions. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Bhattacharjee D, Bhattacharya, P. Ensemble classifier based approach for code-mixed cross-script question classification. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Chakma K, Das A. CMIR: a corpus for evaluation of code mixed information retrieval of Hindi–English tweets. In: The 17th international conference on intelligent text processing and computational linguistics (CICLING). 2016.Choudhury M, Chittaranjan G, Gupta P, Das A. Overview of fire 2014 track on transliterated search. Proceedings of FIRE. 2014. pp. 68–89.Ganguly D, Pal S, Jones GJ. Dcu@fire-2014: fuzzy queries with rule-based normalization for mixed script information retrieval. In: Proceedings of the forum for information retrieval evaluation, ACM, 2014. pp. 80–85.Gella S, Sharma J, Bali K. Query word labeling and back transliteration for Indian languages: shared task system description. FIRE Working Notes. 2013;3.Gupta DK, Kumar S, Ekbal A. Machine learning approach for language identification and transliteration. In: Proceedings of the forum for information retrieval evaluation, ACM, 2014. pp. 60–64.Gupta P, Bali K, Banchs RE, Choudhury M, Rosso P. Query expansion for mixed-script information retrieval. In: Proceedings of the 37th international ACM SIGIR conference on research and development in information retrieval, ACM, 2014. pp. 677–686.Gupta P, Rosso P, Banchs RE. Encoding transliteration variation through dimensionality reduction: fire shared task on transliterated search. In: Fifth forum for information retrieval evaluation. 2013.HB Barathi Ganesh, M Anand Kumar, KP Soman. Distributional semantic representation for information retrieval. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. 2016.HB Barathi Ganesh, M Anand Kumar, KP Soman. Distributional semantic representation for text classification. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Järvelin K, Kekäläinen J. Cumulated gain-based evaluation of IR techniques. ACM Trans Inf Syst. 2002;20:422–46. https://doi.org/10.1145/582415.582418.Joshi H, Bhatt A, Patel H. Transliterated search using syllabification approach. In: Forum for information retrieval evaluation. 2013.King B, Abney S. Labeling the languages of words in mixed-language documents using weakly supervised methods. In: Proceedings of NAACL-HLT, 2013. pp. 1110–1119.Londhe N, Srihari RK. Exploiting named entity mentions towards code mixed IR: working notes for the UB system submission for MSIR@FIRE’16. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. 2016.Anand Kumar M, Soman KP. Amrita-CEN@MSIR-FIRE2016: Code-mixed question classification using BoWs and RNN embeddings. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Majumder G, Pakray P. NLP-NITMZ@MSIR 2016 system for code-mixed cross-script question classification. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Mandal S, Banerjee S, Naskar SK, Rosso P, Bandyopadhyay S. Adaptive voting in multiple classifier systems for word level language identification. In: FIRE workshops, 2015. pp. 47–50.Mukherjee A, Ravi A , Datta K. Mixed-script query labelling using supervised learning and ad hoc retrieval using sub word indexing. In: Proceedings of the Forum for Information Retrieval Evaluation, Bangalore, India, 2014.Pakray P, Bhaskar P. Transliterated search system for Indian languages. In: Pre-proceedings of the 5th FIRE-2013 workshop, forum for information retrieval evaluation (FIRE). 2013.Patel S, Desai V. Liga and syllabification approach for language identification and back transliteration: a shared task report by da-iict. In: Proceedings of the forum for information retrieval evaluation, ACM, 2014. pp. 43–47.Prabhakar DK, Pal S. Ism@fire-2013 shared task on transliterated search. In: Post-Proceedings of the 4th and 5th workshops of the forum for information retrieval evaluation, ACM, 2013. p. 17.Prabhakar DK, Pal S. Ism@ fire-2015: mixed script information retrieval. In: FIRE workshops. 2015. pp. 55–58.Prakash A, Saha SK. A relevance feedback based approach for mixed script transliterated text search: shared task report by bit Mesra. In: Proceedings of the Forum for Information Retrieval Evaluation, Bangalore, India, 2014.Raj A, Karfa S. A list-searching based approach for language identification in bilingual text: shared task report by asterisk. In: Working notes of the shared task on transliterated search at forum for information retrieval evaluation FIRE’14. 2014.Roy RS, Choudhury M, Majumder P, Agarwal K. Overview of the fire 2013 track on transliterated search. In: Post-proceedings of the 4th and 5th workshops of the forum for information retrieval evaluation, ACM, 2013. p. 4.Saini A. Code mixed cross script question classification. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. CEUR-WS.org. 2016.Salton G, McGill MJ. Introduction to modern information retrieval. New York: McGraw-Hill, Inc.; 1986.Sequiera R, Choudhury M, Gupta P, Rosso P, Kumar S, Banerjee S, Naskar SK, Bandyopadhyay S, Chittaranjan G, Das A, et al. Overview of fire-2015 shared task on mixed script information retrieval. FIRE Workshops. 2015;1587:19–25.Singh S, M Anand Kumar, KP Soman. CEN@Amrita: information retrieval on code mixed Hindi–English tweets using vector space models. In: Working notes of FIRE 2016—forum for information retrieval evaluation, Kolkata, India, December 7–10, 2016, CEUR workshop proceedings. 2016.Sinha N, Srinivasa G. Hindi–English language identification, named entity recognition and back transliteration: shared task system description. In: Working notes os shared task on transliterated search at forum for information retrieval evaluation FIRE’14. 2014.Voorhees EM, Tice DM. The TREC-8 question answering track evaluation. In: TREC-8, 1999. pp. 83–105.Vyas Y, Gella S, Sharma J, Bali K, Choudhury M. Pos tagging of English–Hindi code-mixed social media content. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 2014. pp. 974–979
A hybrid approach for transliterated word-level language identification: CRF with post processing heuristics
No full text© {Owner/Author | ACM} {Year}. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in FIRE '14 Proceedings of the Forum for Information Retrieval Evaluation, http://dx.doi.org/10.1145/2824864.2824876[EN] In this paper, we describe a hybrid approach for word-level language (WLL) identification of Bangla words written in Roman script and mixed with English words as part of our participation in the shared task on transliterated search at Forum for Information Retrieval Evaluation (FIRE) in 2014. A CRF based machine learning model and post-processing heuristics are employed for the WLL identification task. In addition to language identification, two transliteration systems were built to transliterate detected Bangla words written in Roman script into native Bangla script. The system demonstrated an overall token level language identification accuracy of 0.905. The token level Bangla and English language identification F-scores are 0.899, 0.920 respectively. The two transliteration systems achieved accuracies of 0.062 and 0.037. The word-level language identification system presented in this paper resulted in the best scores across almost all metrics among all the participating systems for the Bangla-English language pair.We acknowledge the support of the Department of Electronics and Information Technology (DeitY), Government of India, through the project “CLIA System Phase II”. The research work of the last author was carried out in the framework of WIQ-EI IRSES (Grant No. 269180) within the FP 7 Marie Curie, DIANA-APPLICATIONS (TIN2012-38603-C02-01) projects and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.Banerjee, S.; Kuila, A.; Roy, A.; Naskar, SK.; Rosso, P.; Bandyopadhyay, S. (2014). A hybrid approach for transliterated word-level language identification: CRF with post processing heuristics. En FIRE '14 Proceedings of the Forum for Information Retrieval Evaluation. ACM. 170-173. https://doi.org/10.1145/2824864.2824876S170173Y. Al-Onaizan and K. Knight. Named entity translation: Extended abstract. In HLT, pages 122--124. Singapore, 2002.P. J. Antony, V. P. Ajith, and K. P. Suman. Feature extraction based english to kannada transliteration. In In hird International conference on Semantic E-business and Enterprise Computing. SEEC 2010, 2010.P. J. Antony, V. P. Ajith, and K. P. Suman. Kernel method for english to kannada transliteration. In International conference on-Recent trends in Information, Telecommunication and computing. ITC2010, 2010.M. Arbabi, S. M. Fischthal, V. C. Cheng, and E. Bart. Algorithms for arabic name transliteration. In IBM Journal of Research and Development, page 183. TeX Users Group, 1994.S. Banerjee, S. Naskar, and S. Bandyopadhyay. Bengali named entity recognition using margin infused relaxed algorithm. In TSD, pages 125--132. Springer International Publishing, 2014.U. Barman, J. Wagner, G. Chrupala, and J. Foster. Identification of languages and encodings in a multilingual document. page 127. EMNLP, 2014.K. R. Beesley. Language identifier: A computer program for automatic natural-language identification of on-line text. pages 47--54. ATA, 1988.P. F. Brown, S. A. D. Pietra, V. J. D. Pietra, and R. L. Mercer. Mercer: The mathematics of statistical machine translation: parameter estimation. pages 263--311. Computational Linguistics, 1993.M. Carpuat. Mixed-language and code-switching in the canadian hansard. page 107. EMNLP, 2014.G. Chittaranjan, Y. Vyas, K. Bali, and M. Choudhury. Word-level language identification using crf: Code-switching shared task report of msr india system. pages 73--79. EMNLP, 2014.A. Das, A. Ekbal, T. Mandal, and S. Bandyopadhyay. English to hindi machine transliteration system at news. pages 80--83. Proceeding of the Named Entities Workshop ACL-IJCNLP, Singapore, 2009.A. Ekbal, S. Naskar, and S. Bandyopadhyay. A modified joint source channel model for transliteration. pages 191--198. COLING-ACL Australia, 2006.I. Goto, N. Kato, N. Uratani, and T. Ehara. Transliteration considering context information based on the maximum entropy method. pages 125--132. MT-Summit IX, New Orleans, USA, 2003.R. Haque, S. Dandapat, A. K. Srivastava, S. K. Naskar, and A. Way. English to hindi transliteration using context-informed pb-smt:the dcu system for news 2009. NEWS 2009, 2009.S. Y. Jung, S. Hong, and E. Paek. An english to korean transliteration model of extended markov window.S. Y. Jung, S. L. Hong, and E. Paek. An english to korean transliteration model of extended markov window. pages 383--389. COLING, 2000.B. J. Kang and K. S. Choi. Automatic transliteration and back-transliteration by decision tree learning. LERC, May 2000.B. King and S. Abney. Labeling the languages of words in mixed-language documents using weakly supervised methods. pages 1110--1119. NAACL-HLT, 2013.R. Kneser and H. Ney. Improved backing-off for m-gram language modeling. In ICASSP, pages 181--184. Detroit, MI, 1995.R. Kneser and H. Ney. SRILM-an extensible language modeling toolkit. In Intl. Conf. on Spoken Language Processing, pages 901--904, 2002.K. Knight and J. Graehl. Machine transliteration. in computational linguistics. pages 599--612, 1998.P. Koehn, H. Hoang, A. Birch, C. Callison-Burch, M. Federico, N. Bertoldi, B. Cowan, W. Shen, C. Moran, R. Zens, C. Dyer, O. Bojar, A. Constantin, and E. Herbst. Moses: open source toolkit for statistical machine translation. In ACL, pages 177--180, 2007.P. Koehn, F. J. Och, and D. Marcu. Statistical phrase-based translation. In HLT-NAACL, 2003.A. Kumaran and T. Kellner. A generic framework for machine transliteration. In 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 721--722. ACM, 2007.H. Li, Z. Min, and J. Su. A joint source-channel model for machine transliteration. In ACL, page 159, 2004.C. Lignos and M. Marcus. Toward web-scale analysis of codeswitching. In Annual Meeting of the Linguistic Society of America, 2013.J. H. Oh and K. S. Choi. An english-korean transliteration model using pronunciation and contextual rules. In 19th international conference on Computational linguistics. ACL, 2002.T. Rama and K. Gali. Modeling machine transliteration as a phrase based statistical machine translation problem. In Language Technologies Research Centre. IIIT, Hyderabad, India, 2009.A. K. Singh and J. Gorla. Identification of languages and encodings in a multilingual document. In ACL-SIGWAC's Web As Corpus3, page 95. Presses univ. de Louvain, 2007.V. Sowmya, M. Choudhury, K. Bali, T. Dasgupta, and A. Basu. Resource creation for training and testing of transliteration systems for indian languages. In LREC, pages 2902--2907, 2010.V. Sowmya and V. Varma. Transliteration based text input methods for telugu. In ICCPOL-2009, 2009.B. G. Stalls and J. Graehl. Translating names and technical terms in arabic text. In Workshop on Computational Approaches to Semitic Languages, pages 34--41. ACL, 1998.S. Sumaja, R. Loganathan, and K. P. Suman. English to malayalam transliteration using sequence labeling approach. International Journal of Recent Trends in Engineering, 1(2), 2009.M. S. Vijaya, V. P. Ajith, G. Shivapratap, and K. P. Soman. English to tamil transliteration using weka. International Journal of Recent Trends in Engineering, 2009
Classifier combination approach for question classification for Bengali question answering system
No full text[EN] Question classification (QC) is a prime constituent of an automated question answering system. The work presented here demonstrates that a combination of multiple models achieves better classification performance than those obtained with existing individual models for the QC task in Bengali. We have exploited state-of-the-art multiple model combination techniques, i.e., ensemble, stacking and voting, to increase QC accuracy. Lexical, syntactic and semantic features of Bengali questions are used for four well-known classifiers, namely Naive Bayes, kernel Naive Bayes, Rule Induction and Decision Tree, which serve as our base learners. Single-layer question-class taxonomy with 8 coarse-grained classes is extended to two-layer taxonomy by adding 69 fine-grained classes. We carried out the experiments both on single-layer and two-layer taxonomies. Experimental results confirmed that classifier combination approaches outperform single-classifier classification approaches by 4.02% for coarse-grained question classes. Overall, the stacking approach produces the best results for fine-grained classification and achieves 87.79% of accuracy. The approach presented here could be used in other Indo-Aryan or Indic languages to develop a question answering system.Somnath Banerjee and Sudip Kumar Naskar are supported by Digital India Corporation (formerly Media Lab Asia), MeitY, Government of India, under the Visvesvaraya Ph.D. Scheme for Electronics and IT. The work of Paolo Rosso was partially funded by the Spanish MICINN under the research project PGC2018-096212-B-C31.Banerjee, S.; Kumar Naskar, S.; Rosso, P.; Bndyopadhyay, S. (2019). Classifier combination approach for question classification for Bengali question answering system. Sadhana. 44(12):1-14. https://doi.org/10.1007/s12046-019-1224-8S1144412Jurafsky D and Martin J H 2014 Speech and language processing. Pearson, LondonMartin J H and Jurafsky D 2000 Speech and language processing, international edition 710Voorhees E M 2002 Overview of the TREC 2001 question answering track. NIST Special Publication, pp. 42–51Hovy E, Gerber L, Hermjakob U, Lin C Y and Ravichandran D 2001 Toward semantics-based answer pinpointing. In: Proceedings of Human Language Technology Research, ACL, pp. 1–7Ittycheriah A, Franz M, Zhu W J, Ratnaparkhi A and Mammone R J 2000 IBM’s statistical question answering system. In: Proceedings of TRECMoldovan D, Paşca M, Harabagiu S and Surdeanu M 2003 Performance issues and error analysis in an open-domain question answering system. ACM Trans. Inf. Syst. 21(2): 133–154Banerjee S and Bandyopadhyay S 2012 Bengali question classification: towards developing QA system. In: Proceedings of the 3rd Workshop on South and Sotheast Asian Language Processing (SANLP), COLING, pp. 25–40Loni B 2011 A survey of state-of-the-art methods on question classification. Technical Report, Delft University of TechnologyHull D A 1999 Xerox TREC-8 question answering track report. In: Proceedings of TRECPrager J, Radev D, Brown E, Coden A and Samn V 1999 The use of predictive annotation for question answering in TREC8. Inf. Retr. 1(3): 4Moschitti A, Quarteroni S, Basili R and Manandhar S 2007 Exploiting syntactic and shallow semantic kernels for question answer classification. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, p. 776Zhang D and Lee W S 2003 Question classification using support vector machines. In: Proceedings of Research and Development in Informaion Retrieval, ACM, pp. 26–32Huang Z, Thint M and Qin Z 2008 Question classification using head words and their hypernyms. In: Proceedings of Empirical Methods in Natural Language Processing, ACL, pp. 927–936Silva J, Coheur L, Mendes A C and Wichert A 2011 From symbolic to sub-symbolic information in question classification. Artif. Intell. Rev. 35(2): 137–154Li X and Roth D 2006 Learning question classifiers: the role of semantic information. Nat. Lang. Eng. 12(03): 229–249McCallum A, Freitag D and Pereira F C N 2000 Maximum entropy markov models for information extraction and segmentation. In: Proceedings of the International Conference on Machine Learning (ICML), vol. 17, pp. 591–598Cortes C and Vapnik V 1995 Support-vector networks. Mach. Learn. 20(3): 273–297Breiman L 1996 Bagging predictors. Mach. Learn. 24(2): 123–140Clemen R T 1989 Combining forecasts: a review and annotated bibliography. Int. J. Forecast. 5(4): 559–583Perrone M P 1993 Improving regression estimation: averaging methods for variance reduction with extensions to general convex measure optimization. Ph.D. Thesis, Brown UniversityWolpert D H 1992 Stacked generalization. Neural Netw. 5(2): 241–259Hansen L K and Salamon P 1990 Neural network ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 12: 993–1001Krogh A, Vedelsby J et al 1995 Neural network ensembles, cross validation, and active learning. Adv. Neural Inf. Process. Syst. 7: 231–238Hashem S 1997 Optimal linear combinations of neural networks. Neural Netw. 10(4): 599–614Opitz D W and Shavlik J W 1996 Actively searching for an effective neural network ensemble. Connect. Sci. 8(3–4): 337–354Opitz D W and Shavlik J W 1996 Generating accurate and diverse members of a neural-network ensemble. In: Advances in neural information processing systems, pp. 535–541Xin L, Huang X J and Wu L 2006 Question classification by ensemble learning. Int. J. Comput. Sci. Netw. Secur. 6(3): 147Schapire R E 1990 The strength of weak learnability. Mach. Learn. 5(2): 197–227Brill E 1995 Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging. Comput. Linguist. 21(4): 543–565Jia K, Chen K, Fan X and Zhang Y 2007 Chinese question classification based on ensemble learning. In: Proceedings of ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, SNPD 2007. IEEE, vol. 3, pp. 342–347Su L, Liao H, Yu Z and Zhao Q 2009 Ensemble learning for question classification. In: Proceedings of Intelligent Computing and Intelligent Systems, ICIS. IEEE, pp. 501–505Ferrucci D, Brown E, Chu-Carroll J, Fan J et al 2010 Building Watson: an overview of the DeepQA project. AI Mag. 31(3): 59–79Pérez-Coutiño M A, Montes-y-Gómez M, López-López A and Villaseñor-Pineda L 2005 Experiments for tuning the values of lexical features in question answering for Spanish. In: CLEF Working NotesNeumann G and Sacaleanu B 2003 A cross-language question/answering system for German and English. In: Proceedings of the Workshop of the Cross-Language Evaluation Forum for European Languages, pp. 559–571Blunsom P, Kocik K and Curran J R 2006 Question classification with log-linear models. In: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, pp. 615–616Rosso P, Benajiba Y and Lyhyaoui A 2006 In: Proceedings of the 4th Conference on Scientific Research Outlook and Technology Development in the Arab World, pp. 11–14Abouenour L, Bouzoubaa K and Rosso P 2012 IDRAAQ: new Arabic question answering system based on query expansion and passage retrieval. In: Proceedings of CELCTSakai T, Saito Y, Ichimura Y, Koyama M, Kokubu T and Manabe T 2004 ASKMi: a Japanese question answering system based on semantic role analysis. In: Proceedings of Coupling Approaches, Coupling Media and Coupling Languages for Information Retrieval, pp. 215–231Isozaki H, Sudoh K and Tsukada H 2005 NTT’s Japanese–English cross-language question answering system. In: Proceedings of NTCIRYongkui Z, Zheqian Z, Lijun B and Xinqing C 2003 Internet-based Chinese question-answering system. Comput. Eng. 15: 34Sun A, Jiang M, He Y, Chen L and Yuan B 2008 Chinese question answering based on syntax analysis and answer classification. Acta Electron. Sin. 36(5): 833–839Sahu S, Vasnik N and Roy D 2012 Prashnottar: a Hindi question answering system. Int. J. Comput. Sci. Inf. Technol. 4(2): 149Nanda G, Dua M and Singla K 2016 A Hindi question answering system using machine learning approach. In: Proceedings of Computational Techniques in Information and Communication Technologies (ICCTICT). IEEE, pp. 311–314Sekine S and Grishman R 2003 Hindi–English cross-lingual question-answering system. ACM Trans. Asian Lang. Inf. Process. 2(3): 181–192Shukla P, Mukherjee A and Raina A 2004 Towards a language independent encoding of documents. In: Proceedings of NLUCS 2004, p. 116Ray S K, Ahmad A and Shaalan K 2018 A review of the state of the art in Hindi question answering systems. In: Proceedings of Intelligent Natural Language Processing: Trends and Applications, pp. 265–292Kumar P, Kashyap S, Mittal A and Gupta S 2003 A query answering system for e-learning Hindi documents. South Asian Lang. Rev. 13(1–2): 69–81Reddy R, Reddy N and Bandyopadhyay S 2006 Dialogue based question answering system in Telugu. In: Proceedings of the Workshop on Multilingual Question Answering, pp. 53–60Dhanjal G S, Sharma S and Sarao P K 2016 Gravity based Punjabi question answering system. Int. J. Comput. Appl. 147(3): 30–35Bindu M S and Mary I S 2012 Design and development of a named entity based question answering system for Malayalam language. Ph.D. Thesis, Cochin University of Science and TechnologyLee C W et al 2005 ASQA: academia sinica question answering system for NTCIR-5 CLQA. In: Proceedings of the NTCIR-5 Workshop, pp. 202–208Banerjee S and Bandyopadhyay S 2013 Ensemble approach for fine-grained question classification in Bengali. In: Proceedings of the 27th Pacific–Asia Conference on Language, Information, and Computation (PACLIC-27), pp. 75–84Loni B, Van Tulder G, Wiggers P, Tax D M J and Loog M 2011 Question classification by weighted combination of lexical, syntactic and semantic features. In: Proceedings of the International Conference on Text, Speech, and Dialogue, pp. 243–250Huang Z, Thint M and Celikyilmaz A 2009 Investigation of question classifier in question answering. In: Proceedings of Empirical Methods in Natural Language Processing. ACL, vol. 2, pp. 543–550Blunsom P, Kocik K and Curran J R 2006 Question classification with log-linear models. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, pp. 615–616Diwakar S, Goyal P and Gupta R 2010 Transliteration among indian languages using WX notation. In: Proceedings of the Conference on Natural Language Processing, EPFL-CONF-168805. Saarland University Press, pp. 147–150Banerjee S, Naskar S K and Bandyopadhyay S Bengali named entity recognition using margin infused relaxed algorithm. In: Proceedings of the International Conference on Text, Speech, and Dialogue, pp. 125–132Li X and Roth D Learning question classifiers. In: Proceedings of the 19th International Conference on Computational Linguistics, ACL, vol. 1, pp. 1–7Cohen J 1960 A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20(1): 37–46Schapire R E 1990 The strength of weak learnability. Mach. Learn. 5(2): 197–22
Sistema de búsqueda de respuestas para el Bengalí
No full textSolo unos pocos trabajos de investigación se han llevado a cabo sobre sistemas de búsqueda de respuestas (BR) en idiomas de la India. No hay un sistema de BR para bengalí.
El objetivo principal de este TFM es el desarrollo de un sistema de BR para Bengali. Además, se debe proponer una taxonomía para poder clasificar las preguntas en bengalí. También será necesario desarrollar un conjunto de datos de preguntas y etiquetarlo en consecuencia.Only a few research works have been carried out on question answering (QA) systems in Indian languages. There are no QA system for Bengali. The main aim of this TFM is the development of a QA system for Bengali.Moreover, a question taxonomy needs to be proposed in order to classify questions in Bengali. A dataset of questions will need to be developed as well and tagged accordingly.Banerjee, S. (2018). Sistema de búsqueda de respuestas para el Bengalí. Universitat Politècnica de València. https://riunet.upv.es/handle/10251/111183TFG
An assessment of quality of life of transgender adults in an urban area of Burdwan district, West Bengal
No full textBackground: Transgender people are stigmatised in our society and are being discriminated in every aspect of life. Many of them experience abuses in various forms since childhood. Accordingly these might have adverse consequences on their life and modify their quality of life (QOL). This aspect needs to be explored. In this context the present study was conducted to assess the QOL among adult transgender people and to find its association with their socio-demographic characteristics in Burdwan municipal area of Burdwan district.Methods: A cross-sectional study was conducted during July-December 2016 among 79 adult transgender people residing in the study area. Sample size was based on 50% having satisfactory QOL with 95% CI, 10% relative error, and 10% non-response rate with finite population correction (total target reference population 96). Subjects were selected by simple random sampling and recruited for interview by time space sampling. Socio-demographic characteristics were assessed by a predesigned schedule and QOL was assessed by using a validated Bengali version of WHO-QOL BREF questionnaires.Results: 56.9% people were found to be have good QOL score as a whole. Maximum and minimum percentages of good QOL score was found in environmental domain (84.7%) and social relationship domain (45.8%). A significant positive correlation was found between education and monthly income with QOL score while negative correlation between age and QOL score. Marital status, current living status and occupation were found to have a statistically significant association with QOL score.Conclusions: The study measured QOL as well as identified some important socio-demographic variables which affected QOL among transgender people. These findings can help the government to plan conceptually to improve QOL in this special transgender group of population by some legislation, social awareness and facilities dedicated towards them.</jats:p
Diluted magnetic semiconductors of Zn-doped CeO2 nanoparticles synthesized by a chemical precursor method
No full textGraphitic carbon stabilized silver nanoparticles synthesized by a simple chemical precursor method
No full text
- …
