133 Hits in 4.2 sec

A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique [article]

Md. Hasibur Rahman, Chowdhury Rafeed Rahman, Ruhul Amin, Md. Habibur Rahman Sifat, Afra Anika
2020 arXiv   pre-print
Question classification (QC) is the primary step of the Question Answering (QA) system.  ...  Question Classification (QC) system classifies the questions in particular classes so that Question Answering (QA) System can provide correct answers for the questions.  ...  Different QA Systems have been developed in different languages such as Arabic QA system named 'AQAS' [21] , Arabic factoid question answering system [10] , Chinese QA system [30] , Hindi QA system  ... 
arXiv:1912.00127v3 fatcat:z5oxqkakybctnm7o2sz5acwwja

A Comprehensive Comparison of Machine Learning Based Methods Used in Bengali Question Classification [article]

Afra Anika, Md. Hasibur Rahman, Salekul Islam, Abu Shafin Mohammad Mahdee Jameel, Chowdhury Rafeed Rahman
2019 arXiv   pre-print
QA classification system maps questions asked by humans to an appropriate answer category. A sound question classification (QC) system model is the pre-requisite of a sound QA system.  ...  This work demonstrates phases of assembling a QA type classification model.  ...  This work will help the research community to choose a proper classification model for smart Bengali QA system development.  ... 
arXiv:1911.03059v2 fatcat:lrgmougc6rcjbixsugopvuufhi

Code mixed cross script factoid question classification - A deep learning approach

Somnath Banerjee, Sudip Naskar, Paolo Rosso, Sivaji Bandyopadhyay, David Pinto, Vivek Kumar Singh, Aline Villavicencio, Philipp Mayr-Schlegel, Efstathios Stamatatos
2018 Journal of Intelligent & Fuzzy Systems  
for less-computerized languages to build question answering systems.  ...  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  ...  [9] proposed to develop QA system based on informal CMCS data. Also, a dataset [9] was developed for Bengali-English CMCS QA research.  ... 
doi:10.3233/jifs-169481 fatcat:c4nvgunbqvefhjqtufzh6stpja

A Survey of Existing Question Answering Techniques for Indian Languages

Poonam Gupta, Vishal Gupta
2014 Journal of Emerging Technologies in Web Intelligence  
Hindi, Punjabi, Bengali, Kannada, Telugu and Marathi etc are main spoken languages in India.  ...  For these Indian languages, very less number of language resources is available and much of research is going on for developing basic language resources in these languages.  ...  Bengali Question Classification: Towards Developing QA System by Somnath Banerjee et al. in 2012. [4] The baseline system based on Naïve Bayes classifier (using only lexical features) = 80.65%  ... 
doi:10.4304/jetwi.6.2.165-168 fatcat:iw4gbcxycrfx5doy2a2gnqp4du

SD-QA: Spoken Dialectal Question Answering for the Real World [article]

Fahim Faisal, Sharlina Keshava, Md Mahfuz ibn Alam, Antonios Anastasopoulos
2021 arXiv   pre-print
Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces.  ...  To address this gap, we augment an existing QA dataset to construct a multi-dialect, spoken QA benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts  ...  Towards more equitable question answering systems: How much more data do you need?  ... 
arXiv:2109.12072v1 fatcat:pyy66fqphjb3fnw2lsk52eeovq

Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages [article]

Kushal Jain, Adwait Deshpande, Kumar Shridhar, Felix Laumann, Ayushman Dash
2020 arXiv   pre-print
Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks such as text classification, question-answering, and token classification.  ...  We achieve state-of-the-art performance on Hindi and Bengali languages for text classification task.  ...  CLASSIFICATION POS TAGGING QUESTION ANSWERING DATASET HINDI BENGALI TELUGU HINDI BENGALI TELUGU HINDI BENGALI TELUGU NAME BBC Indic-NLP Indic-NLP UD NLTK UD mergedQuAD TyDi-QA TyDi-QA  ... 
arXiv:2011.02323v1 fatcat:oxo6jkzntfexhmz4k2twd3jgxm

Document Classification with Deep Rectifier Neural Networks and Probabilistic Sampling [chapter]

Tamás Grósz, István Nagy T.
2014 Lecture Notes in Computer Science  
Teixeira A Topic Model Scoring Approach for Personalized QA Systems . . . . . . . . . . . . 84 Hamidreza Chinaei, Luc Lamontagne, François Laviolette, and Richard Khoury Feature Exploration for Authorship  ...  Factoid Question Answering System . . . . . . . . . . . . . . . . . . . 217 Somnath Banerjee, Sudip Kumar Naskar, and Sivaji Bandyopadhyay Dictionary-Based Problem Phrase Extraction from User Reviews  ... 
doi:10.1007/978-3-319-10816-2_14 fatcat:xwqnznkokzdormpkalibhdf3ea

Modeling Classifier for Code Mixed Cross Script Questions

Rupal Bhargava, Shubham Khandelwal, Akshit Bhatia, Yashvardhan Sharma
2016 Forum for Information Retrieval Evaluation  
towards QA.  ...  ., non-native script) data gives rise to a new problem and presents serious challenges to automatic Question Answering (QA) and for this question classification will be required which is an important step  ...  Furthermore, it has been observed that the performance of question classification has significant influence on the overall performance of a QA system.  ... 
dblp:conf/fire/BhargavaKBS16 fatcat:tm56fwro3jaybmas35d2i3iafe

Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering [article]

Fahim Faisal, Antonios Anastasopoulos
2021 arXiv   pre-print
Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually.  ...  We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.  ...  We also want to thank Jacob Eisenstein, Manaal Faruqui, and Jon Clark for helpful discussions on question answering and data collection.  ... 
arXiv:2109.12028v1 fatcat:hvox6jcsgrcdhmzf5thqvis7my

Cross-Lingual GenQA: Open-Domain Question Answering with Answer Sentence Generation [article]

Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti
2022 arXiv   pre-print
To foster further development on this topic, we introduce GenTyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian questions  ...  Recent approaches for question answering systems have achieved impressive performance on English by combining document-level retrieval with answer generation.  ...  development of multilingual GENQA systems.  ... 
arXiv:2110.07150v2 fatcat:bk4xr54m2vbvbbqqbdr6cizfdm

Named Entity Recognition on Code-Mixed Cross-Script Social Media Content

Somnath Banerjee, Sudip Kumar Naskar, Paolo Rosso, Sivaji Bandyopadhyay
2018 Journal of Computacion y Sistemas  
Our prime target is to extract NE for question answering.  ...  The classification models based on CRF and SVM performed well among the classifiers.  ...  Since the NER work reported here is specifically targeted towards development of QA system, we proposed NE taxonomies that are suitable for question classification and answering.  ... 
doi:10.13053/cys-21-4-2850 fatcat:kgqlbblju5gehhg56hpns3eure

Solving Sinhala Language Arithmetic Problems using Neural Networks [article]

W.M.T Chathurika, K.C.E De Silva, A.M. Raddella, E.M.R.S. Ekanayake, A. Nugaliyadde, Y. Mallawarachchi
2018 arXiv   pre-print
The system comprises of (a) keyword identification, (b) question identification, (c) mathematical operation identification and is combined using a neural network.  ...  Naive Bayes Classification is used in order to identify keywords and Conditional Random Field to identify the question and the operation which should be performed on the identified keywords to achieve  ...  In Question identification, the significance of the words in the problem is learned by the system. The relevant mathematical operation is identified by the verb categorization process. One-vs.  ... 
arXiv:1809.04557v1 fatcat:ntnoafmlczedpjv6hm6sdqbvde

Analysis and tracking of emotions in english and bengali texts

Dipankar Das
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
Development of lexical resources and corpora meets the preliminary urgencies.  ...  The present discussion highlights the aspects of an ongoing doctoral thesis grounded on the analysis and tracking of emotions from English and Bengali texts.  ...  Question Answering (QA) systems [3] and modern Information Retrieval (IR) [4] , [9] systems are also increasingly incorporating emotion analysis within their scope.  ... 
doi:10.1145/1963192.1963341 dblp:conf/www/Das11 fatcat:biyos66jtfdlfh4aee33nj7mfm

A Review of Question Answering Systems

Bolanle Ojokoh, Emmanuel Adebisi
2019 Journal of Web Engineering  
We subsequently made an informed judgment of the basis for each classification criterion through literature on QA systems.  ...  Question Answering (QA) targets answering questions defined in natural language.  ...  PiQAS: Pisa Question Answering System. TREC. Banerjee, S., and Bandyopadhyay, S. 2012. Bengali Question Classification: Towards Developing QA System.  ... 
doi:10.13052/jwe1540-9589.1785 fatcat:g4bbctufvjd6fkijclxd5rnth4

MultiLingMine 2016: Modeling, Learning and Mining for Cross/Multilinguality [chapter]

Dino Ienco, Mathieu Roche, Salvatore Romeo, Paolo Rosso, Andrea Tagarelli
2016 Lecture Notes in Computer Science  
We have evaluated the system by using a gold standard corpus including manually segmented texts and results are promising. Abstract.  ...  Although discourse parsers have been already developed for several languages, this tool does not exist for Catalan.  ...  This work was partially supported by the Grant of the Ministry of Education, Science and Technological Development of the Republic Serbia, as a part of the project TR33037.  ... 
doi:10.1007/978-3-319-30671-1_83 fatcat:znq74oljzfefrfhzdkpphzekz4
« Previous Showing results 1 — 15 out of 133 results