5,338 Hits in 4.0 sec

BFQA: A Bengali Factoid Question Answering System [chapter]

Somnath Banerjee, Sudip Kumar Naskar, Sivaji Bandyopadhyay
2014 Lecture Notes in Computer Science  
This paper describes the first attempt on building a factoid question answering system for Bengali language. The challenges in developing a question answering system for Bengali have been discussed.  ...  Question Answering (QA) research for factoid questions has recently achieved great success.  ...  Conclusion This paper presents the first attempt to build a factoid QA system for Bengali.  ... 
doi:10.1007/978-3-319-10816-2_27 fatcat:jgf65dehifan7jh5homlbgdlja

The First Cross-Script Code-Mixed Question Answering Corpus

Somnath Banerjee, Sudip Kumar Naskar, Paolo Rosso, Sivaji Bandyopadhyay
2016 European Conference on Information Retrieval  
This paper emphasizes the use of such ever growing user generated content to serve as information collection source for the QA task on a low-resource language for the first time.  ...  For the ease of use multilingual users often pose questions in non-native script.  ...  The work of the third author was in the framework of the SomEMBED MINECO TIN2015-71147-C2-1-P research project.  ... 
dblp:conf/ecir/BanerjeeNRB16 fatcat:4v2vo7tuhfdwlgjotqarcxf6he

A Survey of Existing Question Answering Techniques for Indian Languages

Poonam Gupta, Vishal Gupta
2014 Journal of Emerging Technologies in Web Intelligence  
With advancement in technology, the process of question answering is the main field of research of text mining.  ...  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.  ...  Extraction of answers component is applied for scoring & validating the candidate answers for a particular question [10] . Question answering is novel field of research.  ... 
doi:10.4304/jetwi.6.2.165-168 fatcat:iw4gbcxycrfx5doy2a2gnqp4du

Deep learning based question answering system in Bengali

Tasmiah Tahsin Mayeesha, Abdullah Md Sarwar, Rashedur M. Rahman
2020 Journal of Information and Telecommunication  
Recent advances in the field of natural language processing has improved state-of-the-art performances on many tasks including question answering for languages like English.  ...  Unlike English, there is no benchmark large scale QA dataset collected for Bengali, no pretrained language model that can be modified for Bengali question answering and no human baseline score for QA has  ...  His current research interests are in data science, cloud load characterization, optimization of cloud resource placements, deep learning, etc.  ... 
doi:10.1080/24751839.2020.1833136 fatcat:ltwrsufie5hrrezjtv2tu56fjy

Towards Semi-Automatic Generation of Proposition Banks for Low-Resource Languages

Alan Akbik, vishwajeet kumar, Yunyao Li
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
In this paper, we present an experimental study where we apply this approach to three languages that lack such resources: Tamil, Bengali and Malayalam.  ...  Based on these results, we explore the possibility of using annotation projection as a starting point for inexpensive data curation involving both experts and non-experts.  ...  To encourage discussion within the research community, we make our generated Proposition Banks for Bengali, Malayalam and Tamil (see Table 3 for an overview) publicly available 4 .  ... 
doi:10.18653/v1/d16-1102 dblp:conf/emnlp/AkbikkL16 fatcat:n4et7otfxfhkhjzj6xlfzggzq4

Detecting the Presence of Named Entities in Bengali: Corpus and Experiments

Farzana Rashid, Fahmida Hamid
2021 Proceedings of the ... International Florida Artificial Intelligence Research Society Conference  
Named entities play vital roles in other related fields like question-answering, relationship extraction, and machine translation.  ...  We do not find a comparable amount of work for several South-Asian languages like Bengali/Bangla.  ...  Researchers are working hard to build and improve resources and tools for other low-resource languages.  ... 
doi:10.32473/flairs.v34i1.128445 fatcat:wo7r6u6xjfandcvkn6xf4stnui

A Review on Hindi Question Answering System

Amreen Kaur, Nishi and Beant Kaur
2022 International journal of modern trends in science and technology  
With advancement in technology, the process of question answering is the main field of research of text mining. In India, the natural language of people is mainly Hindi.  ...  There are various approaches that can be used to generate the questions from a given text. This paper presents the review to various question generation techniques.  ...  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.  ... 
doi:10.46501/ijmtst051189 fatcat:swnyahvsanealpxpzywsbkxyfi

Bilingual poetry: expanding the cognitive and cultural dimensions of children's learning

Charmian Kenner, Salman Al-Azami, Eve Gregory, Mahera Ruby
2008 Literacy  
considered a resource for the language and literacy development of bilingual children, particularly if they can work with texts in both mother tongue and English.  ...  Presenting data from an action research project in East London primary schools, we show how children investigated metaphor and cultural content in a Bengali lullaby, clarifying concepts through dialogue  ...  Acknowledgments This research was funded by the ESRC (R000221528).  ... 
doi:10.1111/j.1741-4369.2008.00486.x fatcat:rdznn4leazbbvgvhge4o7onjni

Transliteration as a bridge to learning for bilingual children

Salman Al-Azami, Charmian Kenner, Mahera Ruby, Eve Gregory
2010 International Journal of Bilingual Education and Bilingualism  
Acknowledgements The project Developing Bilingual Learning Strategies in Mainstream and Community Contexts was funded by the Economic and Social Research Council (Award R000221528).  ...  We would like to thank all the children, teachers and families who participated in the study.  ...  Research has not focused on the area considered in this paper, of transliteration as a resource for learning.  ... 
doi:10.1080/13670050903406335 fatcat:tlogca6otjbi3biegwhllntyve

A Novel Approach for Automatic Bengali Question Answering System using Semantic Similarity Analysis [article]

Arijit Das, Jaydeep Mandal, Zargham Danial, Alok Ranjan Pal, Diganta Saha
2019 arXiv   pre-print
This Bengali repository is a product of Technology Development for Indian Languages (TDIL) project sponsored by Govt. of India and provided by the Language Research Unit of Indian Statistical Institute  ...  In the first part of the algorithm, a set of statistical parameters like frequency, index, part-of-speech (POS), etc. is matched between a question and the probable answers.  ...  Detailed Explanation of Score and Result for a Sample Question First, for the question-"কিাথায় চৈতনযপ্রবাফ ু স্পষ্ট?"  ... 
arXiv:1910.10758v1 fatcat:mk2bml3tivd2lm7kxzxrlm4n3q

Bangladeshi Expatriate Students in Saudi Arabia and Their Languages

Pulak Barua
2019 International Journal of English Linguistics  
The paper attempts to throw light on the languages used by Bangladeshi expatriate students in Saudi Arabia as well as their feelings and thoughts towards their mother tongue.  ...  To meet this end, 175 students of Bangladesh International School in Jeddah (both Bengali and English medium) were asked to fill up a questionnaire and later some of them were interviewed randomly to have  ...  In this study, other than demographic questions, the respondents had to answer a few questions in details, and other questions included simple yes/no answers.  ... 
doi:10.5539/ijel.v9n6p271 fatcat:7kjyu5vmy5afjdsmz3devmejni

Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi [article]

Saurabh Gaikwad, Tharindu Ranasinghe, Marcos Zampieri, Christopher M. Homan
2021 arXiv   pre-print
MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in low-resource Indo-Aryan languages.  ...  in Bengali, English, and Hindi.  ...  Acknowledgment We would like to thank the dataset annotators who helped us with the annotation of MOLD. We further thank the anonymous RANLP reviewers for the insightful feedback provided.  ... 
arXiv:2109.03552v1 fatcat:bliymnqtgfbgtfa2xwkgxiygzy

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  ...  In this paper, we extend GenQA beyond English and present the first Cross-Lingual answer sentence generation system (CrossGenQA).  ...  Preliminary experiment on MS-Marco The first research question is about the feasibility of the task: can we generate a correct answer in a target language with candidates different from this language?  ... 
arXiv:2110.07150v2 fatcat:bk4xr54m2vbvbbqqbdr6cizfdm

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.  ...  However, current benchmarks in QA research do not account for the errors that speech recognition models might introduce, nor do they consider the language variations (dialects) of the users.  ...  First, the withingroup unfairness score, which can be interpreted as answering the question "how fair/consistent is the ASR model for the speakers of this dialect?".  ... 
arXiv:2109.12072v1 fatcat:pyy66fqphjb3fnw2lsk52eeovq

Amrita-CEN@MSIR-FIRE2016: Code-Mixed Question Classification using BoWs and RNN Embeddings

M. Anand Kumar, Soman K. P
2016 Forum for Information Retrieval Evaluation  
The experimental result shows that the proposed method is appropriate for the question classification task.  ...  We build two systems that classify questions mostly at the sentence level. We used a recurrent neural network for extracting features from the questions and Logistic regression for classification.  ...  [19] explains the use of growing user generated content to serve as information collection source for the question answering task on a low-resource language for the first time and explained their cross-script  ... 
dblp:conf/fire/MP16 fatcat:cj6yhogpdndcpiqqcc6tcbtzaq
« Previous Showing results 1 — 15 out of 5,338 results