85 Hits in 7.7 sec

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  
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  ...  In this research work, we address the question classification task as part of the code-mixed cross-script question answering research problem.  ...  [9] addressed the code-mixed cross-script QA research problem-"Building a question answering system which takes cross-script code-mixed questions as information request, processes a cross-script codemixed  ... 
doi:10.3233/jifs-169481 fatcat:c4nvgunbqvefhjqtufzh6stpja

Towards Multilingual Neural Question Answering [chapter]

Ekaterina Loginova, Stalin Varanasi, Günter Neumann
2018 Communications in Computer and Information Science  
We believe that recent developments in deep learning approaches are likely to be efficient for question answering tasks spanning several languages.  ...  Cross-lingual and multilingual question answering is a critical part of a successful and accessible natural language interface. However, many current solutions are unsatisfactory.  ...  In the third section, a case study is presented for which we compare the performance of a deep learning model before and after translating a corpus of non-factoid questions and answers.  ... 
doi:10.1007/978-3-030-00063-9_26 fatcat:qdfrwmibrbgpzjxdxezi2cgomi

Modeling Classifier for Code Mixed Cross Script Questions

Rupal Bhargava, Shubham Khandelwal, Akshit Bhatia, Yashvardhan Sharma
2016 Forum for Information Retrieval Evaluation  
This paper proposes an approach to handle cross script question classification as it is an important task of question analysis which detects the category of the question.  ...  Focusing on this current multilingual scenario, code-mixed cross-script (i.e., non-native script) data gives rise to a new problem and presents serious challenges to automatic Question Answering (QA) and  ...  The Subtask 1 in the shared task on Mixed Script Information Retrieval in FIRE-2016 addresses the task of code mixed cross script question classification where 'Q' represents set of factoid questions written  ... 
dblp:conf/fire/BhargavaKBS16 fatcat:tm56fwro3jaybmas35d2i3iafe

MSIR@FIRE: A Comprehensive Report from 2013 to 2016

Somnath Banerjee, Monojit Choudhury, Kunal Chakma, Sudip Kumar Naskar, Amitava Das, Sivaji Bandyopadhyay, Paolo Rosso
2020 SN Computer Science  
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  ...  Keywords Information retrieval • Indian languages • Social media • Transliterated search • Code-mixed QA This article is part of the topical collection "Forum for Information Retrieval Evaluation" guest  ...  Task: Code-Mixed Cross-Script Question Answering In 2015, the code-mixed cross-script question answering (CMCS-QA) was introduced as a pilot task at FIRE.  ... 
doi:10.1007/s42979-019-0058-0 fatcat:z5ojljqkkfatph46hzjj6epnny

Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering

Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya
2018 Proceedings of the 22nd Conference on Computational Natural Language Learning  
In this paper, we propose a linguistically motivated technique for codemixed question generation (CMQG) and a neural network based architecture for code-mixed question answering (CMQA).  ...  For evaluation, we manually create the code-mixed questions for Hindi-English language pair.  ...  In addition to this, we manually create a code-mixed question dataset, and subsequently a code-mixed question classification dataset.  ... 
doi:10.18653/v1/k18-1012 dblp:conf/conll/GuptaLEB18 fatcat:7w7hk6ly3zhmnguojjler7wemy

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  
In this paper, we propose a novel set of language independent features that capture language use from a document at a deep level, using features that are intrinsic to the document.  ...  In this paper we present a Multilingual Ontology-Driven framework for Text Classification (MOoD-TC).  ...  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

If You Can't Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking

Dasha Bogdanova, Jennifer Foster, Daria Dzendzik, Qun Liu
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
We show that a neural approach to the task of non-factoid answer reranking can benefit from the inclusion of tried-and-tested handcrafted features.  ...  Additionally, we present a new dataset of Ask Ubuntu questions where the hybrid approach also achieves good results.  ...  I heard it is Python (Gold) Poked around in Launchpad: ubuntu-desktop to and browsed the source for a few mins. It appears to be a mix of Python and shell scripts.  ... 
doi:10.18653/v1/e17-1012 dblp:conf/eacl/LiuFBD17 fatcat:3u6mznvh7ffjbjfv37qt6gdxg4

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  
This paper also introduces a Bengali-English (Bn-En) code-mixed cross-script dataset for NE research and proposes domain specific taxonomies for NE.  ...  Focusing on the current multilingual scenario in social media, this paper reports automatic extraction of named entities (NE) from code-mixed cross-script social media data.  ...  In the context of code-mixed cross-script (CMCS), we have initiated to develop a CMCS question answering (QA) system for Bengali-English code-mixed data.  ... 
doi:10.13053/cys-21-4-2850 fatcat:kgqlbblju5gehhg56hpns3eure

Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base

Vishal Gupta, Manoj Chinnakotla, Manish Shrivastava
2018 Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching  
They can also answer Code-mix (CM) questions: questions which contain both languages. This ability is attributed to the unique learning ability of humans.  ...  Humans can learn multiple languages. If they know a fact in one language, they can answer a question in another language they understand.  ...  Raghavi et al. (2015) demonstrate question type classification for CM questions and Raghavi et al. (2017) also demonstrate a CM factoid QA system that searches for the lexically translated CM question  ... 
doi:10.18653/v1/w18-3205 dblp:conf/acl-codeswitch/GuptaCS18 fatcat:cuoslyt4pbbkhpmebehn6fc7hy

Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods

Ovishake Sen, Mohtasim Fuad, Md. Nazrul Islam, Jakaria Rabbi, Mehedi Masud, Md. Kamrul Hasan, Md. Abdul Awal, Awal Ahmed Fime, Md. Tahmid Hasan Fuad, Delowar Sikder, Md. Akil Raihan Iftee
2022 IEEE Access  
There is an apparent scarcity of resources that contain a comprehensive review of the recent BNLP tools and methods.  ...  Therefore, in this paper, we present a thorough analysis of 75 BNLP research papers and categorize them into 11 categories,  ...  [35] proposed a statistical languageindependent approach for identifying the foreign words in the code-mixed language. They mainly implemented the model in Bangla-English code-mixed scenarios.  ... 
doi:10.1109/access.2022.3165563 fatcat:rmersduz6vbyjjczvobrebskmi

A Survey of Code-switched Speech and Language Processing [article]

Sunayana Sitaram, Khyathi Raghavi Chandu, Sai Krishna Rallabandi, Alan W Black
2020 arXiv   pre-print
This survey reviews computational approaches for code-switched Speech and Natural Language Processing.  ...  Code-switching, the alternation of languages within a conversation or utterance, is a common communicative phenomenon that occurs in multilingual communities across the world.  ...  One of the initial efforts in eliciting code-mixed data to perform question classification was undertaken by [89] .  ... 
arXiv:1904.00784v3 fatcat:r5tsg4kdnfbtnndae523c32pta

Bangla Natural Language Processing: A Comprehensive Review of Classical, Machine Learning, and Deep Learning Based Methods [article]

Ovishake Sen, Mohtasim Fuad, MD. Nazrul Islam, Jakaria Rabbi, MD. Kamrul Hasan, Mohammed Baz, Mehedi Masud, Md. Abdul Awal, Awal Ahmed Fime, Md. Tahmid Hasan Fuad, Delowar Sikder, MD. Akil Raihan Iftee
2021 arXiv   pre-print
We discuss Classical, Machine Learning and Deep Learning approaches with different datasets while addressing the limitations and current and future trends of the BNLP.  ...  There is an apparent scarcity of resources that contain a comprehensive study of the recent BNLP tools and methods.  ...  They mainly implemented the model in Bangla-English code-mixed scenarios. Moreover, for Bangla-English code-mixed language, the model gained a reasonable accuracy.  ... 
arXiv:2105.14875v2 fatcat:kvqmgxpthvh2fj7jza64n6kaiq

Knowledge Efficient Deep Learning for Natural Language Processing [article]

Hai Wang
2020 arXiv   pre-print
First, we propose a knowledge rich deep learning model (KRDL) as a unifying learning framework for incorporating prior knowledge into deep models.  ...  Deep learning has become the workhorse for a wide range of natural language processing applications. But much of the success of deep learning relies on annotated examples.  ...  Sequence Classification Tasks Finally, we evaluate the expanded model on sequence classification in a mixed-code setting, where results are less sensitive to unseen words. "突然听到 21 ,那强劲的鼓点,那一张张脸。"  ... 
arXiv:2008.12878v1 fatcat:vhcxrhydyfcsnh3iu5t3g5goky

In search of the Why

Suzan Verberne
2011 SIGIR Forum  
Following approaches to factoid QA, we created a classification of semantic an swer types for why-questions.  ...  Learning to Rank approaches Most approaches to learning to rank consider the problem as a case of supervised learning.  ...  A vacancy at the department of Language of Speech for a junior researcher in Natural Language Processing made her decide to go back to the University of Nijmegen in 2005.  ... 
doi:10.1145/1924475.1924501 fatcat:fjnlh6htjfg5bas5rjdxd5wx44

BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis [article]

Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
2019 arXiv   pre-print
To show the generality of the approach, the proposed post-training is also applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment  ...  to answer user questions.  ...  Acknowledgments Bing Liu's work was partially supported by the National Science Foundation (NSF IIS 1838770) and by a research gift from Huawei.  ... 
arXiv:1904.02232v2 fatcat:b62iccqtlbfb3g7znqasscktfq
« Previous Showing results 1 — 15 out of 85 results