Filters








4,180 Hits in 3.6 sec

Towards Multilingual Neural Question Answering [chapter]

Ekaterina Loginova, Stalin Varanasi, Günter Neumann
2018 Communications in Computer and Information Science  
We hope that our findings will ignite interest in neural approaches to multilingual question answering.  ...  Cross-lingual and multilingual question answering is a critical part of a successful and accessible natural language interface. However, many current solutions are unsatisfactory.  ...  A hybrid system can be considered when a neural network generates question-answer pairs, and a human annotator further refines them.  ... 
doi:10.1007/978-3-030-00063-9_26 fatcat:qdfrwmibrbgpzjxdxezi2cgomi

Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation [article]

Humair Raj Khan, Deepak Gupta, Asif Ekbal
2021 arXiv   pre-print
Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task.  ...  Training such models for multilingual setups demand high computing resources and multilingual language-vision dataset which hinders their application in practice.  ...  Dataset and Methods for Multilingual Image Question Answering. In Advances in Neural Information Processing Systems, pages 2296-2304. Souvick Ghosh, Satanu Ghosh, and Dipankar Das. 2017.  ... 
arXiv:2109.04653v1 fatcat:6oac4nogpbbctpoavh64j6iqhy

A Multilingual Modeling Method for Span-Extraction Reading Comprehension [article]

Gaochen Wu, Bin Xu, Dejie Chang, Bangchang Liu
2021 arXiv   pre-print
XLRC by simultaneously modeling the existing extractive reading comprehension training data in a multilingual environment using self-adaptive attention and multilingual attention.  ...  Furthermore, we propose multilingual attention (MLA) to learn the rich knowledge from various language families.  ...  Their goals are to enable research progress toward building high-quality question answering systems in roughly the world top 100 languages and to encourage research on models that behave well across the  ... 
arXiv:2105.14880v1 fatcat:57m24zap4ffvhe4qv4qngnxrcu

Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

Erkut Erdem, Menekse Kuyu, Semih Yagcioglu, Anette Frank, Letitia Parcalabescu, Barbara Plank, Andrii Babii, Oleksii Turuta, Aykut Erdem, Iacer Calixto, Elena Lloret, Elena-Simona Apostol (+6 others)
2022 The Journal of Artificial Intelligence Research  
answering and generation, and dialogue generation.  ...  report also focuses on the seminal applications of these NNLG models such as machine translation, description generation, automatic speech recognition, abstractive summarization, text simplification, question  ...  Acknowledgments This work has been partially supported by the European Commission ICT COST Action "Multi-task, Multilingual, Multi-modal Language Generation" (CA18231).  ... 
doi:10.1613/jair.1.12918 fatcat:xfnul3j5azchfe6pvgvwy3z6em

MLSUM: The Multilingual Summarization Corpus [article]

Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
2020 arXiv   pre-print
We present MLSUM, the first large-scale MultiLingual SUMmarization dataset.  ...  Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization  ...  This methodology could be thus applied on ML-SUM as a first step toward a large-scale multilingual Question Answering corpus.  ... 
arXiv:2004.14900v1 fatcat:vwiennfr4zbstprtrvc3rxf2rm

Multilingual Medical Question Answering and Information Retrieval for Rural Health Intelligence Access [article]

Vishal Vinod, Susmit Agrawal, Vipul Gaurav, Pallavi R, Savita Choudhary
2021 arXiv   pre-print
Our contribution includes defining the NLP pipeline required for named-entity-recognition, language-agnostic sentence embedding, natural language translation, information retrieval, question answering,  ...  In this paper, we describe an approach leveraging the phenomenal progress in Machine Learning and NLP (Natural Language Processing) techniques to design a model that is low-resource, multilingual, and  ...  (for vernacular languages), and is accurate in its associated tasks such as NER (Named Entity Recognition), RE (Relation Extraction), QA (Question Answering), NMT (Neural Machine Translation) and generative  ... 
arXiv:2106.01251v1 fatcat:hmbqc26khvexrffcechbqlitcq

Improving Low-resource Reading Comprehension via Cross-lingual Transposition Rethinking [article]

Gaochen Wu, Bin Xu, Yuxin Qin, Fei Kong, Bangchang Liu, Hongwen Zhao, Dejie Chang
2021 arXiv   pre-print
To address this issue, we propose a Cross-Lingual Transposition ReThinking (XLTT) model by modelling existing high-quality extractive reading comprehension datasets in a multilingual environment.  ...  To be specific, we present multilingual adaptive attention (MAA) to combine intra-attention and inter-attention to learn more general generalizable semantic and lexical knowledge from each pair of language  ...  The goals of these proposed multilingual datasets and benchmarks are to encourage and speedup research on developing high-quality multilingual question answering systems to generalize across a large number  ... 
arXiv:2107.05002v2 fatcat:on63mhbnrnebrjbvs4rn6rlkx4

Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language [article]

H. Jafarian, A. H. Taghavi, A. Javaheri, R. Rawassizadeh
2020 arXiv   pre-print
Aspect-based sentiment analysis (ABSA) is a more detailed task in sentiment analysis, by identifying opinion polarity toward a certain aspect in a text.  ...  In question-answer with multiple output type (QA-M), the auxiliary sentence is a real question and the answer in this case in either positive, negative or neutral.  ...  They proposed a hybrid method of structural correspondence learning (SCL) and convolutional neural network (CNN).  ... 
arXiv:2012.07510v1 fatcat:r6s5bpnigjdajlk4ojsixradoe

A Unified Framework for Multilingual and Code-Mixed Visual Question Answering

Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya
2020 International Joint Conference on Natural Language Processing  
In this paper, we propose an effective deep learning framework for multilingual and codemixed visual question answering.  ...  We propose a robust technique capable of handling the multilingual and code-mixed question to provide the answer against the visual information (image).  ...  We propose a unified neural model for multilingual and code-mixed VQA, which can predict answer of a multilingual or code-mixed question. 3.  ... 
dblp:conf/ijcnlp/GuptaLEB20 fatcat:5kboywx5uncdrpzrwzcgljkb5m

Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian [article]

Momchil Hardalov, Ivan Koychev, Preslav Nakov
2019 arXiv   pre-print
While the quiz authors gave no relevant context, we incorporate knowledge from Wikipedia, retrieving documents matching the combination of question + each answer option.  ...  We propose a new dataset containing 2,221 questions from matriculation exams for twelfth grade in various subjects -history, biology, geography and philosophy-, and 412 additional questions from online  ...  Zero-shot transfer and multilingual models had been a hot topic in (neural) machine translation (MT) in the past several years.  ... 
arXiv:1908.01519v2 fatcat:gvaxbyxdg5hp3oin4a4c5c3eqy

The State of the Art on Knowledge Graph Construction from Text: Named Entity Recognition and Relation Extraction Perspectives

Jennifer D'Souza, Nandana Mihindukulasooriya
2022 Zenodo  
This presentation covers the state-of-the-art benchmark dataset resources as well as the best neural models for the respective task perspectives.  ...  Combines neural and knowledge-based method for silver data creation for multilingual NER.  ...  , 2007), text summarization (Aone et al., 1998), text understanding (Zhang et al., 2019; Cheng and Erk, 2019) and entity linking (Tedeschi et al., 2021), among others • question answering (Mollá et al.  ... 
doi:10.5281/zenodo.6521883 fatcat:swra4e7rf5dljhjojl7nc2cq4i

Cross-language Information Retrieval [article]

Petra Galuščáková, Douglas W. Oard, Suraj Nair
2022 arXiv   pre-print
This chapter reviews the state of the art for CLIR and outlines some open research questions.  ...  Towards multilingual neural question answering. In A. Benczúr, B. Thalheim, T. Horváth, S. Chiusano, T. Cerquitelli, C. Sidló, and P. Z.  ...  question answering.  ... 
arXiv:2111.05988v2 fatcat:4f3qbtcswvdavhzhufehdlbyry

XOR QA: Cross-lingual Open-Retrieval Question Answering [article]

Akari Asai, Jungo Kasai, Jonathan H. Clark, Kenton Lee, Eunsol Choi, Hannaneh Hajishirzi
2021 arXiv   pre-print
Multilingual question answering tasks typically assume answers exist in the same language as the question.  ...  Experimental results suggest that XOR QA is a challenging task that will facilitate the development of novel techniques for multilingual question answering.  ...  In this paper, we introduce the task of crosslingual open-retrieval question answering (XOR QA) which aims at answering multilingual questions from non-English native speakers given multilingual resources  ... 
arXiv:2010.11856v3 fatcat:7mujquejk5fxxmhggc22plic7u

The Effects of Multilingualism on Reading Speed

Gloria Kim, Jeanette Azzaretto, Katie Moltz
2020 Journal of student research  
Among broader implications, a change in education systems to be geared toward advancing reading speed could be highly beneficial.  ...  Both monolinguals and multilinguals participated in order to determine the effects multilingualism has on reading speed.  ...  I also made sure that all my questions were required which means that the participant must answer every question before pressing "submit."  ... 
doi:10.47611/jsrhs.v9i1.1110 fatcat:tgqjahbvhzekhgebjcj5bk6e4u

X-Stance: A Multilingual Multi-Target Dataset for Stance Detection [article]

Jannis Vamvas, Rico Sennrich
2020 arXiv   pre-print
To make learning across targets possible, we prepend to each instance a natural question that represents the target (e.g. "Do you support X?").  ...  Baseline results from multilingual BERT show that zero-shot cross-lingual and cross-target transfer of stance detection is moderately successful with this approach.  ...  concerning a political issue; (B) a natural language commentary on a specific stance towards the question.  ... 
arXiv:2003.08385v2 fatcat:xkxdkeueqnckzgezb4xj7kfbyu
« Previous Showing results 1 — 15 out of 4,180 results