Filters








1,757 Hits in 3.3 sec

Probabilistic models for answer-ranking in multilingual question-answering

Jeongwoo Ko, Luo Si, Eric Nyberg, Teruko Mitamura
2010 ACM Transactions on Information Systems  
This article presents two probabilistic models for answering ranking in the multilingual questionanswering (QA) task, which finds exact answers to a natural language question written in different languages  ...  Although some probabilistic methods have been utilized in traditional monolingual answer-ranking, limited prior research has been conducted for answer-ranking in multilingual question-answering with formal  ...  ACKNOWLEDGMENTS We would like to thank NTCIR for providing the Japanese and Chinese corpora and data set. We would also like to thank Jamie Callan for his valuable discussion and suggestions.  ... 
doi:10.1145/1777432.1777439 fatcat:2aftfesfrfhs5c5synxz5rvkqm

Learning to Translate for Multilingual Question Answering [article]

Ferhan Ture, Elizabeth Boschee
2016 arXiv   pre-print
In multilingual question answering, either the question needs to be translated into the document language, or vice versa.  ...  We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights.  ...  Acknowledgements Jacob Devlin has provided great help in the design and implementation of the context-based question translation approach.  ... 
arXiv:1609.08210v1 fatcat:7rnfctatzbbytppuuxc5aizbdm

Learning to Translate for Multilingual Question Answering

Ferhan Ture, Elizabeth Boschee
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
In multilingual question answering, either the question needs to be translated into the document language, or vice versa.  ...  We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights.  ...  Acknowledgements Jacob Devlin has provided great help in the design and implementation of the context-based question translation approach.  ... 
doi:10.18653/v1/d16-1055 dblp:conf/emnlp/TureB16 fatcat:eja3yohw4zaj3obhl2mgmfovsq

A Machine-Translation Method for Normalization of SMS [chapter]

Darnes Vilariño, David Pinto, Beatriz Beltrán, Saul León, Esteban Castillo, Mireya Tovar
2012 Lecture Notes in Computer Science  
For this purpose, we use a statistical bilingual dictionary calculated on the basis of the IBM-4 model for determining the best translation for a given SMS term.  ...  We have compared the presented approach with a traditional probabilistic method of information retrieval, observing that the normalization model proposed here highly improves the performance of the probabilistic  ...  A Probabilistic Model for SMS-Based FAQ Retrieval We have used a probabilistic model which considers both, the translation and the search process in a single step.  ... 
doi:10.1007/978-3-642-31149-9_30 fatcat:sm5dy7p3wzgqdozuvvl5oycj7u

UH-PRHLT at SemEval-2016 Task 3: Combining Lexical and Semantic-based Features for Community Question Answering [article]

Marc Franco-Salvador, Sudipta Kar, Thamar Solorio, Paolo Rosso
2018 arXiv   pre-print
In this work we describe the system built for the three English subtasks of the SemEval 2016 Task 3 by the Department of Computer Science of the University of Houston (UH) and the Pattern Recognition and  ...  Experimental results outperform the random and Google search engine baselines in the three English subtasks.  ...  We thank Joan Puigcerver (PRHLT) for his support and comments.  ... 
arXiv:1807.11584v1 fatcat:gujwabqoqba73ocyljexjsdpyy

UH-PRHLT at SemEval-2016 Task 3: Combining Lexical and Semantic-based Features for Community Question Answering

Marc Franco-Salvador, Sudipta Kar, Thamar Solorio, Paolo Rosso
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
In this work we describe the system built for the three English subtasks of the Se-mEval 2016 Task 3 by the Department of Computer Science of the University of Houston (UH) and the Pattern Recognition  ...  Experimental results outperform the random and Google search engine baselines in the three English subtasks.  ...  We thank Joan Puigcerver (PRHLT) for his support and comments.  ... 
doi:10.18653/v1/s16-1126 dblp:conf/semeval/Franco-Salvador16 fatcat:buyjlvpzejh6lkhwhk7y6nejlm

Comprehensive Retrospection of Literature Reported Works of Community Question Answering Systems

2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Community question answering CQA) systems are rapidly gaining attention in the society.  ...  Machine learning, probabilistic modeling, deep learning and hybrid approach of solving show profound significance in addressing various challenges encounter with QA systems.  ...  Development of multilingual QA Systems is quite a worth. Ko et al. [11] have earlier developed a probabilistic graphical model to assign ranking for a Question-Answering System.  ... 
doi:10.35940/ijitee.c8769.019320 fatcat:cxn37tzig5bklly3sarl3kilpq

Different Facets of Text Based Automated Question Answering System

vaishali Singh
2018 International Journal for Research in Applied Science and Engineering Technology  
allows users to find the answers to their questions in precise way.  ...  Therefore, this paper attempts to present the state-of-the-art in the field of text based automatic question answering systems and provide a qualitative analysis of different facets.  ...  The work has also proposed a probabilistic model that captures the selection preferences of users based on the questions they choose for answering.  ... 
doi:10.22214/ijraset.2018.1017 fatcat:z2l3qicgvjawpcahqyr3alk3wy

Knowledge Efficient Deep Learning for Natural Language Processing [article]

Hai Wang
2020 arXiv   pre-print
Fourth, we present an episodic memory network for language modelling, in which we encode the large external knowledge for the pre-trained GPT.  ...  Third, we investigate the knowledge transfer techniques in multilingual setting, where we proposed a method that can improve pre-trained multilingual BERT based on the bilingual dictionary.  ...  In KRDL, we focus on learning a discriminative model for predicting the latent labels, using a probabilistic model defined by probabilistic logic to inject weak supervision.  ... 
arXiv:2008.12878v1 fatcat:vhcxrhydyfcsnh3iu5t3g5goky

Towards Understanding Theoretical Developments in Natural Language Processing

Mehnaz khan, Dr. Mehraj-ud-Din Dar, Dr. S.M.K. Quadri
2012 International Journal of Computer Applications  
They use these details to develop the tools for making the computers understand and manipulate the natural languages to perform the desired tasks.  ...  In this paper we describe some of the theoretical developments that have influenced research in NLP.  ...  In information retrieval and NLP, question answering (QA) is the task of automatically answering a question posed in natural language.  ... 
doi:10.5120/4577-6749 fatcat:ywt5dem6qnc6bg2lbcqdxcryva

POLY: Mining Relational Paraphrases from Multilingual Sentences

Adam Grycner, Gerhard Weikum
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
The evaluation of POLY shows significant improvements in precision and recall over the prior works on PATTY and DEFIE. An extrinsic use case demonstrates the benefits of POLY for question answering.  ...  Starting with a very large collection of multilingual sentences parsed into triples of phrases, our method clusters relational phrases using probabilistic measures.  ...  RESOLVER (Yates and Etzioni, 2009 ) introduced a probabilistic relational model for predicting synonymy.  ... 
doi:10.18653/v1/d16-1236 dblp:conf/emnlp/GrycnerW16 fatcat:qojng4dpijeftkptfu5grumogq

ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System [article]

Chia-Chien Hung, Tommaso Green, Robert Litschko, Tornike Tsereteli, Sotaro Takeshita, Marco Bombieri, Goran Glavaš, Simone Paolo Ponzetto
2022 arXiv   pre-print
In this challenging scenario, given an input question the system has to gather evidence documents from a multilingual pool and generate from them an answer in the language of the question.  ...  For answer generation, we focused on language- and domain-specialization by means of continued language model (LM) pretraining of existing multilingual encoders.  ...  ., 2021) , a multilingual version of a pretrained transformer-based encoderdecoder model (Raffel et al., 2020) , and fine-tune it for multilingual answer generation.  ... 
arXiv:2205.14981v1 fatcat:72s2goyk2zhzvii7knfvicwkku

Language Independent Answer Prediction from the Web [chapter]

Alejandro Figueroa, Günter Neumann
2006 Lecture Notes in Computer Science  
We assess the rank of predicted answers by extracting answer candidates for three different kinds of questions.  ...  This matrix models the strength of the syntactic relations between words by means of the frequency of their relative positions in sentences extracted from web snippets.  ...  The methods extract answers as terms biased by the question using probabilistic models constructed from question-answer pairs.  ... 
doi:10.1007/11816508_43 fatcat:wnd3ctpcqrebnntwcipdrrfwyi

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [chapter]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2017 Lecture Notes in Computer Science  
We present the first multilingual QALD pipeline that induces a model from training data for mapping a natural language question into logical form as probabilistic inference.  ...  The task of answering natural language questions over RDF data has received wIde interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  Addressing the lexical gap in question answering over linked data, we present a new system we call AMUSE that relies on probabilistic inference to perform structured prediction in the search space of possible  ... 
doi:10.1007/978-3-319-68288-4_20 fatcat:y7bkqxj64zen7p656jkhmhrs5m

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data [article]

Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
2018 arXiv   pre-print
We present the first multilingual QALD pipeline that induces a model from training data for mapping a natural language question into logical form as probabilistic inference.  ...  The task of answering natural language questions over RDF data has received wide interest in recent years, in particular in the context of the series of QALD benchmarks.  ...  Addressing the lexical gap in question answering over linked data, we present a new system we call AMUSE that relies on probabilistic inference to perform structured prediction in the search space of possible  ... 
arXiv:1802.09296v1 fatcat:e4oc3eadpnbkfifq4wu2kptcgq
« Previous Showing results 1 — 15 out of 1,757 results