Filters








271,093 Hits in 3.9 sec

Entailment-based Question Answering for Structured Data

Bogdan Sacaleanu, Constantin Orasan, Christian Spurk, Shiyan Ou, Óscar Ferrández, Milen Kouylekov, Matteo Negri
2008 International Conference on Computational Linguistics  
This paper describes a Question Answering system which retrieves answers from structured data regarding cinemas and movies.  ...  Based on specially designed domain ontology and using Textual Entailment as a means for semantic inference, the system can be used in both monolingual and cross-language settings with slight adjustments  ...  Description of system Our question answering system implements the concept of entailment-based question answering described in the previous section.  ... 
dblp:conf/coling/SacaleanuOSOFKN08 fatcat:sslazxnoyfdzbcoov5oianad7e

SSL-QA: Analysis of Semi-Supervised Learning for QuestionAnswering

Parth Patel, Jignesh Prajapati
2017 IOSR Journal of Computer Engineering  
In this paper we analyse different intensive researches in semi-supervised learning for question-answering.  ...  These patterns differ from each other in the type of questions and answers and the size of the training data, from a few hundreds to millions of examples.  ...  New graph representation for SSL that can represent textual entailment relations while embedding different question structures.  ... 
doi:10.9790/0661-1903051415 fatcat:iv2qx3pejjf7fkt5rsewld7dky

Question Answering over Structured Data: an Entailment-Based Approach to Question Analysis

Matteo Negri, Milen Kouylekov
2009 Recent Advances in Natural Language Processing  
This paper addresses question analysis in the framework of Question Answering over structured data.  ...  The underlying assumption is that a question expresses a certain relation if a pattern for that relation is entailed by the question.  ...  answer from a given data source.  ... 
dblp:conf/ranlp/NegriK09 fatcat:e7k7pnda5nfi7o7in7bbggnbgi

The QALL-ME Framework: A specifiable-domain multilingual Question Answering architecture ⁎

Óscar Ferrández, Christian Spurk, Milen Kouylekov, Iustin Dornescu, Sergio Ferrández, Matteo Negri, Rubén Izquierdo, David Tomás, Constantin Orasan, Guenter Neumann, Bernardo Magnini, Jose Luis Vicedo
2011 Journal of Web Semantics  
This paper presents the QALL-ME Framework, a reusable architecture for building multi-and crosslingual Question Answering (QA) systems working on structured data modelled by an ontology.  ...  ; (iii) the use of textual entailment engines as the core of the question interpretation; and (iv) an architecture based on Service Oriented Architecture (SOA), which is realized using interchangeable  ...  This paper presents the QALL-ME Framework, a reusable architecture skeleton for building multilingual QA systems that answer questions with the help of structured answer data sources from freely specifiable  ... 
doi:10.1016/j.websem.2011.01.002 fatcat:fjn3vq5rhnbf7doj6nwdelhyea

Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations

Vinayshekhar Bannihatti Kumar, Ashwin Srinivasan, Aditi Chaudhary, James Route, Teruko Mitamura, Eric Nyberg
2019 Proceedings of the 18th BioNLP Workshop and Shared Task  
Our system is based on the prior work Liu et al. (2019) which uses a multi-task objective function for textual entailment.  ...  This paper presents the submissions by Team Dr.Quad to the ACL-BioNLP 2019 shared task on Textual Inference and Question Entailment in the Medical Domain.  ...  Acknowledgement We are thankful to the anonymous reviewers for their valuable suggestions.  ... 
doi:10.18653/v1/w19-5048 dblp:conf/bionlp/KumarSCRMN19 fatcat:2ppzwnhdxvavfptcxhcnna3pbm

Information Synthesis for Answer Validation [chapter]

Rui Wang, Günter Neumann
2009 Lecture Notes in Computer Science  
Our system casts the AVE task into a Recognizing Textual Entailment (RTE) problem and uses an existing RTE system to validate answers.  ...  In all, we have submitted two runs, one run for English and the other for German. They have achieved f-measures of 0.64 and 0.61 respectively.  ...  Tree skeletons are extracted based on the dependency structures derived by Minipar (Lin, 1998) for English and SMES (Neumann and Piskorski, 2002) for German.  ... 
doi:10.1007/978-3-642-04447-2_57 fatcat:tslisz7vl5enjim7vpumw5w5jq

An Ontology-based Question Answering Method with the use of Query Template

Lakshmi Palaniappan, N. Sambasiva Rao
2010 International Journal of Computer Applications  
This paper presents a new method for ontology-based question answering (QA) with the use of Query template for Dining Ontology as the domain (Service of the restaurant is called dining).  ...  Hypothesis questions and query templates can be produced from domain ontology. Pre-generation of hypothesis questions on the basis of the domain ontology and textual entailment.  ...  In question answering the issue of representing question as a structured format for data retrieval is not a trivial task. automatic question pattern generation for ontology based question answering was  ... 
doi:10.5120/1413-1909 fatcat:tcdnbw46irh63iv4fd2alev3rm

Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations [article]

Vinayshekhar Bannihatti Kumar, Ashwin Srinivasan, Aditi Chaudhary, James Route, Teruko Mitamura, Eric Nyberg
2019 arXiv   pre-print
Our system is based on the prior work Liu et al. (2019) which uses a multi-task objective function for textual entailment.  ...  This paper presents the submissions by Team Dr.Quad to the ACL-BioNLP 2019 shared task on Textual Inference and Question Entailment in the Medical Domain.  ...  Acknowledgement We are thankful to the anonymous reviewers for their valuable suggestions.  ... 
arXiv:1907.10136v1 fatcat:5m4diusafjb25pbjsw2krken2q

Experimenting a "General Purpose" Textual Entailment Learner in AVE [chapter]

Fabio Massimo Zanzotto, Alessandro Moschitti
2007 Lecture Notes in Computer Science  
In this paper we present the use of a "general purpose" textual entailment recognizer in the Answer Validation Exercise (AVE) task.  ...  Its main feature is the use of Support Vector Machines (SVMs) with kernel functions based on cross-pair similarity between entailment pairs.  ...  The Answer Validation Exercise (AVE) instead provides an opportunity to show that such recognizers are useful for Question Answering.  ... 
doi:10.1007/978-3-540-74999-8_61 fatcat:swyhrfm5ljd33buh5fs7yab5bm

Two Approaches for QA4MRE: Information Retrieval and Graph-based Knowledge Representation

Helena Gómez-Adorno, David Pinto, Darnes Vilariño Ayala
2013 Conference and Labs of the Evaluation Forum  
This approach validates the answers based on a textual entailment assessment, lexical and semantic similarity measures.  ...  In this paper we present our approaches for tackling the QA4MRE 2013 main task.  ...  Graph-based representation for one reference document Information Retrieval Information Retrieval Hypothesis + Retrieved Passage + IR score Answer Selection Final Answer Answer Validation Textual Entailment  ... 
dblp:conf/clef/Gomez-AdornoPA13 fatcat:frrl7uxpm5h7jjccocxr7bm7ie

Natural Language Processing Applications: A New Taxonomy using Textual Entailment

Manar Elshazly, Mohammed Haggag, Soha Ahmed Ehssan
2021 International Journal of Advanced Computer Science and Applications  
Also, it compares textual entailment application models according to the method used, the result for each model, and the pros and cons of each model.  ...  For this purpose, when combining a textual entailment with deep learning, they can hugely showed an improvement in performance accuracy and aid in new applications such as depression detection.  ...  The model new data, SCITAIL, is designed for the final task of answering high school science questions.  ... 
doi:10.14569/ijacsa.2021.0120580 fatcat:yp7wtq6n7bamjcsnpl2hathrwy

Visuo-Linguistic Question Answering (VLQA) Challenge [article]

Shailaja Keyur Sampat, Yezhou Yang, Chitta Baral
2020 arXiv   pre-print
We propose a novel task to derive joint inference about a given image-text modality and compile the Visuo-Linguistic Question Answering (VLQA) challenge corpus in a question answering setting.  ...  Each dataset item consists of an image and a reading passage, where questions are designed to combine both visual and textual information i.e., ignoring either modality would make the question unanswerable  ...  Acknowledgments We are thankful to the anonymous reviewers for the feedback. This work is partially supported by the National Science Foundation grant IIS-1816039.  ... 
arXiv:2005.00330v3 fatcat:ss4t4exf6ze5fjnmsvj3yfq6ny

Annotating Entailment Relations for Shortanswer Questions

Simon Ostermann, Andrea Horbach, Manfred Pinkal
2015 Proceedings of the 2nd Workshop on Natural Language Processing Techniques for Educational Applications  
We annotate entailment relations between learner and target answers in the Corpus of Reading Comprehension Exercises for German (CREG) with a finegrained label inventory and compare them in various ways  ...  This paper presents an annotation project that explores the relationship between textual entailment and short answer scoring (SAS).  ...  We also thank our annotators Fernando Ardente, Sophie Henning and Maximilian Wolf for their help with this study and alexis Palmer for valuable feedback for our annotation guidelines.  ... 
doi:10.18653/v1/w15-4408 dblp:conf/acl-tea/OstermannHP15 fatcat:bybiyw2aafdujdjk6zochs46h4

SciTaiL: A Textual Entailment Dataset from Science Question Answering

Tushar Khot, Ashish Sabharwal, Peter Clark
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem.  ...  Different from existing entailment datasets, we create hypotheses from science questions and the corresponding answer candidates, and premises from relevant web sentences retrieved from a large corpus.  ...  Acknowledgments The authors would like to thank Dongyeop Kang, Oyvind Tafjord, Luke Zettlemoyer for valuable discussions and help throughout the project.  ... 
doi:10.1609/aaai.v32i1.12022 fatcat:euqrudwzj5gedphidbnfgj444i

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction [article]

Rui Feng, Jie Yuan, Chao Zhang
2020 arXiv   pre-print
, we formulate event detection as a textual entailment prediction problem, and argument detection as a question answer-ing problem.  ...  Moreover, our model can be fine-tuned with a small amount of data to boost its performance.  ...  CONCLUSION We propose a reading comprehension framework for event extraction tasks. We design a textual entailment based method for event detection and question answering for argument detection.  ... 
arXiv:2010.11325v1 fatcat:4v564b3y5rhwjkekppt5gsyxxm
« Previous Showing results 1 — 15 out of 271,093 results