Filters








82,174 Hits in 9.0 sec

Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming [article]

Arindam Mitra, Peter Clark, Oyvind Tafjord, Chitta Baral
2019 arXiv   pre-print
However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text.  ...  The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment.  ...  The research is partially funded by NSF 1816039 and AI2 Key Scientific Challenges Program.  ... 
arXiv:1905.00198v1 fatcat:cdftqh7l5jggndxph5drccg5pm

Declarative Question Answering over Knowledge Bases Containing Natural Language Text with Answer Set Programming

Arindam Mitra, Peter Clark, Oyvind Tafjord, Chitta Baral
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text.  ...  The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment.  ...  The research is partially funded by NSF 1816039 and AI2 Key Scientific Challenges Program.  ... 
doi:10.1609/aaai.v33i01.33013003 fatcat:mclpytwogbbtbfesn2n7bx7zdm

An ASP-based Approach to Answering Natural Language Questions for Texts [article]

Dhruva Pendharkar, Kinjal Basu, Farhad Shakerin, Gopal Gupta
2021 arXiv   pre-print
An approach based on answer set programming (ASP) is proposed in this paper for representing knowledge generated from natural language texts.  ...  Knowledge in a text is modeled using a Neo Davidsonian-like formalism, which is then represented as an answer set program.  ...  The Knowledge Generation System is mainly responsible for extracting knowledge from a natural language text and representing it as an answer set program.  ... 
arXiv:2112.11241v1 fatcat:wl7upalae5cjvibd4epxvoyw5u

Natural Language QA Approaches using Reasoning with External Knowledge [article]

Chitta Baral, Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra
2020 arXiv   pre-print
Question answering (QA) in natural language (NL) has been an important aspect of AI from its early days. Winograd's "councilmen" example in his 1972 paper and McCarthy's Mr.  ...  use in various NLQA models have brought the issue of NLQA using "reasoning" with external knowledge to the forefront.  ...  The semantics of ASP is based on the stable model (answer set) semantics of logic programming.  ... 
arXiv:2003.03446v1 fatcat:5ssmvcdzajc5flasg3s5hsfxsu

Task-Oriented API Usage Examples Prompting Powered By Programming Task Knowledge Graph [article]

Jiamou Sun, Zhenchang Xing, Xin Peng, Xiwei Xu, Liming Zhu
2020 arXiv   pre-print
The recently proposed activity-centric search over knowledge graph supports direct search of programming actions, but it has limitations in action coverage, natural language based task search, and coarse-grained  ...  We integrate our knowledge graph and task search method in the IDE, and develop an observe-push based tool to prompt developers with task-oriented API usage examples.  ...  They develop knowledge graph based task search by natural language queries.  ... 
arXiv:2006.07058v1 fatcat:fwjfupasp5ay5oj6w3c4pkciam

Information retrieval on the semantic web

Urvi Shah, Tim Finin, Anupam Joshi
2002 Proceedings of the eleventh international conference on Information and knowledge management - CIKM '02  
We describe an approach for information retrieval over documents that consist of both free text and semantically enriched markup.  ...  In particular, we present the design and implementation prototype of a framework in which both documents and queries can be marked up with statements in the DAML+OIL semantic web language.  ...  Web documents may contain free text along with some markup.  ... 
doi:10.1145/584865.584868 fatcat:thgtu5uhk5eb5acvqc34so4nbq

Information retrieval on the semantic web

Urvi Shah, Tim Finin, Anupam Joshi
2002 Proceedings of the eleventh international conference on Information and knowledge management - CIKM '02  
We describe an approach for information retrieval over documents that consist of both free text and semantically enriched markup.  ...  In particular, we present the design and implementation prototype of a framework in which both documents and queries can be marked up with statements in the DAML+OIL semantic web language.  ...  Web documents may contain free text along with some markup.  ... 
doi:10.1145/584792.584868 dblp:conf/cikm/ShahFJ02 fatcat:ubguewm4yrhdvoshudhewgrjzm

Work Out the Semantic Web Search: The Cooperative Way

Dora Melo, Irene Pimenta Rodrigues, Vitor Beires Nogueira
2012 Advances in Artificial Intelligence  
We propose a Cooperative Question Answering System that takes as input natural language queries and is able to return a cooperative answer based on semantic web resources, more specifically DBpedia represented  ...  in OWL/RDF as knowledge base and WordNet to build similar questions.  ...  A study on the usability of Natural Language Interfaces and natural language query languages, over ontology-based knowledge, for the end-users is presented in [7] .  ... 
doi:10.1155/2012/867831 fatcat:ujptv336p5fixas2d5aqhlxo24

Question answering over knowledge graphs

Weiguo Zheng, Jeffrey Xu Yu, Lei Zou, Hong Cheng
2018 Proceedings of the VLDB Endowment  
The gap between unstructured natural language and structured data makes it challenging to build a system that supports using natural language to query large knowledge graphs.  ...  Many existing methods construct a structured query for the input question based on a syntactic parser.  ...  QALD is a benchmark delivered for the evaluation campaign answering over knowledge bases. It provides a set of a natural language questions, the corresponding SPARQL queries and answers.  ... 
doi:10.14778/3236187.3236192 fatcat:f4bs2xnqj5dyjjgp55nrkio2zu

Solving Probability Problems in Natural Language

Anton Dries, Angelika Kimmig, Jesse Davis, Vaishak Belle, Luc de Raedt
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
the first step, a question formulated in natural language is analysed and transformed into a high-level model specified in a declarative language.  ...  In this paper, we develop a two-step end-to-end fully automated approach for solving such questions that is able to automatically provide answers to exercises about probability formulated in natural language.In  ...  we want to answer based on the probability distribution over the content of containers defined above.  ... 
doi:10.24963/ijcai.2017/556 dblp:conf/ijcai/DriesKDBR17 fatcat:q26wodhlf5b5hghwihvvwrcoma

Integrating top-down and bottom-up strategies in a text processing system

Lisa F. Rau, Paul S. Jacobs
1988 Proceedings of the second conference on Applied natural language processing -  
The SCISOR. system is a computer program designed to scan naturally occurring texts in constrained domains, extract information, and answer questions about that information.  ...  from texts.  ...  The system described here competently answers questions about constrained texts, uses the same language analyzer for text processing and question answering, and has been applied to other domains as well  ... 
doi:10.3115/974235.974259 dblp:conf/anlp/RauJ88 fatcat:n424iliujbcfjpgb5mnkgly6gq

Programming Bots by Synthesizing Natural Language Expressions into API Invocations [article]

Shayan Zamanirad, Boualem Benatallah, Moshe Chai Barukh, Fabio Casati, Carlos Rodriguez
2017 arXiv   pre-print
required synthesis from natural language user expressions into API calls.  ...  To overcome this, we introduce BotBase, a bot programming platform that dynamically synthesizes natural language user expressions into API invocations.  ...  ACKNOWLEDGMENT We Acknowledge Data to Decisions CRC for funding scholarship on Query Answering and Predictive Techniques for Analyst Tasks in End-User Big Data Analytic.  ... 
arXiv:1711.05410v1 fatcat:qoot5pnzt5d67n6sz54ccekz54

EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering [article]

Momchil Hardalov, Todor Mihaylov, Dimitrina Zlatkova, Yoan Dinkov, Ivan Koychev, Preslav Nakov
2020 arXiv   pre-print
We hope that EXAMS will enable researchers to explore challenging reasoning and knowledge transfer methods and pre-trained models for school question answering in various languages which was not possible  ...  We collected more than 24,000 high-quality high school exam questions in 16 languages, covering 8 language families and 24 school subjects from Natural Sciences and Social Sciences, among others.  ...  Acknowledgments We thank the anonymous reviewers for their helpful questions and comments. We thank the AI2 Aristo Team for providing the data splits used for pre-training on SciEN datasets.  ... 
arXiv:2011.03080v1 fatcat:5lorr5p5encmpanb66jp5ctkki

Lynx D3.9 Information Retrieval and Recommender Services

Maria Khvalchik, Artem Revenko, Christian Sageder, Víctor Rodríguez-Doncel, Pablo Calleja-Ibáñez
2020 Zenodo  
Question Answering takes in a natural language question and returns the most promising answer. Finally, the Semant [...]  ...  This requires the gathering of relevant regulations, which enables end-users to find answers to their regulatory related needs with ease.  ...  QUESTION ANSWERING General Description of Method In this section, we present a question answering system that accepts a question asked in a natural language in English and in Spanish, the latter being  ... 
doi:10.5281/zenodo.3870456 fatcat:s4yfxdewlje5rfu6ewecwdeuti

Graph-based retrieval of information in hypertext systems

Yuri Quintana, Mohamed Kamel, Andrew Lo
1992 Proceedings of the 10th annual international conference on Systems documentation - SIGDOC '92  
GKR diil'ers by using a single semantic interpreter to process both declarative sentences (stored in knowledge base) and natural language queries posed on the knowledge base.  ...  in the C programming language. One answer is the description of the C library function fgets.  ... 
doi:10.1145/147001.147022 dblp:conf/sigdoc/QuintanaKL92 fatcat:pkmcwmrs65brpfjzc3nr7sq66a
« Previous Showing results 1 — 15 out of 82,174 results