Filters








30,453 Hits in 8.3 sec

Open Domain Real-Time Question Answering Based on Semantic and Syntactic Question Similarity

Vivek V. Datla, Sadid A. Hasan, Joey Liu, Yassine Benajiba, Kathy Lee, Ashequl Qadir, Aaditya Prakash, Oladimeji Farri
2016 Text Retrieval Conference  
The Live-QA task involves real user questions, extracted from the stream of most recent questions submitted to the Yahoo Answers (YA) site, which have not yet been answered by humans.  ...  Our strategy for answering the questions include question decomposition, question relatedness identification, and answer generation.  ...  In order to extract semantically and syntactically similar questions we filtered the candidate questions further based on similar keywords and word order.  ... 
dblp:conf/trec/DatlaHLBLQPF16 fatcat:tvypr2buuraf3mmisudgrybrvi

Comparative Analysis of Keyword and Semantically Enhanced Question Answering System on Law Domain

Shubhangi C. Tirpude
2020 Bioscience Biotechnology Research Communications  
The question answering system is based on syntactical & semantical analysis by creating the semantic graph and defining the semantic relationship between semantic entities.  ...  We have developed a Question Answering system that considers the semantic information of question inputted and answer retrieved focussing on retrieval of information which is context based.  ...  Aaditya prakash, oladimeji Farri[5] implements a real-time question answering system using the syntactic and semantic similarity on open domain.  ... 
doi:10.21786/bbrc/13.14/66 fatcat:dvidkuonq5cqxljv5zzgh3ou2i

A literature survey on question answering system in natural language processing

A Clementeena, Dr P. Sripriya
2018 International Journal of Engineering & Technology  
The con-straints will include the semantic and syntactic knowledge and framing that sort of question with possible correct answers.  ...  Thus this paper gives you a clear vision of how its being worked on question answering and thus it presents a machine learning approach.  ...  and answering can be an open ended and can be nearly any kind of domain or topics.  And so these domain questioning will have a large set of data base and thus the answers can be retrieved at any time  ... 
doi:10.14419/ijet.v7i2.33.14209 fatcat:eqv7oz2xanctdoesj5tauh24za

Speech-based Question Answering System " Ikkyu "

Stijn De Saeger, Jun Goto, Istvan Varga
2012 Journal of NICT  
Example: the original sentence from which Ikkyu extracted an unexpected but valuable answer regarding the cause of the Japanese deflation  ...  Ikkyu regards the question answering process as a relation extraction problem and solves it by a real-time adaptation of the semantic relation acquisition method proposed in [1] and [2] .  ...  Semantic similarity of words calculated based on their distributional profile is called context similarity.  ... 
doi:10.24812/nictjournal.59.3.4_083 fatcat:qbixobicb5g7bkqc5xc2hkxa24

SimQ: Real-Time Retrieval of Similar Consumer Health Questions

Jake Luo, Guo-Qiang Zhang, Susan Wentz, Licong Cui, Rong Xu
2015 Journal of Medical Internet Research  
Objective: In this study, we aim to develop efficient informatics methods that can retrieve similar Web-based consumer health questions using syntactic and semantic analysis.  ...  Finally, the similarity between sentences was calculated using both semantic and syntactic features. Results: We used 2000 randomly selected consumer questions to evaluate the system's performance.  ...  Often times, these users post similar questions that have been answered previously.  ... 
doi:10.2196/jmir.3388 pmid:25689608 pmcid:PMC4376128 fatcat:taodytcfrvejpfbnjypxukd7sy

A survey on question answering technology from an information retrieval perspective

Oleksandr Kolomiyets, Marie-Francine Moens
2011 Information Sciences  
On the one hand, natural language queries are reduced to keyword-based searches, on the other hand, knowledge bases are queried with structured or logical queries obtained from the natural language questions  ...  We discuss different levels of processing yielding bag-of-words-based and more complex representations integrating part-of-speech tags, classification of the expected answer type, semantic roles, discourse  ...  approaches promoted by the TREC, CLEF and NTCIR that focus on open domain QA.  ... 
doi:10.1016/j.ins.2011.07.047 fatcat:se6dcorj2jbidath35go5wi5yy

A Semantic Question Answering through Heterogeneous Data Source in the Domain of Smart Factory

Orçun Oruç
2020 International Journal on Natural Language Computing  
In this study, we propose a semantic question answering that connects with heterogeneous data sources from different areas and devices of a smart factory.  ...  In the end, we will perform qualitative and quantitative evaluation regarding the semantic question answering that exploits heterogeneous data sources, as well as findings and conclude the main points  ...  ACKNOWLEDGEMENTS This work is funded by the German Research (DFG) within the Research Training Group Role-Based Software Infrastructures for continuous-context-sensitive Systems (GRK 1907).  ... 
doi:10.5121/ijnlc.2020.9403 fatcat:gcknl4k7yfhbbp5fkepycdtbpq

Comparison of Question Answering Systems Based on Ontology and Semantic Web in Different Environment

S.
2012 Journal of Computer Science  
Approach: This paper surveys different types of question answering system based on ontology and semantic web model with different query format.  ...  Results: The semantic search methodology is implemented by using RDF graph in the application of data structure domain and the performance is also analyzed.  ...  Semantic Search Algorithm is based on Conceptual Graph form of user query and domain ontology.  ... 
doi:10.3844/jcssp.2012.1407.1413 fatcat:xdfchvwntrfjxemyw6z5nogwvm

Principle-to-Program: Neural Methods for Similar Question Retrieval in Online Communities [chapter]

Muthusamy Chelliah, Manish Shrivastava, Jaidam Ram Tej
2020 Lecture Notes in Computer Science  
and semantic equivalence.  ...  Similar question retrieval is a challenge due to lexical gap between query and candidates in archive and is very different from traditional IR methods for duplicate detection, paraphrase identification  ...  Units in a semantic parse can be leveraged to alleviate defining/labeling them in open domain.  ... 
doi:10.1007/978-3-030-45442-5_88 fatcat:rdzo4nrrzbhgvd54zkykt4zi4a

Shoo the Spectre of Ignorance with QA2SPR - An Open Domain Question Answering Architecture with Semantic Prioritisation of Roles

Simone Scannapieco, Claudio Tomazzoli
2017 International Workshop on Knowledge Discovery on the Web  
Open Domain Question Answering (ODQA) aims at automatically understanding and giving responses to general questions posed in natural language.  ...  This, in turn, relies on a proper (i) identification of question keywords to isolate candidate answer passages from documents, and (ii) ranking of the candidate answers to decide which passage contains  ...  answering [19] , semantic approaches for question classification [14] , and ODQA based on syntactic and semantic question similarity [6] , with special consideration of existing QA system implementations  ... 
dblp:conf/kdweb/ScannapiecoT17 fatcat:ejtpjcobinfbjaet2qakanhqoa

Natural Language Question Answering with Goal-directed Answer Set Programming

Kinjal Basu, Gopal Gupta
2021 International Conference on Logic Programming  
Keeping all of these in mind, we have developed various NLU application ranging from visual question answering to a conversational agent.  ...  Ideally, for any realistic (human like) NLU system, commonsense reasoning must be an integral part of it and goal directed answer-setprogramming (ASP) is indispensable to do commonsense reasoning.  ...  Our goal is also to develop an open-domain conversational AI chatbot based on automated commonsense reasoning that can "converse" with a human based on "truly understanding" that person's utterances.  ... 
dblp:conf/iclp/0002G21 fatcat:lrvytk3lyff6rekw7utm6vfy4i

Question Answering System over Linked Data: A Detailed Survey

G. M. Rasiqul Islam Rasiq, Abdullah Al Sefat, Tanjila Hossain, Md. Israt-E-Hasan Munna, Jubayeath Jahan Jisha, Mohammad Moinul Hoque
2020 ABC Research Alert  
We also discuss the evaluation campaigns of the existing models based on their precision, recall and F-1 scores on the QALD dataset.  ...  As the amount of information in the world is growing very quickly, in the case of the semantic web this increasing amount of information is becoming more difficult to find and manage the exact answers  ...  to the end enabled us to development an understanding of the subject and helped us a lot to finish our literature review based research work.  ... 
doi:10.18034/abcra.v8i1.449 fatcat:whgbzdj5vrfktfwci5akwamh2e

Mapping of Semantic Web Ontology in User Query System

Rupali R.Khune
2015 International Journal of Computer Applications  
develop a question answering system from developed framework of ontology's and improve performance by adding semantic relation interpreter which improves response time.  ...  The main purpose of the Semantic Web promises a kind Machine Intelligence, which can support a verity of user tasks like efficiency of search engine or Question Answering (QA).  ...  Semantic relation interpreter can be used to provide result in quick response time, which used compound nouns to analyse the semantic and syntactic similarity.  ... 
doi:10.5120/19604-1456 fatcat:3p2r65qbprgi3ibkv7es3ly46u

Using semantic templates for a natural language interface to the CINDI virtual library

Niculae Stratica, Leila Kosseim, Bipin C. Desai
2005 Data & Knowledge Engineering  
The input sentences are syntactically parsed using the Link Parser, and semantically parsed through the use of domain-specific templates.  ...  This knowledge base is then used at run time to semantically parse the input and create the corresponding SQL query.  ...  Acknowledgment This research was supported in part by a grant from NSERC Canada and IDEAS.  ... 
doi:10.1016/j.datak.2004.12.002 fatcat:64csjthe6nd43p4lxnylzo5sti

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

Minjoon Seo, Jinhyuk Lee, Tom Kwiatkowski, Ankur Parikh, Ali Farhadi, Hannaneh Hajishirzi
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query, which is computationally prohibitive  ...  In particular, our dense-sparse phrase encoding effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents.  ...  gifts from Allen Institute for AI, Google, and Amazon.  ... 
doi:10.18653/v1/p19-1436 dblp:conf/acl/SeoLKPFH19 fatcat:khayf34qmzhfjebghkopaurpmi
« Previous Showing results 1 — 15 out of 30,453 results