Multi-Field Structural Decomposition for Question Answering. Jurczyk, T. & Choi, J. D. Technical Report 1604.00938, ArXiv, 2015. ![Multi-Field Structural Decomposition for Question Answering [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an abso- lute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.
@techreport{jurczyk:15b,
abstract = {This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an abso- lute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.},
author = {Jurczyk, Tomasz and Choi, Jinho D.},
date-added = {2016-07-02 02:16:03 +0000},
date-modified = {2017-08-31 03:01:06 +0000},
institution = {ArXiv},
keywords = {emorynlp,selected},
number = {1604.00938},
title = {{Multi-Field Structural Decomposition for Question Answering}},
url = {http://arxiv.org/abs/1604.00938},
year = {2015},
Bdsk-Url-1 = {http://arxiv.org/pdf/1604.00938v1.pdf}}
Downloads: 0
{"_id":"6rjaAPfgvALDDc3Mo","bibbaseid":"jurczyk-choi-multifieldstructuraldecompositionforquestionanswering-2015","downloads":0,"creationDate":"2016-10-25T00:52:24.918Z","title":"Multi-Field Structural Decomposition for Question Answering","author_short":["Jurczyk, T.","Choi, J. D."],"year":2015,"bibtype":"techreport","biburl":"http://www.mathcs.emory.edu/~choi/cv/jinho_choi-20210601.bib","bibdata":{"bibtype":"techreport","type":"techreport","abstract":"This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an abso- lute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.","author":[{"propositions":[],"lastnames":["Jurczyk"],"firstnames":["Tomasz"],"suffixes":[]},{"propositions":[],"lastnames":["Choi"],"firstnames":["Jinho","D."],"suffixes":[]}],"date-added":"2016-07-02 02:16:03 +0000","date-modified":"2017-08-31 03:01:06 +0000","institution":"ArXiv","keywords":"emorynlp,selected","number":"1604.00938","title":"Multi-Field Structural Decomposition for Question Answering","url":"http://arxiv.org/abs/1604.00938","year":"2015","bdsk-url-1":"http://arxiv.org/pdf/1604.00938v1.pdf","bibtex":"@techreport{jurczyk:15b,\n\tabstract = {This paper presents a precursory yet novel approach to the question answering task using structural decomposition. Our system first generates linguistic structures such as syntactic and semantic trees from text, decomposes them into multiple fields, then indexes the terms in each field. For each question, it decomposes the question into multiple fields, measures the relevance score of each field to the indexed ones, then ranks all documents by their relevance scores and weights associated with the fields, where the weights are learned through statistical modeling. Our final model gives an abso- lute improvement of over 40% to the baseline approach using simple search for detecting documents containing answers.},\n\tauthor = {Jurczyk, Tomasz and Choi, Jinho D.},\n\tdate-added = {2016-07-02 02:16:03 +0000},\n\tdate-modified = {2017-08-31 03:01:06 +0000},\n\tinstitution = {ArXiv},\n\tkeywords = {emorynlp,selected},\n\tnumber = {1604.00938},\n\ttitle = {{Multi-Field Structural Decomposition for Question Answering}},\n\turl = {http://arxiv.org/abs/1604.00938},\n\tyear = {2015},\n\tBdsk-Url-1 = {http://arxiv.org/pdf/1604.00938v1.pdf}}\n\n","author_short":["Jurczyk, T.","Choi, J. D."],"key":"jurczyk:15b","id":"jurczyk:15b","bibbaseid":"jurczyk-choi-multifieldstructuraldecompositionforquestionanswering-2015","role":"author","urls":{"Paper":"http://arxiv.org/abs/1604.00938"},"keyword":["emorynlp","selected"],"metadata":{"authorlinks":{"choi, j":"http://www.cs.emory.edu/"}},"html":""},"search_terms":["multi","field","structural","decomposition","question","answering","jurczyk","choi"],"keywords":["emorynlp","selected"],"authorIDs":["rEtLdWCDtG8gkC3Sw"],"dataSources":["WRbWtphN7JFZaJSwS","KCe4LtCfLaE5R9apZ"]}