{"id":"https://openalex.org/W2985964562","doi":"https://doi.org/10.18653/v1/d19-5818","title":"Bend but Don\u2019t Break? Multi-Challenge Stress Test for QA Models","display_name":"Bend but Don\u2019t Break? Multi-Challenge Stress Test for QA Models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2985964562","doi":"https://doi.org/10.18653/v1/d19-5818","mag":"2985964562"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/d19-5818","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002450533","display_name":"Hemant Pugaliya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hemant Pugaliya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055340301","display_name":"James Route","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Route","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038055180","display_name":"Kaixin Ma","orcid":"https://orcid.org/0000-0001-7414-5673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixin Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068836463","display_name":"Yixuan Geng","orcid":"https://orcid.org/0000-0002-8942-2562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Geng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063241234","display_name":"Eric Nyberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Nyberg","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002450533"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80833473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473059892654419},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5833649039268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4995088577270508},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46222957968711853},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4532928168773651},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44241863489151},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4223708510398865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34347936511039734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473059892654419},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5833649039268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4995088577270508},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46222957968711853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4532928168773651},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44241863489151},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4223708510398865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34347936511039734},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-5818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1801866228","https://openalex.org/W2267186426","https://openalex.org/W2551396370","https://openalex.org/W2606974598","https://openalex.org/W2609826708","https://openalex.org/W2734823783","https://openalex.org/W2742122443","https://openalex.org/W2798858969","https://openalex.org/W2799081691","https://openalex.org/W2886441967","https://openalex.org/W2889787757","https://openalex.org/W2892280852","https://openalex.org/W2893268956","https://openalex.org/W2951873305","https://openalex.org/W2962727366","https://openalex.org/W2962816513","https://openalex.org/W2963323070","https://openalex.org/W2963339397","https://openalex.org/W2963341493","https://openalex.org/W2963341956","https://openalex.org/W2963343509","https://openalex.org/W2963403868","https://openalex.org/W2963748441","https://openalex.org/W2963866616","https://openalex.org/W2963963993","https://openalex.org/W2964207259"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,35,49,88,116],"question":[3],"answering":[4],"(QA)":[5],"has":[6],"seen":[7],"rapid":[8],"growth":[9],"in":[10,16,31,43,58,80,133],"new":[11],"tasks":[12],"and":[13,22,65,86,110,122,138,147],"modeling":[14],"approaches":[15],"recent":[17],"years.":[18],"Large":[19],"scale":[20],"datasets":[21,121,135,148],"focus":[23],"on":[24,113],"challenging":[25],"linguistic":[26],"phenomena":[27],"have":[28,37],"driven":[29],"development":[30],"neural":[32],"models,":[33],"some":[34],"which":[36],"achieved":[38],"parity":[39],"with":[40,100],"human":[41],"performance":[42,66],"limited":[44],"cases.":[45],"However,":[46],"an":[47],"examination":[48],"state-of-the-art":[50],"model":[51,127],"output":[52],"reveals":[53],"that":[54,149],"a":[55,63,140],"gap":[56],"remains":[57],"reasoning":[59],"ability":[60],"compared":[61],"to":[62,68,74,96,103,126],"human,":[64],"tends":[67],"degrade":[69],"when":[70],"models":[71,90,118,146],"are":[72,78],"exposed":[73],"less-constrained":[75],"tasks.":[76],"We":[77,106,129],"interested":[79],"more":[81],"clearly":[82],"defining":[83],"the":[84,114,134],"strengths":[85],"limitations":[87,132],"leading":[89],"across":[91,119],"diverse":[92],"QA":[93,152],"challenges,":[94],"intending":[95],"help":[97],"future":[98],"researchers":[99],"identifying":[101],"pathways":[102],"generalizable":[104,145],"performance.":[105],"conduct":[107],"extensive":[108],"qualitative":[109],"quantitative":[111],"analyses":[112],"results":[115],"four":[117,120],"relate":[123],"common":[124],"errors":[125],"capabilities.":[128,153],"also":[130],"illustrate":[131],"we":[136],"examine":[137],"discuss":[139],"way":[141],"forward":[142],"for":[143],"achieving":[144],"broadly":[150],"test":[151]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}