{"id":"https://openalex.org/W2902447889","doi":"https://doi.org/10.18653/v1/w18-6547","title":"The Task Matters: Comparing Image Captioning and Task-Based Dialogical Image Description","display_name":"The Task Matters: Comparing Image Captioning and Task-Based Dialogical Image Description","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902447889","doi":"https://doi.org/10.18653/v1/w18-6547","mag":"2902447889"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6547","pdf_url":"https://www.aclweb.org/anthology/W18-6547.pdf","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 11th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6547.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055162329","display_name":"Nikolai Ilinykh","orcid":"https://orcid.org/0000-0001-9048-5467"},"institutions":[{"id":"https://openalex.org/I203082224","display_name":"Hochschule Bielefeld","ror":"https://ror.org/00edvg943","country_code":"DE","type":"education","lineage":["https://openalex.org/I203082224"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nikolai Ilinykh","raw_affiliation_strings":["Dialogue Systems Group University of Bielefeld Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialogue Systems Group University of Bielefeld Germany","institution_ids":["https://openalex.org/I203082224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078051602","display_name":"Sina Zarrie\u00df","orcid":"https://orcid.org/0000-0002-1384-1218"},"institutions":[{"id":"https://openalex.org/I203082224","display_name":"Hochschule Bielefeld","ror":"https://ror.org/00edvg943","country_code":"DE","type":"education","lineage":["https://openalex.org/I203082224"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sina Zarrie\u00df","raw_affiliation_strings":["Dialogue Systems Group University of Bielefeld Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialogue Systems Group University of Bielefeld Germany","institution_ids":["https://openalex.org/I203082224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032801642","display_name":"David Schlangen","orcid":"https://orcid.org/0000-0002-2686-6887"},"institutions":[{"id":"https://openalex.org/I203082224","display_name":"Hochschule Bielefeld","ror":"https://ror.org/00edvg943","country_code":"DE","type":"education","lineage":["https://openalex.org/I203082224"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Schlangen","raw_affiliation_strings":["Dialogue Systems Group University of Bielefeld Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dialogue Systems Group University of Bielefeld Germany","institution_ids":["https://openalex.org/I203082224"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.424,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6867457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"397","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9822999835014343,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9797000288963318,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9579613208770752},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.763102650642395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570454478263855},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6783506870269775},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6568435430526733},{"id":"https://openalex.org/keywords/dialogical-self","display_name":"Dialogical self","score":0.6064732074737549},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5221928954124451},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.520507276058197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.507483184337616},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4445044994354248},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.42498287558555603},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38071149587631226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3688194453716278},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10327973961830139},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08672791719436646}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9579613208770752},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.763102650642395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570454478263855},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6783506870269775},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6568435430526733},{"id":"https://openalex.org/C10646191","wikidata":"https://www.wikidata.org/wiki/Q1996523","display_name":"Dialogical self","level":2,"score":0.6064732074737549},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5221928954124451},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.520507276058197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507483184337616},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4445044994354248},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.42498287558555603},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38071149587631226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3688194453716278},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10327973961830139},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08672791719436646},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w18-6547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6547","pdf_url":"https://www.aclweb.org/anthology/W18-6547.pdf","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 11th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:pub.uni-bielefeld.de:2931465","is_oa":true,"landing_page_url":"https://pub.uni-bielefeld.de/record/2931465","pdf_url":null,"source":{"id":"https://openalex.org/S4306401624","display_name":"Publikationen an der Universit\u00e4t Bielefeld (Universit\u00e4t Bielefeld)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ilinykh N, Zarrie\u00df S, Schlangen D. The Task Matters. Comparing Image Captioning and Task-Based Dialogical Image Description. In:  &lt;em&gt;Proceedings of 11th International Conference on Natural Language Generation (INLG 2018)&lt;/em&gt;. 2018.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6547","pdf_url":"https://www.aclweb.org/anthology/W18-6547.pdf","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 11th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902447889.pdf","grobid_xml":"https://content.openalex.org/works/W2902447889.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W8550301","https://openalex.org/W68733909","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1996430422","https://openalex.org/W2105103432","https://openalex.org/W2119775030","https://openalex.org/W2185175083","https://openalex.org/W2251512949","https://openalex.org/W2282219577","https://openalex.org/W2507296351","https://openalex.org/W2558809543","https://openalex.org/W2561997787","https://openalex.org/W2741931646","https://openalex.org/W2768661419","https://openalex.org/W2835434549","https://openalex.org/W2949341804","https://openalex.org/W2952782394","https://openalex.org/W2963109634","https://openalex.org/W2963925269","https://openalex.org/W2964195418","https://openalex.org/W2964248669"],"related_works":["https://openalex.org/W2776402699","https://openalex.org/W2989758125","https://openalex.org/W2289593370","https://openalex.org/W4210416330","https://openalex.org/W4313139854","https://openalex.org/W2991526051","https://openalex.org/W3032811015","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4399485860"],"abstract_inverted_index":{"Image":[0],"captioning":[1,150],"models":[2],"are":[3,14,68,140],"typically":[4],"trained":[5],"on":[6],"data":[7,59],"that":[8,55,123,139],"is":[9,34,48,61,132],"collected":[10],"from":[11,118],"people":[12],"who":[13],"asked":[15],"to":[16,36,41,63,71,107],"describe":[17,108],"an":[18],"image,":[19],"without":[20],"being":[21],"given":[22],"any":[23],"further":[24],"task":[25,42,51],"context.":[26],"As":[27,76],"we":[28,79,153],"argue":[29],"here,":[30],"this":[31,102,119],"context":[32],"independence":[33],"likely":[35],"cause":[37],"problems":[38],"for":[39,155],"transferring":[40],"settings":[43],"in":[44,96,130,143],"which":[45,67,152],"image":[46,65,127,149],"description":[47],"bound":[49],"by":[50],"demands.":[52],"We":[53,114],"demonstrate":[54],"careful":[56],"design":[57],"of":[58,92,126],"collection":[60],"required":[62],"obtain":[64],"descriptions":[66,128,144],"contextually":[69],"bounded":[70],"a":[72,77,82,97,116,147],"particular":[73],"meta-level":[74],"task.":[75],"task,":[78,151],"use":[80],"MeetUp!,":[81],"text-based":[83],"communication":[84],"game":[85],"where":[86],"two":[87],"players":[88,105],"have":[89],"the":[90,104,124],"goal":[91],"finding":[93],"each":[94],"other":[95],"visual":[98],"environment.":[99],"To":[100],"reach":[101],"goal,":[103],"need":[106],"images":[109],"representing":[110],"their":[111],"current":[112],"location.":[113],"analyse":[115],"dataset":[117],"domain":[120],"and":[121,135],"show":[122],"nature":[125],"found":[129],"MeetUp!":[131],"diverse,":[133],"dynamic":[134],"rich":[136],"with":[137],"phenomena":[138],"not":[141],"present":[142],"obtained":[145],"through":[146],"simple":[148],"ran":[154],"comparison.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
