{"id":"https://openalex.org/W4385239309","doi":"https://doi.org/10.1145/3609798","title":"ICON: A Linguistically-Motivated Large-Scale Benchmark Indonesian Constituency Treebank","display_name":"ICON: A Linguistically-Motivated Large-Scale Benchmark Indonesian Constituency Treebank","publication_year":2023,"publication_date":"2023-07-25","ids":{"openalex":"https://openalex.org/W4385239309","doi":"https://doi.org/10.1145/3609798"},"language":"en","primary_location":{"id":"doi:10.1145/3609798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609798","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101822506","display_name":"Ee Suan Lim","orcid":"https://orcid.org/0000-0001-5417-7897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ee Suan Lim","raw_affiliation_strings":["AI Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5417-7897","affiliations":[{"raw_affiliation_string":"AI Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038370332","display_name":"Wei Qi Leong","orcid":"https://orcid.org/0009-0002-0645-1112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Qi Leong","raw_affiliation_strings":["AI Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-0645-1112","affiliations":[{"raw_affiliation_string":"AI Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101944406","display_name":"Thanh Ngan Nguyen","orcid":"https://orcid.org/0009-0009-7995-9866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thanh Ngan Nguyen","raw_affiliation_strings":["AI Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-7995-9866","affiliations":[{"raw_affiliation_string":"AI Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092538209","display_name":"Wei Ming Kng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ming Kng","raw_affiliation_strings":["AI Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-4076-9554","affiliations":[{"raw_affiliation_string":"AI Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086528347","display_name":"William Chandra Tjhi","orcid":"https://orcid.org/0009-0009-9861-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Chandra Tjhi","raw_affiliation_strings":["AI Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-9861-3545","affiliations":[{"raw_affiliation_string":"AI Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092538210","display_name":"Dea Adhista","orcid":"https://orcid.org/0009-0003-4326-0646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dea Adhista","raw_affiliation_strings":["Prosa.ai, Indonesia"],"raw_orcid":"https://orcid.org/0009-0003-4326-0646","affiliations":[{"raw_affiliation_string":"Prosa.ai, Indonesia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021128017","display_name":"Ayu Purwarianti","orcid":"https://orcid.org/0000-0002-5016-3700"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Prosa.ai and Institut Teknologi Bandung, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-5016-3700","affiliations":[{"raw_affiliation_string":"Prosa.ai and Institut Teknologi Bandung, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07957183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"8","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9724000096321106,"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/treebank","display_name":"Treebank","score":0.9863100051879883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973843216896057},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.782657265663147},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.7113492488861084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6828214526176453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6429234743118286},{"id":"https://openalex.org/keywords/icon","display_name":"Icon","score":0.6366979479789734},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5770089626312256},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5443257093429565},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.4482380449771881},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24619781970977783},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11846515536308289}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9863100051879883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973843216896057},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.782657265663147},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.7113492488861084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6828214526176453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6429234743118286},{"id":"https://openalex.org/C2778447006","wikidata":"https://www.wikidata.org/wiki/Q1156474","display_name":"Icon","level":2,"score":0.6366979479789734},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5770089626312256},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5443257093429565},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.4482380449771881},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24619781970977783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11846515536308289},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3609798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609798","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":110,"referenced_works":["https://openalex.org/W128638292","https://openalex.org/W182831726","https://openalex.org/W419994591","https://openalex.org/W560202235","https://openalex.org/W803770162","https://openalex.org/W1482921657","https://openalex.org/W1490476168","https://openalex.org/W1500398412","https://openalex.org/W1516184288","https://openalex.org/W1532548519","https://openalex.org/W1537658846","https://openalex.org/W1970961429","https://openalex.org/W1972913706","https://openalex.org/W1975323159","https://openalex.org/W1984947923","https://openalex.org/W1987923986","https://openalex.org/W1996309571","https://openalex.org/W1998506279","https://openalex.org/W2002032183","https://openalex.org/W2011520099","https://openalex.org/W2034693287","https://openalex.org/W2038324640","https://openalex.org/W2082722939","https://openalex.org/W2088115296","https://openalex.org/W2093647425","https://openalex.org/W2107370057","https://openalex.org/W2114691286","https://openalex.org/W2122531007","https://openalex.org/W2123442489","https://openalex.org/W2129882630","https://openalex.org/W2133707058","https://openalex.org/W2151170651","https://openalex.org/W2152907450","https://openalex.org/W2163107094","https://openalex.org/W2165225913","https://openalex.org/W2229162816","https://openalex.org/W2250218929","https://openalex.org/W2251204185","https://openalex.org/W2252026558","https://openalex.org/W2297780049","https://openalex.org/W2343954916","https://openalex.org/W2491886887","https://openalex.org/W2498564848","https://openalex.org/W2531638282","https://openalex.org/W2563495010","https://openalex.org/W2608787653","https://openalex.org/W2620628668","https://openalex.org/W2766056037","https://openalex.org/W2798833929","https://openalex.org/W2799253188","https://openalex.org/W2800577862","https://openalex.org/W2805853209","https://openalex.org/W2885212328","https://openalex.org/W2900819242","https://openalex.org/W2908475389","https://openalex.org/W2915977242","https://openalex.org/W2932376173","https://openalex.org/W2932637973","https://openalex.org/W2948947170","https://openalex.org/W2962739339","https://openalex.org/W2963021447","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963754491","https://openalex.org/W2964030814","https://openalex.org/W2970810281","https://openalex.org/W2970830889","https://openalex.org/W2970854433","https://openalex.org/W2985521958","https://openalex.org/W3001279689","https://openalex.org/W3011411500","https://openalex.org/W3011924861","https://openalex.org/W3016560063","https://openalex.org/W3034522557","https://openalex.org/W3035390927","https://openalex.org/W3035636774","https://openalex.org/W3035970863","https://openalex.org/W3037109418","https://openalex.org/W3088636528","https://openalex.org/W3099023595","https://openalex.org/W3101638898","https://openalex.org/W3105033018","https://openalex.org/W3105234369","https://openalex.org/W3116295307","https://openalex.org/W3118514006","https://openalex.org/W3132360492","https://openalex.org/W3156159991","https://openalex.org/W3169483174","https://openalex.org/W3169499208","https://openalex.org/W3173293897","https://openalex.org/W3175666528","https://openalex.org/W3185341429","https://openalex.org/W3189958166","https://openalex.org/W3192459431","https://openalex.org/W3204163842","https://openalex.org/W4224298595","https://openalex.org/W4225849768","https://openalex.org/W4226155321","https://openalex.org/W4246282176","https://openalex.org/W4281687091","https://openalex.org/W4285159183","https://openalex.org/W4291331426","https://openalex.org/W4292358172","https://openalex.org/W4385245566","https://openalex.org/W4404778218","https://openalex.org/W4404783772","https://openalex.org/W6629354627","https://openalex.org/W6792210918","https://openalex.org/W6930676798","https://openalex.org/W7021285659"],"related_works":["https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W2109902858","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2575884139","https://openalex.org/W3101476433"],"abstract_inverted_index":{"Constituency":[0],"parsing":[1,17,32],"is":[2],"an":[3],"important":[4],"task":[5],"of":[6,62,77,83,86,117,140,149],"informing":[7],"how":[8],"words":[9],"are":[10,109],"combined":[11],"to":[12,104,162],"form":[13],"sentences.":[14],"While":[15],"constituency":[16,31,57,172],"in":[18,24,33,99,101,166],"English":[19],"has":[20],"seen":[21],"significant":[22],"progress":[23],"the":[25,49,75,84,88,94,107,114,124,128,137,155],"last":[26],"few":[27,36],"years,":[28],"tools":[29],"for":[30,113,171],"Indonesian":[34,56,167],"remain":[35],"and":[37,65,69,92,96,111],"far":[38],"between.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,90],"publish":[44],"ICON":[45,125],"(Indonesian":[46],"CONstituency":[47],"treebank),":[48],"hitherto":[50],"largest":[51],"publicly":[52],"available":[53],"manually-annotated":[54],"benchmark":[55],"treebank":[58],"with":[59,132,136],"a":[60],"size":[61],"10,000":[63],"sentences":[64],"approximately":[66],"124,000":[67],"constituents":[68],"182,000":[70],"tokens,":[71],"which":[72],"can":[73],"support":[74],"training":[76],"state-of-the-art":[78],"transformer-based":[79,133],"models.":[80],"As":[81],"part":[82],"process":[85],"building":[87],"treebank,":[89],"review":[91],"revamp":[93],"constituent":[95],"POS":[97],"tagsets":[98],"use":[100],"existing":[102],"treebanks":[103],"ensure":[105],"that":[106,168],"labels":[108],"relevant":[110],"suitable":[112],"grammatical":[115],"features":[116],"Indonesian.":[118],"We":[119,152],"establish":[120],"strong":[121],"baselines":[122],"on":[123],"dataset":[126],"using":[127],"Berkeley":[129],"Neural":[130],"Parser":[131],"pre-trained":[134],"embeddings,":[135],"best":[138],"performance":[139],"88.85%":[141],"F1":[142],"score":[143],"coming":[144],"from":[145],"our":[146,159],"own":[147],"version":[148],"SpanBERT":[150],"(IndoSpanBERT).":[151],"further":[153],"analyze":[154],"predictions":[156],"made":[157],"by":[158],"best-performing":[160],"model":[161],"reveal":[163],"certain":[164],"idiosyncrasies":[165],"pose":[169],"challenges":[170],"parsing.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}