Get quick answers to your questions about the article from our AI researcher chatbot
{'id': 'https://openalex.org/W2154756108', 'doi': 'https://doi.org/10.1162/089120104773633394', 'title': 'Accessor Variety Criteria for Chinese Word Extraction', 'display_name': 'Accessor Variety Criteria for Chinese Word Extraction', 'publication_year': 2004, 'publication_date': '2004-03-01', 'ids': {'openalex': 'https://openalex.org/W2154756108', 'doi': 'https://doi.org/10.1162/089120104773633394', 'mag': '2154756108'}, 'language': 'en', 'primary_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1162/089120104773633394', 'pdf_url': 'http://www.mitpressjournals.org/doi/pdf/10.1162/089120104773633394', 'source': {'id': 'https://openalex.org/S155526855', 'display_name': 'Computational Linguistics', 'issn_l': '0891-2017', 'issn': ['0891-2017', '1530-9312'], 'is_oa': True, 'is_in_doaj': True, 'is_indexed_in_scopus': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320244', 'host_organization_name': 'Association for Computational Linguistics', 'host_organization_lineage': ['https://openalex.org/P4310320244'], 'host_organization_lineage_names': ['Association for Computational Linguistics'], 'type': 'journal'}, 'license': 'cc-by-nc-nd', 'license_id': 'https://openalex.org/licenses/cc-by-nc-nd', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'type': 'article', 'type_crossref': 'journal-article', 'indexed_in': ['crossref'], 'open_access': {'is_oa': True, 'oa_status': 'hybrid', 'oa_url': 'http://www.mitpressjournals.org/doi/pdf/10.1162/089120104773633394', 'any_repository_has_fulltext': False}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5101498861', 'display_name': 'Haodi Feng', 'orcid': 'https://orcid.org/0000-0002-0656-5905'}, 'institutions': [{'id': 'https://openalex.org/I168719708', 'display_name': 'City University of Hong Kong', 'ror': 'https://ror.org/03q8dnn23', 'country_code': 'HK', 'type': 'funder', 'lineage': ['https://openalex.org/I168719708']}, {'id': 'https://openalex.org/I99065089', 'display_name': 'Tsinghua University', 'ror': 'https://ror.org/03cve4549', 'country_code': 'CN', 'type': 'funder', 'lineage': ['https://openalex.org/I99065089']}, {'id': 'https://openalex.org/I154099455', 'display_name': 'Shandong University', 'ror': 'https://ror.org/0207yh398', 'country_code': 'CN', 'type': 'funder', 'lineage': ['https://openalex.org/I154099455']}], 'countries': ['CN', 'HK'], 'is_corresponding': True, 'raw_author_name': 'Haodi Feng', 'raw_affiliation_strings': ['Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong. E-mail: or', 'Shandong University Tsinghua University City University of Hong Kong, School of Computer Science and Technology, Jinan, PRC; Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong.or'], 'affiliations': [{'raw_affiliation_string': 'Shandong University Tsinghua University City University of Hong Kong, School of Computer Science and Technology, Jinan, PRC; Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong.or', 'institution_ids': ['https://openalex.org/I168719708', 'https://openalex.org/I99065089', 'https://openalex.org/I154099455']}, {'raw_affiliation_string': 'Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong. E-mail: or', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5100447195', 'display_name': 'Kang Chen', 'orcid': 'https://orcid.org/0000-0002-8368-1109'}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'funder', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': True, 'raw_author_name': 'Kang Chen', 'raw_affiliation_strings': ['Department of Computer Science and Technology, Peking, PR China.'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Science and Technology, Peking, PR China.', 'institution_ids': ['https://openalex.org/I20231570']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5100638710', 'display_name': 'Xiaotie Deng', 'orcid': 'https://orcid.org/0000-0002-5282-6467'}, 'institutions': [{'id': 'https://openalex.org/I168719708', 'display_name': 'City University of Hong Kong', 'ror': 'https://ror.org/03q8dnn23', 'country_code': 'HK', 'type': 'funder', 'lineage': ['https://openalex.org/I168719708']}, {'id': 'https://openalex.org/I99065089', 'display_name': 'Tsinghua University', 'ror': 'https://ror.org/03cve4549', 'country_code': 'CN', 'type': 'funder', 'lineage': ['https://openalex.org/I99065089']}], 'countries': ['CN', 'HK'], 'is_corresponding': True, 'raw_author_name': 'Xiaotie Deng', 'raw_affiliation_strings': ['City University of Hong Kong Tsinghua University, Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong.'], 'affiliations': [{'raw_affiliation_string': 'City University of Hong Kong Tsinghua University, Department of Computer Science, Tat Chee Avenue, Kowloon, Hong Kong.', 'institution_ids': ['https://openalex.org/I168719708', 'https://openalex.org/I99065089']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5108050911', 'display_name': 'Weimin Zheng', 'orcid': 'https://orcid.org/0000-0002-4450-5428'}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'funder', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': True, 'raw_author_name': 'Weimin Zheng', 'raw_affiliation_strings': ['Department of Computer Science and Technology, Peking, PR China.'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Science and Technology, Peking, PR China.', 'institution_ids': ['https://openalex.org/I20231570']}]}], 'institution_assertions': [], 'countries_distinct_count': 2, 'institutions_distinct_count': 4, 'corresponding_author_ids': ['https://openalex.org/A5101498861', 'https://openalex.org/A5100447195', 'https://openalex.org/A5100638710', 'https://openalex.org/A5108050911'], 'corresponding_institution_ids': ['https://openalex.org/I168719708', 'https://openalex.org/I99065089', 'https://openalex.org/I154099455', 'https://openalex.org/I20231570', 'https://openalex.org/I168719708', 'https://openalex.org/I99065089', 'https://openalex.org/I20231570'], 'apc_list': {'value': 0, 'currency': 'USD', 'value_usd': 0, 'provenance': 'doaj'}, 'apc_paid': {'value': 0, 'currency': 'USD', 'value_usd': 0, 'provenance': 'doaj'}, 'fwci': 2.451, 'has_fulltext': True, 'fulltext_origin': 'pdf', 'cited_by_count': 127, 'citation_normalized_percentile': {'value': 0.974037, 'is_in_top_1_percent': False, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 97, 'max': 98}, 'biblio': {'volume': '30', 'issue': '1', 'first_page': '75', 'last_page': '93'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T10181', 'display_name': 'Natural Language Processing Techniques', 'score': 0.9996, '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': 0.9996, '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': 0.9976, '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/T13083', 'display_name': 'Advanced Text Analysis Techniques', 'score': 0.9957, '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/independence', 'display_name': 'Independence', 'score': 0.45590585}], 'concepts': [{'id': 'https://openalex.org/C157486923', 'wikidata': 'https://www.wikidata.org/wiki/Q1376436', 'display_name': 'String (physics)', 'level': 2, 'score': 0.8187752}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.77621204}, {'id': 'https://openalex.org/C90805587', 'wikidata': 'https://www.wikidata.org/wiki/Q10944557', 'display_name': 'Word (group theory)', 'level': 2, 'score': 0.695794}, {'id': 'https://openalex.org/C136197465', 'wikidata': 'https://www.wikidata.org/wiki/Q1729295', 'display_name': 'Variety (cybernetics)', 'level': 2, 'score': 0.66990745}, {'id': 'https://openalex.org/C204321447', 'wikidata': 'https://www.wikidata.org/wiki/Q30642', 'display_name': 'Natural language processing', 'level': 1, 'score': 0.63142323}, {'id': 'https://openalex.org/C2779343474', 'wikidata': 'https://www.wikidata.org/wiki/Q3109175', 'display_name': 'Context (archaeology)', 'level': 2, 'score': 0.5668434}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.47067437}, {'id': 'https://openalex.org/C35651441', 'wikidata': 'https://www.wikidata.org/wiki/Q625303', 'display_name': 'Independence (probability theory)', 'level': 2, 'score': 0.45590585}, {'id': 'https://openalex.org/C2781051154', 'wikidata': 'https://www.wikidata.org/wiki/Q8201', 'display_name': 'Chinese characters', 'level': 2, 'score': 0.43354064}, {'id': 'https://openalex.org/C41895202', 'wikidata': 'https://www.wikidata.org/wiki/Q8162', 'display_name': 'Linguistics', 'level': 1, 'score': 0.4188304}, {'id': 'https://openalex.org/C2780586882', 'wikidata': 'https://www.wikidata.org/wiki/Q7520643', 'display_name': 'Simple (philosophy)', 'level': 2, 'score': 0.4124553}, {'id': 'https://openalex.org/C33923547', 'wikidata': 'https://www.wikidata.org/wiki/Q395', 'display_name': 'Mathematics', 'level': 0, 'score': 0.17027882}, {'id': 'https://openalex.org/C95457728', 'wikidata': 'https://www.wikidata.org/wiki/Q309', 'display_name': 'History', 'level': 0, 'score': 0.10897678}, {'id': 'https://openalex.org/C138885662', 'wikidata': 'https://www.wikidata.org/wiki/Q5891', 'display_name': 'Philosophy', '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/C166957645', 'wikidata': 'https://www.wikidata.org/wiki/Q23498', 'display_name': 'Archaeology', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C37914503', 'wikidata': 'https://www.wikidata.org/wiki/Q156495', 'display_name': 'Mathematical physics', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C111472728', 'wikidata': 'https://www.wikidata.org/wiki/Q9471', 'display_name': 'Epistemology', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': True, 'landing_page_url': 'https://doi.org/10.1162/089120104773633394', 'pdf_url': 'http://www.mitpressjournals.org/doi/pdf/10.1162/089120104773633394', 'source': {'id': 'https://openalex.org/S155526855', 'display_name': 'Computational Linguistics', 'issn_l': '0891-2017', 'issn': ['0891-2017', '1530-9312'], 'is_oa': True, 'is_in_doaj': True, 'is_indexed_in_scopus': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320244', 'host_organization_name': 'Association for Computational Linguistics', 'host_organization_lineage': ['https://openalex.org/P4310320244'], 'host_organization_lineage_names': ['Association for Computational Linguistics'], 'type': 'journal'}, 'license': 'cc-by-nc-nd', 'license_id': 'https://openalex.org/licenses/cc-by-nc-nd', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}], 'best_oa_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1162/089120104773633394', 'pdf_url': 'http://www.mitpressjournals.org/doi/pdf/10.1162/089120104773633394', 'source': {'id': 'https://openalex.org/S155526855', 'display_name': 'Computational Linguistics', 'issn_l': '0891-2017', 'issn': ['0891-2017', '1530-9312'], 'is_oa': True, 'is_in_doaj': True, 'is_indexed_in_scopus': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320244', 'host_organization_name': 'Association for Computational Linguistics', 'host_organization_lineage': ['https://openalex.org/P4310320244'], 'host_organization_lineage_names': ['Association for Computational Linguistics'], 'type': 'journal'}, 'license': 'cc-by-nc-nd', 'license_id': 'https://openalex.org/licenses/cc-by-nc-nd', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'sustainable_development_goals': [{'score': 0.49, 'id': 'https://metadata.un.org/sdg/4', 'display_name': 'Quality education'}], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 34, 'referenced_works': ['https://openalex.org/W114321176', 'https://openalex.org/W1491693718', 'https://openalex.org/W1503913248', 'https://openalex.org/W1518670641', 'https://openalex.org/W1557074680', 'https://openalex.org/W1558333962', 'https://openalex.org/W1582664203', 'https://openalex.org/W1660390307', 'https://openalex.org/W1847536016', 'https://openalex.org/W1979262500', 'https://openalex.org/W1991566282', 'https://openalex.org/W1996034123', 'https://openalex.org/W2008434289', 'https://openalex.org/W2015152466', 'https://openalex.org/W2025214515', 'https://openalex.org/W2047792838', 'https://openalex.org/W2053695062', 'https://openalex.org/W2070164178', 'https://openalex.org/W2121497944', 'https://openalex.org/W2127683092', 'https://openalex.org/W2129287413', 'https://openalex.org/W2166391512', 'https://openalex.org/W2198380824', 'https://openalex.org/W2334801970', 'https://openalex.org/W2420187884', 'https://openalex.org/W2610493035', 'https://openalex.org/W2729906263', 'https://openalex.org/W2785679778', 'https://openalex.org/W2996160789', 'https://openalex.org/W3043710305', 'https://openalex.org/W3200634688', 'https://openalex.org/W4231741839', 'https://openalex.org/W4241850027', 'https://openalex.org/W786936280'], 'related_works': ['https://openalex.org/W54497855', 'https://openalex.org/W3125814499', 'https://openalex.org/W3121970507', 'https://openalex.org/W2565703248', 'https://openalex.org/W217960748', 'https://openalex.org/W2143548620', 'https://openalex.org/W2110028391', 'https://openalex.org/W2090827041', 'https://openalex.org/W2032233321', 'https://openalex.org/W187246281'], 'abstract_inverted_index': {'We': [0, 13, 64, 86, 117], 'are': [1, 34, 52, 56, 91, 101], 'interested': [2], 'in': [3, 48, 81, 136, 165], 'the': [4, 42, 67, 88, 98, 112, 115, 123, 126, 150, 153, 160, 163, 166], 'problem': [5], 'of': [6, 23, 44, 114, 122, 128, 133, 152, 156, 162], 'word': [7, 16, 71, 185], 'extraction': [8, 186], 'from': [9, 41, 159], 'Chinese': [10, 25, 39, 184], 'text': [11], 'collections.': [12], 'define': [14], 'a': [15, 19, 70, 73, 94, 104, 134, 137, 157], 'to': [17], 'be': [18, 79], 'meaningful': [20], 'string': [21, 95, 105, 135, 158], 'composed': [22], 'several': [24], 'characters.': [26], 'For': [27], 'example,': [28], '‘percent’,': [29], 'and,': [30], '‘more': [31], 'and': [32, 60, 97, 131, 142, 146, 173, 187, 191], 'more’,': [33], 'not': [35], 'recognized': [36], 'as': [37, 107, 149], 'traditional': [38], 'words': [40, 53, 194], 'viewpoint': [43, 68], 'some': [45], 'people.': [46], 'However,': [47], 'our': [49, 171], 'work,': [50], 'they': [51, 55], 'because': [54], 'very': [57], 'widely': [58], 'used': [59, 80], 'have': [61], 'specific': [62], 'meanings.': [63], 'start': [65], 'with': [66], 'that': [69, 77, 90, 100, 175], 'is': [72, 188], 'distinguished': [74], 'linguistic': [75], 'entity': [76], 'can': [78], 'many': [82], 'different': [83], 'language': [84], 'environments.': [85], 'consider': [87, 125], 'characters': [89, 99, 120], 'directly': [92, 102], 'before': [93], '(predecessors)': [96], 'after': [103], '(successors)': [106], 'important': [108], 'factors': [109], 'for': [110, 183, 192], 'determining': [111], 'independence': [113], 'string.': [116], 'call': [118], 'such': [119], 'accessors': [121], 'string,': [124], 'number': [127], 'distinct': [129], 'predecessors': [130], 'successors': [132], 'large': [138], 'corpus': [139], '(TREC': [140], '5': [141], 'TREC': [143], '6': [144], 'documents),': [145], 'use': [147], 'them': [148], 'measurement': [151], 'context': [154], 'independency': [155], 'rest': [161], 'sentences': [164], 'document.': [167], 'Our': [168], 'experiments': [169], 'confirm': [170], 'hypothesis': [172], 'show': [174], 'this': [176], 'simple': [177], 'rule': [178], 'gives': [179], 'quite': [180], 'good': [181], 'results': [182], 'comparable': [189], 'to,': [190], 'long': [193], 'outperforms,': [195], 'other': [196], 'iterative': [197], 'methods.': [198]}, 'abstract_inverted_index_v3': None, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2154756108', 'counts_by_year': [{'year': 2024, 'cited_by_count': 3}, {'year': 2023, 'cited_by_count': 2}, {'year': 2022, 'cited_by_count': 2}, {'year': 2021, 'cited_by_count': 2}, {'year': 2020, 'cited_by_count': 2}, {'year': 2019, 'cited_by_count': 8}, {'year': 2018, 'cited_by_count': 7}, {'year': 2017, 'cited_by_count': 7}, {'year': 2016, 'cited_by_count': 4}, {'year': 2015, 'cited_by_count': 5}, {'year': 2014, 'cited_by_count': 11}, {'year': 2013, 'cited_by_count': 12}, {'year': 2012, 'cited_by_count': 15}], 'updated_date': '2025-01-26T04:54:06.742937', 'created_date': '2016-06-24'}