Publication Information

{'id': 'https://openalex.org/W2496235729', 'doi': 'https://doi.org/10.1075/cilt.292.32var', 'title': 'Parallel corpora for medium density languages', 'display_name': 'Parallel corpora for medium density languages', 'publication_year': 2007, 'publication_date': '2007-12-13', 'ids': {'openalex': 'https://openalex.org/W2496235729', 'doi': 'https://doi.org/10.1075/cilt.292.32var', 'mag': '2496235729'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1075/cilt.292.32var', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4210203166', 'display_name': 'Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory', 'issn_l': '0304-0763', 'issn': ['0304-0763'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320402', 'host_organization_name': 'John Benjamins Publishing Company', 'host_organization_lineage': ['https://openalex.org/P4310320402'], 'host_organization_lineage_names': ['John Benjamins Publishing Company'], 'type': 'book series'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'book-chapter', 'type_crossref': 'book-chapter', 'indexed_in': ['crossref'], 'open_access': {'is_oa': True, 'oa_status': 'green', 'oa_url': 'https://eprints.sztaki.hu/7902/1/Kornai_1762382_ny.pdf', 'any_repository_has_fulltext': True}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5078450617', 'display_name': 'Dániel Varga', 'orcid': 'https://orcid.org/0000-0002-8004-1704'}, 'institutions': [], 'countries': [], 'is_corresponding': False, 'raw_author_name': 'Dániel Varga', 'raw_affiliation_strings': ['Media Research and Education Center Stoczek u. 2 H-1111 Budapest'], 'affiliations': [{'raw_affiliation_string': 'Media Research and Education Center Stoczek u. 2 H-1111 Budapest', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5045106271', 'display_name': 'Péter Halácsy', 'orcid': None}, 'institutions': [], 'countries': [], 'is_corresponding': False, 'raw_author_name': 'Péter Halácsy', 'raw_affiliation_strings': ['1111 Budapest'], 'affiliations': [{'raw_affiliation_string': '1111 Budapest', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5065413313', 'display_name': 'András Kornai', 'orcid': 'https://orcid.org/0000-0001-6078-6840'}, 'institutions': [], 'countries': ['US'], 'is_corresponding': False, 'raw_author_name': 'András Kornai', 'raw_affiliation_strings': ['MetaCarta Inc. 875 Massachusetts Avenue Cambridge MA 02139'], 'affiliations': [{'raw_affiliation_string': 'MetaCarta Inc. 875 Massachusetts Avenue Cambridge MA 02139', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5110928615', 'display_name': 'Viktor Nagy', 'orcid': None}, 'institutions': [], 'countries': [], 'is_corresponding': False, 'raw_author_name': 'Viktor Nagy', 'raw_affiliation_strings': ['Institute of Linguistics Benczúr u 33 H-1399 Budapest'], 'affiliations': [{'raw_affiliation_string': 'Institute of Linguistics Benczúr u 33 H-1399 Budapest', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5026599769', 'display_name': 'László Németh', 'orcid': 'https://orcid.org/0000-0001-9062-9280'}, 'institutions': [{'id': 'https://openalex.org/I98677209', 'display_name': 'University of Edinburgh', 'ror': 'https://ror.org/01nrxwf90', 'country_code': 'GB', 'type': 'education', 'lineage': ['https://openalex.org/I98677209']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'László Németh', 'raw_affiliation_strings': ['U of Edinburgh'], 'affiliations': [{'raw_affiliation_string': 'U of Edinburgh', 'institution_ids': ['https://openalex.org/I98677209']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5053973863', 'display_name': 'Viktor Trón', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I98677209', 'display_name': 'University of Edinburgh', 'ror': 'https://ror.org/01nrxwf90', 'country_code': 'GB', 'type': 'education', 'lineage': ['https://openalex.org/I98677209']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'Viktor Trón', 'raw_affiliation_strings': ['U of Edinburgh'], 'affiliations': [{'raw_affiliation_string': 'U of Edinburgh', 'institution_ids': ['https://openalex.org/I98677209']}]}], 'institution_assertions': [], 'countries_distinct_count': 2, 'institutions_distinct_count': 1, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 6.796, 'has_fulltext': True, 'fulltext_origin': 'pdf', 'cited_by_count': 382, 'citation_normalized_percentile': {'value': 0.99982, 'is_in_top_1_percent': True, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 99, 'max': 100}, 'biblio': {'volume': None, 'issue': None, 'first_page': '247', 'last_page': '258'}, 'is_retracted': False, 'is_paratext': 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': 0.9982, '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/T13629', 'display_name': 'Text Readability and Simplification', 'score': 0.9907, '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': [], 'concepts': [{'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.5731414}, {'id': 'https://openalex.org/C204321447', 'wikidata': 'https://www.wikidata.org/wiki/Q30642', 'display_name': 'Natural language processing', 'level': 1, 'score': 0.46769193}, {'id': 'https://openalex.org/C41895202', 'wikidata': 'https://www.wikidata.org/wiki/Q8162', 'display_name': 'Linguistics', 'level': 1, 'score': 0.4259566}, {'id': 'https://openalex.org/C138885662', 'wikidata': 'https://www.wikidata.org/wiki/Q5891', 'display_name': 'Philosophy', 'level': 0, 'score': 0.10081977}], 'mesh': [], 'locations_count': 2, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1075/cilt.292.32var', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4210203166', 'display_name': 'Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory', 'issn_l': '0304-0763', 'issn': ['0304-0763'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320402', 'host_organization_name': 'John Benjamins Publishing Company', 'host_organization_lineage': ['https://openalex.org/P4310320402'], 'host_organization_lineage_names': ['John Benjamins Publishing Company'], 'type': 'book series'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, {'is_oa': True, 'landing_page_url': 'http://eprints.sztaki.hu/7902/', 'pdf_url': 'https://eprints.sztaki.hu/7902/1/Kornai_1762382_ny.pdf', 'source': {'id': 'https://openalex.org/S4306401907', 'display_name': 'SZTAKI Publication Repository (Hungarian Academy of Sciences)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I7597260', 'host_organization_name': 'Hungarian Academy of Sciences', 'host_organization_lineage': ['https://openalex.org/I7597260'], 'host_organization_lineage_names': ['Hungarian Academy of Sciences'], 'type': 'repository'}, 'license': 'public-domain', 'license_id': 'https://openalex.org/licenses/public-domain', 'version': 'acceptedVersion', 'is_accepted': True, 'is_published': False}], 'best_oa_location': {'is_oa': True, 'landing_page_url': 'http://eprints.sztaki.hu/7902/', 'pdf_url': 'https://eprints.sztaki.hu/7902/1/Kornai_1762382_ny.pdf', 'source': {'id': 'https://openalex.org/S4306401907', 'display_name': 'SZTAKI Publication Repository (Hungarian Academy of Sciences)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I7597260', 'host_organization_name': 'Hungarian Academy of Sciences', 'host_organization_lineage': ['https://openalex.org/I7597260'], 'host_organization_lineage_names': ['Hungarian Academy of Sciences'], 'type': 'repository'}, 'license': 'public-domain', 'license_id': 'https://openalex.org/licenses/public-domain', 'version': 'acceptedVersion', 'is_accepted': True, 'is_published': False}, 'sustainable_development_goals': [{'score': 0.84, 'display_name': 'Quality education', 'id': 'https://metadata.un.org/sdg/4'}], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 16, 'referenced_works': ['https://openalex.org/W1089141', 'https://openalex.org/W1489181569', 'https://openalex.org/W1491634991', 'https://openalex.org/W1636405317', 'https://openalex.org/W1819903106', 'https://openalex.org/W2006969979', 'https://openalex.org/W2017180565', 'https://openalex.org/W2031338704', 'https://openalex.org/W2047295649', 'https://openalex.org/W2117652747', 'https://openalex.org/W2127973959', 'https://openalex.org/W2138553032', 'https://openalex.org/W2138753018', 'https://openalex.org/W2167925143', 'https://openalex.org/W2168929382', 'https://openalex.org/W2406530069'], 'related_works': ['https://openalex.org/W3169305685', 'https://openalex.org/W2789919619', 'https://openalex.org/W2610387714', 'https://openalex.org/W2369308426', 'https://openalex.org/W2359001871', 'https://openalex.org/W2351428524', 'https://openalex.org/W2293457016', 'https://openalex.org/W1569841287', 'https://openalex.org/W1551406738', 'https://openalex.org/W1512718085'], 'abstract_inverted_index': {'The': [0], 'choice': [1], 'of': [2, 17, 23, 32, 78], 'natural': [3], 'language': [4, 10], 'technology': [5], 'appropriate': [6, 35], 'for': [7, 36, 59, 67], 'a': [8, 56], 'given': [9], 'is': [11], 'greatly': [12], 'impacted': [13], 'by': [14], 'density': [15, 28, 40, 50, 69], '(availability': [16], 'digitally': [18], 'stored': [19], 'material).More': [20], 'than': [21], 'half': [22], 'the': [24, 33, 48, 76, 87], 'world': [25], 'speaks': [26], 'medium': [27, 49, 68], 'languages,': [29, 70], 'yet': [30], 'many': [31], 'methods': [34], 'high': [37], 'or': [38], 'low': [39], 'languages': [41], 'yield': [42], 'suboptimal': [43], 'results': [44], 'when': [45], 'applied': [46], 'to': [47], 'case.In': [51], 'this': [52], 'paper': [53], 'we': [54, 92], 'describe': [55, 84], 'general': [57], 'methodology': [58], 'rapidly': [60], 'collecting,': [61], 'building,': [62], 'and': [63, 81, 85], 'aligning': [64], 'parallel': [65], 'corpora': [66], 'illustrating': [71], 'our': [72], 'main': [73], 'points': [74], 'on': [75], 'case': [77], 'Hungarian,': [79], 'Romanian,': [80], 'Slovenian.We': [82], 'also': [83], 'evaluate': [86], 'hybrid': [88], 'sentence': [89], 'alignment': [90], 'method': [91], 'are': [93], 'using.': [94]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2496235729', 'counts_by_year': [{'year': 2024, 'cited_by_count': 3}, {'year': 2023, 'cited_by_count': 20}, {'year': 2022, 'cited_by_count': 12}, {'year': 2021, 'cited_by_count': 27}, {'year': 2020, 'cited_by_count': 43}, {'year': 2019, 'cited_by_count': 36}, {'year': 2018, 'cited_by_count': 25}, {'year': 2017, 'cited_by_count': 20}, {'year': 2016, 'cited_by_count': 23}, {'year': 2015, 'cited_by_count': 19}, {'year': 2014, 'cited_by_count': 37}, {'year': 2013, 'cited_by_count': 22}, {'year': 2012, 'cited_by_count': 39}], 'updated_date': '2025-01-10T08:05:16.252434', 'created_date': '2016-08-23'}