{"id":"https://openalex.org/W7140109441","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.307","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training","display_name":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140109441","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.307"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.307","pdf_url":"https://aclanthology.org/2026.findings-eacl.307.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.307.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jeffrey Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Joshua P Gardner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joshua P Gardner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Doug Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doug Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fangping Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangping Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Karanjeet Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karanjeet Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chun-Liang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun-Liang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Herumb Shandilya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herumb Shandilya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"David Leo Wright Hall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Leo Wright Hall","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Oncel Tuzel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oncel Tuzel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Percy Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Percy Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ludwig Schmidt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ludwig Schmidt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hadi Pouransari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hadi Pouransari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fartash Faghri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fartash Faghri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5836","last_page":"5861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.6201000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.6201000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.0674000009894371,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.06340000033378601,"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/extraction","display_name":"Extraction (chemistry)","score":0.5023999810218811},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.25209999084472656},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2337999939918518},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.22939999401569366},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.2223999947309494}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38499999046325684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.23819999396800995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2337999939918518},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.22939999401569366},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2223999947309494},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.22059999406337738},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.21819999814033508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.307","pdf_url":"https://aclanthology.org/2026.findings-eacl.307.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.307","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.307","pdf_url":"https://aclanthology.org/2026.findings-eacl.307.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5317394137382507,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140109441.pdf","grobid_xml":"https://content.openalex.org/works/W7140109441.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Jeffrey":[0],"Li,":[1,12],"Joshua":[2],"P":[3],"Gardner,":[4],"Doug":[5],"Kang,":[6],"Fangping":[7],"Shi,":[8],"Karanjeet":[9],"Singh,":[10],"Chun-Liang":[11],"Herumb":[13],"Shandilya,":[14],"David":[15],"Leo":[16],"Wright":[17],"Hall,":[18],"Oncel":[19],"Tuzel,":[20],"Percy":[21],"Liang,":[22],"Ludwig":[23],"Schmidt,":[24],"Hadi":[25],"Pouransari,":[26],"Fartash":[27],"Faghri.":[28],"Findings":[29],"of":[30],"the":[31],"Association":[32],"for":[33],"Computational":[34],"Linguistics:":[35],"EACL":[36],"2026.":[37,38]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-01T00:00:00"}