{"corpus_id":28333432,"paper_sha":"40efb77ca54ee33ac16f01e034ca951abe653a56","doi":"10.1609/aaai.v31i1.11012","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2605024074,"dblp_id":"conf/aaai/LiYWC17","acl_id":null,"title":"Efficiently Mining High Quality Phrases from Texts","year":2017,"publication_date":"2017-02-12","venue":"AAAI Conference on Artificial Intelligence","journal":{"name":null,"pages":"3474-3481","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science"],"reference_count":33,"citation_count":16,"influential_citation_count":0,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11012/10871","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/40efb77ca54ee33ac16f01e034ca951abe653a56","s2_open_access_license":null,"s2_open_access_status":"BRONZE","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"\n \n Phrase mining is a key research problem for semantic analysis and text-based information retrieval. The existing approaches based on NLP, frequency, and statistics cannot extract high quality phrases and the processing is also time consuming, which are not suitable for dynamic on-line applications. In this paper, we propose an efficient high-quality phrase mining approach (EQPM). To the best of our knowledge, our work is the first effort that considers both intra-cohesion and inter-isolation in mining phrases, which is able to guarantee appropriateness. We also propose a strategy to eliminate order sensitiveness, and ensure the completeness of phrases. We further design efficient algorithms to make the proposed model and strategy feasible. The empirical evaluations on four real data sets demonstrate that our approach achieved a considerable quality improvement and the processing time was 2.3X - 29X faster than the state-of-the-art works.\n \n","claims":[{"public_id":"cl_ef3f7f59e0da76828a3e8fbe0ef6853b","status":"active","text":"A strategy is introduced to eliminate order sensitiveness and ensure phrase completeness.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_ef3f7f59e0da76828a3e8fbe0ef6853b"},{"public_id":"cl_c57bcbf04e7be4d89c2b789aaa2c297e","status":"active","text":"EQPM is a phrase mining approach that considers both intra-cohesion and inter-isolation to guarantee phrase appropriateness.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_c57bcbf04e7be4d89c2b789aaa2c297e"},{"public_id":"cl_725d91a3558dae769747c4136bc9820f","status":"active","text":"Efficient algorithms make the proposed model and strategy feasible for phrase mining.","confidence":0.9,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_725d91a3558dae769747c4136bc9820f"},{"public_id":"cl_d85a4aada636c5f20b2ef5c2360595e1","status":"active","text":"Empirical evaluations on four real datasets show considerable quality improvement and 2.3X–29X faster processing than state-of-the-art methods.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_d85a4aada636c5f20b2ef5c2360595e1"}],"concepts":[{"public_id":"co_0dd0fdcfecc00e8223719c90c0a6f675","status":"active","name":"intra-cohesion","description":"The internal semantic or statistical connectedness among words within a phrase.","types":["criterion"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_0dd0fdcfecc00e8223719c90c0a6f675"},{"public_id":"co_1dbaa9d5f355163ad2a6a69a72faf383","status":"active","name":"phrase completeness","description":"The property of capturing an entire phrase rather than only part of it.","types":["property"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1dbaa9d5f355163ad2a6a69a72faf383"},{"public_id":"co_224afaf77df3e52d6b74fe09891a2bfa","status":"active","name":"state-of-the-art works","description":"The strongest existing phrase mining methods used as comparison baselines.","types":["baseline"],"aliases":["state-of-the-art methods"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_224afaf77df3e52d6b74fe09891a2bfa"},{"public_id":"co_2b1fb63bf826551fe13923027eab746a","status":"active","name":"EQPM","description":"An efficient phrase mining approach designed to extract high-quality phrases from text.","types":["method"],"aliases":["efficient high-quality phrase mining approach"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2b1fb63bf826551fe13923027eab746a"},{"public_id":"co_6c3c5d1dffc9697be4046c3367622502","status":"active","name":"efficient algorithms","description":"Algorithms designed to reduce the computational cost of the proposed phrase mining approach.","types":["algorithm"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6c3c5d1dffc9697be4046c3367622502"},{"public_id":"co_93690c0256a97f6666a1fb0b2cf9c459","status":"active","name":"quality improvement","description":"An increase in the quality of extracted phrases relative to comparison methods.","types":["outcome"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_93690c0256a97f6666a1fb0b2cf9c459"},{"public_id":"co_bc1f5bee3b6205bb49cd41f118780e5e","status":"active","name":"inter-isolation","description":"The degree to which a phrase is distinct from surrounding text or other candidate phrases.","types":["criterion"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_bc1f5bee3b6205bb49cd41f118780e5e"},{"public_id":"co_c4ebf948fd0e0dd3511a82111e611eda","status":"active","name":"order sensitiveness","description":"Sensitivity of phrase mining results to word order variations in candidate phrases.","types":["property"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c4ebf948fd0e0dd3511a82111e611eda"},{"public_id":"co_db9fc0f78f39a20793135c3bf36e11b0","status":"active","name":"four real data sets","description":"Four real-world datasets used to evaluate the phrase mining approach.","types":["evaluation dataset"],"aliases":["four real datasets"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_db9fc0f78f39a20793135c3bf36e11b0"}],"external_ids":{"DOI":"10.1609/aaai.v31i1.11012","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2605024074,"DBLP":"conf/aaai/LiYWC17","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11012/10871","landing_url":"https://www.semanticscholar.org/paper/40efb77ca54ee33ac16f01e034ca951abe653a56","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":null,"status":"BRONZE","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":634894,"paper_uid":"79f789f7-8a0e-498a-a4d1-560027010c60","canonical_identity":{"paper_id":634894,"paper_uid":"79f789f7-8a0e-498a-a4d1-560027010c60","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/28333432"}