{"doi":"10.1162/tacl_a_00138","title":"Domain Adaptation for Syntactic and Semantic Dependency Parsing Using                     Deep Belief Networks","abstract":"<jats:p> In current systems for syntactic and semantic dependency parsing, people usually define a very high-dimensional feature space to achieve good performance. But these systems often suffer severe performance drops on out-of-domain test data due to the diversity of features of different domains. This paper focuses on how to relieve this domain adaptation problem with the help of unlabeled target domain data. We propose a deep learning method to adapt both syntactic and semantic parsers. With additional unlabeled target domain data, our method can learn a latent feature representation (LFR) that is beneficial to both domains. Experiments on English data in the CoNLL 2009 shared task show that our method largely reduced the performance drop on out-of-domain test data. Moreover, we get a Macro F1 score that is 2.32 points higher than the best system in the CoNLL 2009 shared task in out-of-domain tests. </jats:p>","journal":"Transactions of the Association for Computational Linguistics","year":2015,"id":22453,"datarank":0.8379605782809663,"base_score":2.4849066497880004,"endowment":2.4849066497880004,"self_citation_contribution":0.37273599746820013,"citation_network_contribution":0.4652245808127662,"self_endowment_contribution":0.37273599746820013,"citer_contribution":0.4652245808127662,"corpus_percentile":null,"corpus_rank":null,"citation_count":11,"citer_count":8,"citers_with_citation_signal":8,"citers_with_endowment":8,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":141111,"name":"Tao Zhuang","orcid":null,"position":1,"is_corresponding":false},{"id":141112,"name":"Chengqing Zong","orcid":null,"position":2,"is_corresponding":false},{"id":141110,"name":"Haitong Yang","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":2.4849066497880004,"endowment":2.4849066497880004,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"21071399","pmcid":null,"openalex_id":"https://openalex.org/W1907444042","authors":[],"funders":[],"total_grants":0,"fwci":1.7804,"citation_percentile":0.88373688,"influential_citations":1,"citation_trend":[{"year":2016,"count":3},{"year":2017,"count":1},{"year":2019,"count":3},{"year":2020,"count":2},{"year":2022,"count":2}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00138","host_type":"journal"},{"url":"https://doi.org/10.1162/tacl_a_00138","host_type":"GOLD"},{"url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00138","host_type":"publisher"},{"url":"https://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00138","host_type":"publisher"},{"url":"https://doaj.org/article/22242390c9324d17a1628f213301aed2","host_type":"repository"}],"fields_of_study":["Natural Language Processing Techniques","Topic Modeling","Speech Recognition and Synthesis","Computer Science"],"mesh_terms":[],"keywords":["Computer science","Dependency grammar","Artificial intelligence","Natural language processing","Parsing","Domain (mathematical analysis)","Feature (linguistics)","Task (project management)","Semantic role labeling","Test data","Domain adaptation","Dependency (UML)","Machine learning","Programming language"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-07T00:25:42.276726Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}