{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/44091"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/44091","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Semantic role labeling using rich morphological features","abstract":"In this thesis, I examine the impact of morphological features on semantic role labeling (SRL) in Modern Standard Arabic. This study provides the first rigorous examination of the effect of individual morphological attributes on the automatic classification of predicate-argument roles in Arabic. I obtain a classification accuracy comparable to the best-published previous results using fewer features and a linear kernel SVM. This provides evidence that there is a strong morpho-semantic interaction in Arabic and that careful, language-dependent feature engineering may provide substantial improvements to morphologically rich languages. I demonstrate that the incorporation of rich-morphological features substantially outperform the established lexico-syntactic featuresets of standard SRL systems. A principled feature selection algorithm for SRL is also introduced that significantly decreases generalization error, leading to state-of-the-art argument role classification results.","abstract_html":"In this thesis, I examine the impact of morphological features on semantic role labeling (SRL) in Modern Standard Arabic. This study provides the first rigorous examination of the effect of individual morphological attributes on the automatic classification of predicate-argument roles in Arabic. I obtain a classification accuracy comparable to the best-published previous results using fewer features and a linear kernel SVM. This provides evidence that there is a strong morpho-semantic interaction in Arabic and that careful, language-dependent feature engineering may provide substantial improvements to morphologically rich languages. I demonstrate that the incorporation of rich-morphological features substantially outperform the established lexico-syntactic featuresets of standard SRL systems. A principled feature selection algorithm for SRL is also introduced that significantly decreases generalization error, leading to state-of-the-art argument role classification results.","abstract_has_math":false,"creators":["Lundgren, David"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Girju, Roxana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-05-24T21:50:24Z","date_published":"2013-05-24T21:50:24Z","updated_at":"2026-07-22T22:25:33Z","subjects":["semantic role labeling (SRL)","Arabic","morphology","semantics"],"languages":["en"],"rights":["Copyright 2013 David Lundgren"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/44091","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Girju, Roxana"]},{"key":"dc:creator","label":"Author","values":["Lundgren, David"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013-05-24T21:50:24Z","2013-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["semantic role labeling (SRL)","Arabic","morphology","semantics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2013 David Lundgren"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/44091"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this thesis, I examine the impact of morphological features on semantic role labeling (SRL) in Modern Standard Arabic. This study provides the first rigorous examination of the effect of individual morphological attributes on the automatic classification of predicate-argument roles in Arabic. I obtain a classification accuracy comparable to the best-published previous results using fewer features and a linear kernel SVM. This provides evidence that there is a strong morpho-semantic interaction in Arabic and that careful, language-dependent feature engineering may provide substantial improvements to morphologically rich languages. I demonstrate that the incorporation of rich-morphological features substantially outperform the established lexico-syntactic featuresets of standard SRL systems. A principled feature selection algorithm for SRL is also introduced that significantly decreases generalization error, leading to state-of-the-art argument role classification results.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-04-22T12:54:00Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Lundgren_David.pdf: 327310 bytes, checksum: f18c382ebe9dd0b7e3a55e36f73ca175 (MD5)","Made available in DSpace on 2013-05-24T21:50:24Z (GMT). No. of bitstreams: 2 David_Lundgren.pdf: 326519 bytes, checksum: 08c139b87ffd96d39d0cb6a91724e0fc (MD5) license.txt: 4064 bytes, checksum: 0dbe750d773dcc3519c0e1ef399e9e7c (MD5)"]},{"key":"dc:title","label":"Title","values":["Semantic role labeling using rich morphological features"]}]}],"canonical_facts":{"dc:contributor":["Girju, Roxana"],"dc:creator":["Lundgren, David"],"dc:date":["2013-05-24T21:50:24Z","2013-05"],"dc:description":["In this thesis, I examine the impact of morphological features on semantic role labeling (SRL) in Modern Standard Arabic. This study provides the first rigorous examination of the effect of individual morphological attributes on the automatic classification of predicate-argument roles in Arabic. I obtain a classification accuracy comparable to the best-published previous results using fewer features and a linear kernel SVM. This provides evidence that there is a strong morpho-semantic interaction in Arabic and that careful, language-dependent feature engineering may provide substantial improvements to morphologically rich languages. I demonstrate that the incorporation of rich-morphological features substantially outperform the established lexico-syntactic featuresets of standard SRL systems. A principled feature selection algorithm for SRL is also introduced that significantly decreases generalization error, leading to state-of-the-art argument role classification results.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-04-22T12:54:00Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Lundgren_David.pdf: 327310 bytes, checksum: f18c382ebe9dd0b7e3a55e36f73ca175 (MD5)","Made available in DSpace on 2013-05-24T21:50:24Z (GMT). No. of bitstreams: 2 David_Lundgren.pdf: 326519 bytes, checksum: 08c139b87ffd96d39d0cb6a91724e0fc (MD5) license.txt: 4064 bytes, checksum: 0dbe750d773dcc3519c0e1ef399e9e7c (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/44091"],"dc:language":["en"],"dc:rights":["Copyright 2013 David Lundgren"],"dc:subject":["semantic role labeling (SRL)","Arabic","morphology","semantics"],"dc:title":["Semantic role labeling using rich morphological features"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:33Z"}