Automatic labeling of semantic roles Export

@article{citeulike:453920, abstract = {We present a system for identifying the semantic relationships, or semantic roles , filled by constituents of a sentence within a semantic frame. Given an input sentence and a target word and frame, the system labels constituents with either abstract semantic roles, such as AGENT or PATIENT, or more domain-specific semantic roles, such as SPEAKER, MESSAGE, and TOPIC. The system is based on statistical classifiers trained on roughly 50,000 sentences that were hand-annotated with semantic roles by the FrameNet semantic labeling project. We then parsed each training sentence into a syntactic tree and extracted various lexical and syntactic features, including the phrase type of each constituent, its grammatical function, and its position in the sentence. These features were combined with knowledge of the predicate verb, noun, or adjective, as well as information such as the prior probabilities of various combinations of semantic roles. We used various lexical clustering algorithms to generalize across possible fillers of roles. Test sentences were parsed, were annotated with these features, and were then passed through the classifiers . Our system achieves 82\% accuracy in identifying the semantic role of presegmented constituents. At the more difficult task of simultaneously segmenting constituents and identifying their semantic role, the system achieved 65\% precision and 61\% recall . Our study also allowed us to compare the usefulness of different features and feature combination methods in the semantic role labeling task. We also explore the integration of role labeling with statistical syntactic parsing and attempt to generalize to predicates unseen in the training data .}, address = {Cambridge, MA, USA}, author = {Gildea, Daniel and Jurafsky, Daniel}, citeulike-article-id = {453920}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=643093}, citeulike-linkout-1 = {http://dx.doi.org/10.1162/089120102760275983}, comment = {field: natural language understanding. problem: traditonal method is domain-specific. goal: domain-independent. approach: use FrameNet corpus. result: presegmented-82\% or 65\%p and 61\%r. }, doi = {10.1162/089120102760275983}, issn = {0891-2017}, journal = {Comput. Linguist.}, keywords = {semantic\_roles\_labeling, term\_relation, thesis}, month = {September}, number = {3}, pages = {245--288}, posted-at = {2006-01-01 02:59:19}, priority = {0}, publisher = {MIT Press}, title = {Automatic labeling of semantic roles}, url = {http://dx.doi.org/10.1162/089120102760275983}, volume = {28}, year = {2002} }

TY - JOUR ID - citeulike:453920 L3 - citeulike-article-id:453920 N2 - We present a system for identifying the semantic relationships, or semantic roles , filled by constituents of a sentence within a semantic frame. Given an input sentence and a target word and frame, the system labels constituents with either abstract semantic roles, such as AGENT or PATIENT, or more domain-specific semantic roles, such as SPEAKER, MESSAGE, and TOPIC. The system is based on statistical classifiers trained on roughly 50,000 sentences that were hand-annotated with semantic roles by the FrameNet semantic labeling project. We then parsed each training sentence into a syntactic tree and extracted various lexical and syntactic features, including the phrase type of each constituent, its grammatical function, and its position in the sentence. These features were combined with knowledge of the predicate verb, noun, or adjective, as well as information such as the prior probabilities of various combinations of semantic roles. We used various lexical clustering algorithms to generalize across possible fillers of roles. Test sentences were parsed, were annotated with these features, and were then passed through the classifiers . Our system achieves 82% accuracy in identifying the semantic role of presegmented constituents. At the more difficult task of simultaneously segmenting constituents and identifying their semantic role, the system achieved 65% precision and 61% recall . Our study also allowed us to compare the usefulness of different features and feature combination methods in the semantic role labeling task. We also explore the integration of role labeling with statistical syntactic parsing and attempt to generalize to predicates unseen in the training data . IS - 3 JF - Comput. Linguist. SN - 0891-2017 AD - Cambridge, MA, USA EP - 288 TI - Automatic labeling of semantic roles PB - MIT Press VL - 28 SP - 245 KW - semantic_roles_labeling KW - term_relation KW - thesis N1 - field: natural language understanding. problem: traditonal method is domain-specific. goal: domain-independent. approach: use FrameNet corpus. result: presegmented-82% or 65%p and 61%r. AU - Gildea, Daniel AU - Jurafsky, Daniel PY - 2002/09// UR - http://dx.doi.org/10.1162/089120102760275983 ER -