| lr,10-5-P05-1053,ak | </term> such as <term> WordNet </term> and <term> | Name List | </term> , can be used in <term> feature-based | #9363 We also demonstrate how semantic information such as WordNet andName List, can be used in feature-based relation extraction to further improve the performance. | |
| lr-prod,3-6-P05-1053,ak | the performance . Evaluation on the <term> | ACE corpus | </term> shows that effective incorporation | #9382 Evaluation on theACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types. | |
| lr-prod,8-5-P05-1053,ak | semantic information </term> such as <term> | WordNet | </term> and <term> Name List </term> , can be | #9361 We also demonstrate how semantic information such asWordNet and Name List, can be used in feature-based relation extraction to further improve the performance. | |
| measure(ment),35-6-P05-1053,ak | kernel-based systems </term> by over 20 in <term> | F-measure | </term> on the 5 <term> ACE relation types </term> | #9414 Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 inF-measure on the 5 ACE relation types. | |
| model,8-4-P05-1053,ak | that most of useful information in <term> | full parse trees | </term> for <term> relation extraction </term> | #9338 This suggests that most of useful information infull parse trees for relation extraction is shallow and can be captured by chunking. | |
| other,1-1-P05-1053,ak | MT architectures </term> . Extracting <term> | semantic relationships | </term> between <term> entities </term> is challenging | #9266 Extractingsemantic relationships between entities is challenging. | |
| other,11-6-P05-1053,ak | effective incorporation of diverse <term> | features | </term> enables our system outperform previously | #9390 Evaluation on the ACE corpus shows that effective incorporation of diversefeatures enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types. | |
| other,22-6-P05-1053,ak | previously best-reported systems on the 24 <term> | ACE relation subtypes | </term> and significantly outperforms <term> | #9401 Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types. | |
| other,39-6-P05-1053,ak | 20 in <term> F-measure </term> on the 5 <term> | ACE relation types | </term> . <term> Sentence boundary detection | #9418 Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5ACE relation types. | |
| other,4-1-P05-1053,ak | semantic relationships </term> between <term> | entities | </term> is challenging . This paper investigates | #9269 Extracting semantic relationships betweenentities is challenging. | |
| other,4-5-P05-1053,ak | chunking </term> . We also demonstrate how <term> | semantic information | </term> such as <term> WordNet </term> and <term> | #9357 We also demonstrate howsemantic information such as WordNet and Name List, can be used in feature-based relation extraction to further improve the performance. | |
| other,6-3-P05-1053,ak | Our study illustrates that the base <term> | phrase chunking information | </term> is very effective for <term> relation | #9299 Our study illustrates that the basephrase chunking information is very effective for relation extraction and contributes to most of the performance improvement from syntactic aspect while additional information from full parsing gives limited further enhancement. | |
| other,7-2-P05-1053,ak | investigates the incorporation of diverse <term> | lexical , syntactic and semantic knowledge | </term> in <term> feature-based relation extraction | #9280 This paper investigates the incorporation of diverselexical , syntactic and semantic knowledge in feature-based relation extraction using SVM. | |
| tech,12-4-P05-1053,ak | in <term> full parse trees </term> for <term> | relation extraction | </term> is shallow and can be captured by | #9342 This suggests that most of useful information in full parse trees forrelation extraction is shallow and can be captured by chunking. | |
| tech,13-3-P05-1053,ak | information </term> is very effective for <term> | relation extraction | </term> and contributes to most of the performance | #9306 Our study illustrates that the base phrase chunking information is very effective forrelation extraction and contributes to most of the performance improvement from syntactic aspect while additional information from full parsing gives limited further enhancement. | |
| tech,14-2-P05-1053,ak | syntactic and semantic knowledge </term> in <term> | feature-based relation extraction | </term> using <term> SVM </term> . Our study | #9287 This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge infeature-based relation extraction using SVM. | |
| tech,17-5-P05-1053,ak | <term> Name List </term> , can be used in <term> | feature-based relation extraction | </term> to further improve the performance | #9370 We also demonstrate how semantic information such as WordNet and Name List, can be used infeature-based relation extraction to further improve the performance. | |
| tech,18-2-P05-1053,ak | feature-based relation extraction </term> using <term> | SVM | </term> . Our study illustrates that the | #9291 This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction usingSVM. | |
| tech,21-4-P05-1053,ak | </term> is shallow and can be captured by <term> | chunking | </term> . We also demonstrate how <term> semantic | #9351 This suggests that most of useful information in full parse trees for relation extraction is shallow and can be captured bychunking. | |
| tech,28-6-P05-1053,ak | </term> and significantly outperforms <term> | tree kernel-based systems | </term> by over 20 in <term> F-measure </term> | #9407 Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperformstree kernel-based systems by over 20 in F-measure on the 5 ACE relation types. |
