Abstract | ||
---|---|---|
We present a series of experiments on automatically identifying the sense of implicit discourse relations, i.e. relations that are not marked with a discourse connective such as "but" or "because". We work with a corpus of implicit relations present in newspaper text and report results on a test set that is representative of the naturally occurring distribution of senses. We use several linguistically informed features, including polarity tags, Levin verb classes, length of verb phrases, modality, context, and lexical features. In addition, we revisit past approaches using lexical pairs from unannotated text as features, explain some of their shortcomings and propose modifications. Our best combination of features outperforms the baseline from data intensive approaches by 4% for comparison and 16% for contingency. |
Year | Venue | Keywords |
---|---|---|
2009 | ACL/IJCNLP | verb phrase,automatic sense prediction,lexical feature,implicit discourse relation,implicit relation,newspaper text,lexical pair,levin verb class,unannotated text,discourse connective,best combination |
Field | DocType | Volume |
Verb,Discourse relation,Computer science,Newspaper,Artificial intelligence,Natural language processing,Linguistics,Contingency,Test set | Conference | P09-1 |
Citations | PageRank | References |
130 | 5.11 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Emily Pitler | 1 | 573 | 27.65 |
Annie Louis | 2 | 443 | 24.78 |
Ani Nenkova | 3 | 1831 | 109.14 |