Summary of the paper
| Title | Exploiting Scope for Shallow Discourse Parsing |
|---|---|
| Authors | Rashmi Prasad, Aravind Joshi and Bonnie Webber |
| Abstract | We present an approach to automatically identifying the arguments ofdiscourse connectives based on data from the Penn Discourse Treebank.Of the two arguments of connectives, called Arg1 and Arg2, we focus onArg1, which has proven more challenging to identify. Our approachemploys a sentence-based representation of arguments, anddistinguishes "intra-sentential connectives", which take both theirarguments in the same sentence, from "inter-sentential connectives",whose arguments are found in different sentences. The latter arefurther distinguished by paragraph position into "ParaInit"connectives, which appear in a paragraph-initial sentence, and"ParaNonInit" connectives, which appear elsewhere. The paper focusseson predicting Arg1 of Inter-sentential ParaNonInit connectives,presenting a set of scope-based filters that reduce the search spacefor Arg1 from all the previous sentences in the paragraph to a subsetof them. For cases where these filters do not uniquely identify Arg1,coreference-based heuristics are employed. Our analysis shows anabsolute 3% performance improvement over the high baseline of 83.3%for identifying Arg1 of Inter-sentential ParaNonInit connectives. |
| Language | Information Extraction, Information Retrieval |
| Topics | Discourse annotation, representation and processing, Text mining, Information Extraction, Information Retrieval |
Full paper  |
Exploiting Scope for Shallow Discourse Parsing |
| Bibtex | @InProceedings{PRASAD10.935, author = {Rashmi Prasad, Aravind Joshi and Bonnie Webber}, title = {Exploiting Scope for Shallow Discourse Parsing}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |