Paper: Domain-Independent Shallow Sentence Ordering

ACL ID N09-3014
Title Domain-Independent Shallow Sentence Ordering
Venue HLT-NAACL Companion Volume: Student Research Workshop and Doctoral Consortium
Session
Year 2009
Authors

We present a shallow approach to the sentence ordering problem. The employed features are based on discourse entities, shallow syntac- tic analysis, and temporal precedence relations retrieved from VerbOcean. We show that these relatively simple features perform well in a machine learning algorithm on datasets con- taining sequences of events, and that the re- sulting models achieve optimal performance with small amounts of training data. The model does not yet perform well on datasets describing the consequences of events, such as the destructions after an earthquake.