Learning to parse spontaneous speech

We describe and experimentally evaluate a system, FeasPar, that learns parsing of spontaneous speech. To train and run FeasPar (Feature Structure Parser), only limited handmodeled knowledge is required. The FeasPar architecture consists of neural networks and a search. The networks split the incoming sentence into chunks, which are labeled with feature values and chunk relations. Then the search finds the most probable and consistent feature structure. FeasPar is trained, tested and evaluated with the spontaneous scheduling task, and compared with two samples of a handmodeled GLR* parser, developed for 4 months and 2 years, respectively. The handmodeling effort for FeasPar is 2 weeks. FeasPar performs better than the GLR* parser developed 4 months in all six comparisons that are made and has a similar performance to the GLR* parser developed for 2 years