For incomplete sentences, different structural descriptions with different levels of prediction are possible. Two existing dependency parsers have been modified to generate sequences of output hypotheses in an incremental manner. The parsing results can be characterized with respect to different criteria like the amount of predicted information, its quality, monotonicity, delay, inclusiveness and connectedness. We propose an evaluation scheme able to capture these properties and apply it to the parsers in different configurations.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com