A systematic comparison of various statistical alignment models
Computational Linguistics
Inducing multilingual text analysis tools via robust projection across aligned corpora
HLT '01 Proceedings of the first international conference on Human language technology research
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Speeding up LFG parsing using c-structure pruning
GEAF '08 Proceedings of the Workshop on Grammar Engineering Across Frameworks
Cross-lingual induction for deep broad-coverage syntax: a case study on German participles
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Hi-index | 0.00 |
We provide a detailed comparison of strategies for implementing medium-to-low frequency phenomena such as German adverbial participles in a broad-coverage, rule-based parsing system. We show that allowing for general adverb conversion of participles in the German LFG grammar seriously affects its overall performance, due to increased spurious ambiguity. As a solution, we present a corpus-based cross-lingual induction technique that detects adverbially used participles in parallel text. In a grammar-based evaluation, we show that the automatically induced resource appropriately restricts the adverb conversion to a limited class of participles, and improves parsing quantitatively as well as qualitatively.