Paper: A Maximum Entropy Framework That Integrates Word Dependencies And Grammatical Relations For Reading Comprehension

ACL ID N06-2047
Title A Maximum Entropy Framework That Integrates Word Dependencies And Grammatical Relations For Reading Comprehension
Venue Human Language Technologies
Session Short Paper
Year 2006
Authors

Automatic reading comprehension (RC) systems can analyze a given passage and generate/extract answers in response to questions about the passage. The RC passages are often constrained in their lengths and the target answer sentence usually occurs very few times. In order to generate/extract a speci c precise an- swer, this paper proposes the integration of two types of deep linguistic features, namely word dependencies and grammati- cal relations, in a maximum entropy (ME) framework to handle the RC task. The proposed approach achieves 44.7% and 73.2% HumSent accuracy on the Reme- dia and ChungHwa corpora respectively. This result is competitive with other re- sults reported thus far.