Combining deep linguistics analysis and surface pattern learning

Abstract

We explore a hybrid approach for Chinese definitional question answering by combining deep linguistic analysis with surface pattern learning. We answer four questions in this study: 1) How helpful are linguistic analysis and pattern learning? 2) What kind of questions can be answered by pattern matching? 3) How much annotation is required for a pattern-based system to achieve good performance? 4) What linguistic features are most useful? Extensive experiments are conducted on biographical questions and other definitional questions. Major findings include: 1) linguistic analysis and pattern learning are complementary; both are required to make a good definitional QA system; 2) pattern matching is very effective in answering biographical questions while less effective for other definitional questions; 3) only a small amount of annotation is required for a pattern learning system to achieve good performance on biographical questions; 4) the most useful linguistic features are copulas and appositives; relations also play an important role; only some propositions convey vital facts.