Truth Discovery in Constituency Parse Tree Aggregation
Diverse Natural Language Processing tasks employ constituency parsing to understand the syntactic structure of a sentence according to a phrase structure grammar. Many state-of-the-art constituency parsers are proposed, but they may provide different results for the same sentences, especially for corpora outside their training domains. In this study, we adopt the truth discovery idea to aggregate constituency parse trees from different parsers by estimating their reliability in the absence of ground truth. Our goal is to obtain high-quality aggregated constituency parse trees consistently. We formulate the constituency parse tree aggregation problem in two steps, structure aggregation and constituent label aggregation. Specifically, we propose the first truth discovery solution for tree structures by minimizing the weighted sum of Robinson-Foulds RF distance, a classic symmetric distance metric between two trees. Extensive experiments are conducted on benchmark datasets in different languages and domains. The experimental results show that our method, CPTAM, outperforms the state-of-the-art aggregation baselines. We also demonstrate that the weight estimation can adequately evaluate constituency parsers in the absence of ground truth.
Committee: Dr. Qi Li (major professor), Dr. Kris De Brabanter, Dr. Oliver Eulenstein, Dr. Zhu Zhang, Dr. Jia Liu