CPTAM: Constituency Parse Tree Aggregation Method
This addresses the issue of inconsistent parser outputs for NLP tasks, especially in out-of-domain corpora, by providing a method to aggregate trees without ground truth, though it is incremental as it builds on existing truth discovery ideas.
The paper tackles the problem of aggregating constituency parse trees from multiple parsers when ground truth is unavailable, using a truth discovery approach to estimate parser reliability and achieve high-quality aggregated trees. Experimental results show that CPTAM outperforms state-of-the-art aggregation baselines on benchmark datasets across languages and domains.
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. This paper adopts 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 consistently obtain high-quality aggregated constituency parse trees. 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) distances, 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 weights estimated by CPTAM can adequately evaluate constituency parsers in the absence of ground truth.