Improved Parsing for Argument-Clusters Coordination
This work addresses a specific parsing issue for natural language processing applications, but it is incremental as it focuses on a narrow structural modification.
The paper tackled the problem of poor performance in predicting Argument-Cluster Coordination (ACC) by modifying the PTB representation to be more suitable for learning, resulting in a 2.7x improvement in recovering ACC structures on a 4th grade science exam corpus.
Syntactic parsers perform poorly in prediction of Argument-Cluster Coordination (ACC). We change the PTB representation of ACC to be more suitable for learning by a statistical PCFG parser, affecting 125 trees in the training set. Training on the modified trees yields a slight improvement in EVALB scores on sections 22 and 23. The main evaluation is on a corpus of 4th grade science exams, in which ACC structures are prevalent. On this corpus, we obtain an impressive x2.7 improvement in recovering ACC structures compared to a parser trained on the original PTB trees.