A Linguistically Inspired Statistical Model for Chinese Punctuation Generation

摘要

This article investigates a relatively underdeveloped subject in natural language processing-the generation of punctuation marks. From a theoretical perspective, we study 16 Chinese punctu-ation marks as denned in the Chinese national standard of punctuation usage, and categorize these punctuation marks into three different types according to their syntactic properties. We implement a three-tier maximum entropy model incorporating linguistically-motivated features for generating the commonly used Chinese punctuation marks in unpunctuated sentences out-put by a surface realizer. Furthermore, we present a method to automatically extract cue words indicating sentence-final punctuation marks as a specialized feature to construct a more precise model. Evaluating on the Penn Chinese Treebank data, the MaxEnt model achieves an f-score of 79.83% for punctuation insertion and 74.61% for punctuation restoration using gold data input, 79.50% for insertion and 73.32% for restoration using parser-based imperfect input. The experi-ments show that the MaxEnt model significantly outperforms a baseline 5-gram language model that scores 54.99% for punctuation insertion and 52.01% for restoration. We show that our results are not far from human performance on the same task with human insertion f-scores in the range of 81-87% and human restoration in the range of 71-82%. Finally, a manual error analysis of the generation output shows that close to 40% of the mismatched punctuation marks do in fact result in acceptable choices, a fact obscured in the automatic string-matching based evaluation scores.