tailieunhanh - Báo cáo khoa học: "Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing"

We investigate active learning methods for Japanese dependency parsing. We propose active learning methods of using partial dependency relations in a given sentence for parsing and evaluate their effectiveness empirically. Furthermore, we utilize syntactic constraints of Japanese to obtain more labeled examples from precious labeled ones that annotators give. Experimental results show that our proposed methods improve considerably the learning curve of Japanese dependency parsing. | Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing Manabu Sassano Yahoo Japan Corporation Midtown Tower 9-7-1 Akasaka Minato-ku Tokyo 107-6211 Japan msassano@ Abstract We investigate active learning methods for Japanese dependency parsing. We propose active learning methods of using partial dependency relations in a given sentence for parsing and evaluate their effectiveness empirically. Furthermore we utilize syntactic constraints of Japanese to obtain more labeled examples from precious labeled ones that annotators give. Experimental results show that our proposed methods improve considerably the learning curve of Japanese dependency parsing. In order to achieve an accuracy of over one of our methods requires only of labeled examples as compared to passive learning. 1 Introduction Reducing annotation cost is very important because supervised learning approaches which have been successful in natural language processing require typically a large number of labeled examples. Preparing many labeled examples is time consuming and labor intensive. One of most promising approaches to this issue is active learning. Recently much attention has been paid to it in the field of natural language processing. Various tasks have been targeted in the research on active learning. They include word sense disambiguation . Zhu and Hovy 2007 POS tagging Ringger et al. 2007 named entity recognition Laws and Schutze 2008 word segmentation . Sassano 2002 and parsing . Tang et al. 2002 Hwa 2004 . It is the main purpose of this study to propose methods of improving active learning for parsing by using a smaller constituent than a sentence as a unit that is selected at each iteration of active learning. Typically in active learning for parsing a Sadao Kurohashi Graduate School of Informatics Kyoto University Yoshida-honmachi Sakyo-ku Kyoto 606-8501 Japan kuro@ sentence has been considered to be a