tailieunhanh - Báo cáo khoa học: "A Discriminative Model for Joint Morphological Disambiguation and Dependency Parsing"

Most previous studies of morphological disambiguation and dependency parsing have been pursued independently. Morphological taggers operate on n-grams and do not take into account syntactic relations; parsers use the “pipeline” approach, assuming that morphological information has been separately obtained. However, in morphologically-rich languages, there is often considerable interaction between morphology and syntax, such that neither can be disambiguated without the other. | A Discriminative Model for Joint Morphological Disambiguation and Dependency Parsing John Lee Department of Chinese Translation and Linguistics City University of Hong Kong jsylee@ Jason Naradowsky David A. Smith Department of Computer Science University of Massachusetts Amherst narad dasmith @ Abstract Most previous studies of morphological disambiguation and dependency parsing have been pursued independently. Morphological taggers operate on n-grams and do not take into account syntactic relations parsers use the pipeline approach assuming that morphological information has been separately obtained. However in morphologically-rich languages there is often considerable interaction between morphology and syntax such that neither can be disambiguated without the other. In this paper we propose a discriminative model that jointly infers morphological properties and syntactic structures. In evaluations on various highly-inflected languages this joint model outperforms both a baseline tagger in morphological disambiguation and a pipeline parser in head selection. 1 Introduction To date studies of morphological analysis and dependency parsing have been pursued more or less independently. Morphological taggers disambiguate morphological attributes such as part-of-speech POS or case without taking syntax into account Hakkani-Tur et al. 2000 Hajic et al. 2001 dependency parsers commonly assume the pipeline approach relying on morphological information as part of the input Buchholz and Marsi 2006 Nivre et al. 2007 . This approach serves many languages well especially those with less morphological ambiguity. In English for example accuracy of POS tagging has risen above 885 97 Toutanova et al. 2003 and that of dependency parsing has reached the low nineties Nivre et al. 2007 . For these languages there may be little to be gained to justify the computational cost of incorporating syntactic inference during the morphological tagging task conversely it .

• Báo cáo khoa học
• A Discriminative Model
• Joint Morphological Disambiguation
• Dependency Parsing
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• A Discriminative Latent Variable Model
• Statistical Machine Translation
• A Discriminative Latent Variable Model for Statistical Machine Translation
• xử lý ngôn ngữ tự nhiên
• A Discriminative Hierarchical Model
• Fast Coreference
• Large Scale
• An Ensemble Model
• Combines Syntactic and Semantic Clustering
• Discriminative Dependency Parsing
• Robust Approach to Abbreviating Terms
• Global Information
• A Discriminative Syntactic
• Word Order Model
• Machine Translation
• mô hình ngôn ngữ
• A Discriminative Language Model
• Pseudo Negative Samples
• Daisuke Okanohara
• Flexible Answer Typing
• Discriminative Preference Ranking
• Christopher Pinchak
• scientific reports
• model language
• process natural language
• Discriminative Sentence Compression
• Soft Syntactic Evidence
• Ryan McDonald
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo
• BMC Bioinformatics
• Microscopy imaging
• Subcategory model
• Discriminative feature transform
• Subcellular localization