Probabilistic Parsing of Korean Sentences Using Collocational Information

نویسنده

  • Jae-Hoon Kim
چکیده

Lexical information is one of the most important source that can improve the accuracy of the syntactic disambigua-tion. This paper describes a Korean probabilistic parser that is based on the probabilities of phrase structure rules as well as the probabilities of collocational information between lexical items to resolve syntactic ambiguity. The proposed parser is shown by means of an extensive experiment to gain improvements in parsing accuracy. The experimental result shows about 84% in parsing accuracy .

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Probabilistic Language Model for Analyzing Korean Sentences

In this paper, we introduce a restricted form of phrase structure grammar to handle the characteristics of Korean more eeciently. Based on this restricted form of the grammar, we propose a probabilistic parser for Korean sentences. To show usefulness of the parser proposed in this paper, we made a preliminary experiment. We extract a set of rules from about 1,682 tree annotated sentences. The e...

متن کامل

An improved joint model: POS tagging and dependency parsing

Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...

متن کامل

Active Learning for Dependency Parsing Using Partially Annotated Sentences

Current successful probabilistic parsers require large treebanks which are difficult, time consuming, and expensive to produce. Some parts of these data do not contain any useful information for training a parser. Active learning strategies allow to select the most informative samples for annotation. Most existing active learning strategies for parsing rely on selecting uncertain sentences for ...

متن کامل

The Impact of Decision-making Tasks and Production Tasks On the Collocational Knowledge of Iranian Intermediate EFL Learners

The current study is an attempt to investigate the impact of decision-making (selecting and matching) tasks and production (creation of sentences and completion of sentences) tasks on the collocational knowledge of Iranian intermediate EFL learners. To this end, sixty EFL learners were divided into two experimental (decision-making and production) groups. To determine the effects of the tasks, ...

متن کامل

Bracketing Input for Accurate Parsing

Syntax parsers can benefit from speakers' intuition about constituent structures indicated in the input string in the form of parentheses. Focusing on languages like Korean, whose orthographic convention requires more than one word to be written without spaces, we describe an algorithm for passing the bracketing information across the tagger to the probabilistic CFG parser, together with one fo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1997