Rules vs. Examples: An Experimental Study Using the Banzai Parser

نویسنده

  • Noriko Nagata
چکیده

This paper introduces a new parser-driven Japanese tutor called BANZAI, and presents an experimental study comparing the relative effectiveness of deductive (rule driven) feedback and inductive (example driven) feedback implemented in the BANZAI program. The study finds that deductive feedback can be superior to inductive feedback when the learning task involves relatively complex structures whose grammatical rules are not salient in light of the examples.

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

ارائۀ راهکاری قاعده‌مند جهت تبدیل خودکار درخت تجزیۀ نحوی وابستگی به درخت تجزیۀ نحوی ساخت‌سازه‌ای برای زبان فارسی

In this paper, an automatic method in converting a dependency parse tree into an equivalent phrase structure one, is introduced for the Persian language. In first step, a rule-based algorithm was designed. Then, Persian specific dependency-to-phrase structure conversion rules merged to the algorithm. Subsequently, the Persian dependency treebank with about 30,000 sentences was used as an input ...

متن کامل

Studying impressive parameters on the performance of Persian probabilistic context free grammar parser

In linguistics, a tree bank is a parsed text corpus that annotates syntactic or semantic sentence structure. The exploitation of tree bank data has been important ever since the first large-scale tree bank, The Penn Treebank, was published. However, although originating in computational linguistics, the value of tree bank is becoming more widely appreciated in linguistics research as a whole. F...

متن کامل

The impact of picture-based vs. context-based method on Iranian intermediate EFL learners' knowledge of prepositions

The present study aimed to investigate the effect of picture-based vs. context-base method onIranian intermediate EFL learners' knowledge of prepositions. The main question this study triedto answer were whether using picture-based vs. context-based method might enhance higherknowledge of prepositions in Iranian learners of English at intermediate level. To answer thequestions, 45 intermediate ...

متن کامل

Feature Engineering in Persian Dependency Parser

Dependency parser is one of the most important fundamental tools in the natural language processing, which extracts structure of sentences and determines the relations between words based on the dependency grammar. The dependency parser is proper for free order languages, such as Persian. In this paper, data-driven dependency parser has been developed with the help of phrase-structure parser fo...

متن کامل

Learning Programming Language Parsing Rules

Modern programming languages have some natural language properties, such as scoping/precedence ambiguities regarding arithmetic operators (e. g. + vs. *) and word (symbol) sense ambiguities (e. g. unary vs. binary +). Typically these ambiguities are resolved according to well-known conventions so that programs do not need to contain too many parentheses. These ambiguities are not necessary in p...

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