Automatic Learning of Knowledge for Example-Based Disambiguation of Attachment

نویسنده

  • Naohiko URAMOTO
چکیده

This paper describes an attempt to improve the accuracy of example-based disambiguation with minimal human intervention. Two types of knowledge – interchangeable relationships and word-to-word dependencies with preference values – are learned automatically by using the enhanced bootstrapping method, and are stored in an acquired example base. Use of this example-base improved the accuracy of the disambiguation of attachment from 85.9% to 90.3%.

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

Unsupervised Learning of Ontology-Linked Selectional Preferences

We present a method for extracting selectional preferences of verbs from unannotated text. These selectional preferences are linked to an ontology (e.g. the hypernym relations found in WordNet), which allows for extending the coverage for unseen valency fillers. For example, if drink vodka is found in the training corpus, a whole WordNet hierarchy is assigned to the verb to drink (drink liquor,...

متن کامل

The Mediating Role of Automatic Thoughts in Relationship Between Attachment Style with Sexual Dysfunction and Marital Commitment: A Path Analysis

Background: This article explores the effects of attachment style and automatic thoughts on sexual dysfunction and marital commitment, using the path analysis model. This descriptive-correlational study was conducted on 375 married female students in Shahid Chamran University of Ahvaz, Iran, from 2016 to 2017. Methods: According to Morgan and Jersey table and the statistical population (375 pe...

متن کامل

An Example-Based Disambiguation of Prepositional Phrase Attachment

Spoken language translation is a challenging new application that differs from written language translation in several ways, for instance, 1) human intervention (pre-edit or post-edit) should be avoided; 2) a real-time response is desirable for success. Example-based approaches meet these requirements, that is, they realize accurate structural disambiguation and target word selection, and respo...

متن کامل

Resolving Relative Clause Attachment Ambiguities using Machine Learning Techniques and WordNet Hierarchies

We describe an approach for resolving relative clause attachment ambiguities using machine learning techniques and WordNet hierarchies. When the relative clause is preceded by the pattern NP1 Prep NP2, a decision has to be made between local and wide attachment. We train a network to make this decision and conclude that knowledge sources like WordNet have a constructive role to play in making s...

متن کامل

PP-Attachment Disambiguation Boosted by a Gigantic Volume of Unambiguous Examples

We present a PP-attachment disambiguation method based on a gigantic volume of unambiguous examples extracted from raw corpus. The unambiguous examples are utilized to acquire precise lexical preferences for PP-attachment disambiguation. Attachment decisions are made by a machine learning method that optimizes the use of the lexical preferences. Our experiments indicate that the precise lexical...

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 1995