A Connectionist Approach to Prepositional Phrase Attachment for Real World Texts

In this paper we describe a neural network-based approach to prepositional phrase attachment disambiguation for real world texts. Although the use of semantic classes in this task seems intuitively to be adequate, methods employed to date have not used them very effectively. Causes of their poor results are discussed. Our model, which uses only classes, scores appreciably better than the other class-based methods which have been tested on the Wall Street Journal corpus. To date, the best result obtained using only classes was a score of 79.1%; we obtained an accuracy score of 86.8%. This score is among the best reported in the literature using this corpus.

• Publication year

  2002

• Venue

  International Conference on Computational Linguistics

• Publication date

  Unknown publication date

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3115/980432.980770
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generalizing Case Frames Using a Thesaurus and the MDL Principle

  1995cited by this paper
• A Rule-Based Approach to Prepositional Phrase Attachment Disambiguation

  1994cited by this paper
• A Maximum Entropy Model for Prepositional Phrase Attachment

  1994influential reference
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993cited by this paper
• Universal approximation bounds for superpositions of a sigmoidal function

  1993cited by this paper
• Structural Ambiguity and Lexical Relations

  1991cited by this paper
• Structural Ambiguity and Lexical Relations

  1990cited by this paper
• The structure of a semantic theory

  1963cited by this paper

• World Models for Math Story Problems

  2023cites this paper
• TDIL PROGRAMME VISION TO MISSION ON ANUVADAKSH MACHINE TRANSLATION SYSTEM July 2013-Dec 2013

  2016cites this paper
• TRANFERING OF PREPOSITIONAL PHRASES IN ENGLISH INTO TAMIL: A MACHINE LEARINING APPROACH

  2016cites this paper
• Transferring of Prepositional phrases in English into Tamil: A machine learning approach

  2014cites this paper
• APPROACHES TO HANDLE SCARCE RESOURCES FOR BENGALI STATISTICAL MACHINE TRANSLATION

  2010cites this paper
• Prepositions in Applications: A Survey and Introduction to the Special Issue

  2009cites this paper
• Simple Preposition Correspondence: A Problem in English to Indian Language Machine Translation

  2007cites this paper
• The Benefit of Stochastic PP Attachment to a Rule-Based Parser

  2006cites this paper
• Handling of Prepositions in English to Bengali Machine Translation

  2006cites this paper
• Sense Disambiguation for Preposition ‘ with ’

  2005cites this paper
• Decision Trees for Sense Disambiguation of Prepositions: Case of Over

  2004cites this paper
• Composicionalidad, cómputo de estructura y redes neuronales

  2002cites this paper
• PP-Attachment Disambiguation for Swedish: Combining Unsupervised and Supervised Training Data

  2000cites this paper
• Machine Learning and Natural Language Processing

  2000cites this paper
• ANNP: a neural network parser for real world texts

  2000cites this paper
• Using Levins verb classification for preposition sense selection in English to Indian language MT

  year unknowncites this paper