Prepositional Phrase Attachment through a Backed-off Model

Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form v np1 p np2 are resolved through a model which considers values of the four head words (v, n1, p and n2). This paper shows that the problem is analogous to n-gram language models in speech recognition, and that one of the most common methods for language modeling, the backed-off estimate, is applicable. Results on Wall Street Journal data of 84.5% accuracy are obtained using this method. A surprising result is the importance of low-count events — ignoring events which occur less than 5 times in training data reduces performance to 81.6%.

• Publication year

  1995

• Venue

  VLC@ACL

• Publication date

  1995-06-22

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1007/978-94-017-2390-9_11arXiv cmp-lg/9506021
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for 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
• A Freely Available Wide Coverage Morphological Analyzer for English

  1992cited by this paper
• Structural Ambiguity and Lexical Relations

  1991cited by this paper
• Poor Estimates of Context are Worse than None

  1990cited by this paper
• Estimation of probabilities from sparse data for the language model component of a speech recognizer

  1987cited by this paper

• Can Informativity Effects Be Predictability Effects in Disguise?

  2025cites this paper
• Active use of latent tree-structured sentence representation in humans and large language models

  2025cites this paper
• Tree Transformer's Disambiguation Ability of Prepositional Phrase Attachment and Garden Path Effects

  2024cites this paper
• Resolving Prepositional Phrase Attachment Ambiguities with Contextualized Word Embeddings

  2021cites this paper
• Competency Problems: On Finding and Removing Artifacts in Language Data

  2021cites this paper
• Something Old, Something New: Grammar-based CCG Parsing with Transformer Models

  2021cites this paper
• Evaluating Models’ Local Decision Boundaries via Contrast Sets

  2020cites this paper
• Evaluating NLP Models via Contrast Sets

  2020cites this paper
• Using Brain Imaging to Gauge Difficulties in Processing Ambiguous Text by Non-native Speakers

  2019cites this paper
• National Library of Medicine

  2019cites this paper
• Modeling Ambiguity in Text: A Corpus of Legal Literature

  2019cites this paper
• Association Metrics in Neural Transition-Based Dependency Parsing

  2019cites this paper
• Using Word Sketches to Resolve Prepositional Phrase Attachment Ambiguity in Arabic

  2019cites this paper
• Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics

  2019influential citation
• A STUDY ON NLP APPLICATIONS AND AMBIGUITY PROBLEMS SHAIDAH JUSOH

  2018cites this paper
• Valency-Augmented Dependency Parsing

  2018cites this paper
• An Analysis of Prepositional-Phrase Attachment Disambiguation

  2018cites this paper
• Probabilistic latent variable models for knowledge discovery and optimization

  2017cites this paper
• Improving Syntactic Parsing of Clinical Text Using Domain Knowledge

  2017influential citation
• Prepositions in Context

  2017cites this paper
• Weighted DAG Automata for Semantic Graphs

  2017cites this paper
• Prepositional Phrase Attachment over Word Embedding Products

  2017cites this paper
• Incrementally Identifying Objects from Referring Expressions using Spatial Object Models

  2016cites this paper
• Machine Reading with Background Knowledge

  2016influential citation
• An Empirical Study of Smoothing Techniques for Language Modeling

  2015cites this paper
• An Empirical Study of Smoothing Techniques for Language Modeling

  2015cites this paper
• A Knowledge-Intensive Model for Prepositional Phrase Attachment

  2015influential citation
• Prepositional Phrase Attachment Problem Revisited: how Verbnet can Help

  2015cites this paper
• An Empirical Study of Smoothing Techniques for Language Modeling

  2015cites this paper
• An Empirical Study of Smoothing Techniques for Language Modeling

  2015cites this paper
• Boosting drug named entity recognition using an aggregate classifier

  2015cites this paper
• Semantic Relatedness and Textual Entailment via Corpus Patterns

  2015cites this paper
• Web as a Corpus: Going Beyond the n-gram

  2014cites this paper
• Neural Network Architectures for Prepositional Phrase Attachment Disambiguation

  2014cites this paper
• Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment

  2014cites this paper
• Models for improved tractability and accuracy in dependency parsing

  2013cites this paper
• Computing with prepositions: Syntax

  2013cites this paper
• Two Word Reordering Strategies in English-to-Chinese Translation

  2013cites this paper
• Identification of English Prepositional Phrases within Business Domain for Machine Translation

  2013cites this paper
• Rule based Approach for Prepositional Phrase Attachment in English-Tamil Translation

  2013cites this paper
• UCCA: A Semantics-based Grammatical Annotation Scheme

  2013cites this paper
• Learning Corpus Patterns Using Finite State Automata

  2013cites this paper
• Using a Cognitive Architecture in Incremental Sentence Processing

  2012cites this paper
• Semantic based orthographic with prepositional phrase for English-Tamil translation

  2012cites this paper
• UNIVERSITY OF ALGARVE FACULTY OF SOCIAL AND HUMAN SCIENCE THE UNIVERSITY OF WOLVERHAMPTON SCHOOL OF LAW, SOCIAL SCIENCES AND COMMUNICATIONS

  2012cites this paper
• Ensemble Learning for Low Resources Prepositional Phrase Attachment

  2012cites this paper
• Toward Robust Information Extraction Models for Multimedia Documents

  2012cites this paper
• Buildind a Resource of Patterns Using Semantic Types

  2012cites this paper
• Extraction of linguistic resources from multilingual corpora and their exploitation

  2012cites this paper
• FOR MUC-6 Breck

  2012cites this paper
• Resolving prepositional phrase attachment ambiguities in Spanish with a classifier

  2011cites this paper
• A collocation based approach for prepositional phrase identification

  2011cites this paper
• Using graphical models for PP attachment

  2011influential citation
• Simple Semi-Supervised Learning for Prepositional Phrase Attachment

  2011cites this paper
• Automated Translation Machines: Challenges and a Proposed Solution

  2011cites this paper
• Statistical Parsing

  2011cites this paper
• Hat Categories: Representing Form and Function Simultaneously in Combinatory Categorial Grammar

  2010cites this paper
• How Bad is the Problem of PP-Attachment? A Comparison of English, German and Swedish

  2010cites this paper
• Integrating Parsing and Word Alignment in Syntax-Based Machine Translation

  2010cites this paper
• Syntactic Disambiguation by Learning Weighted Government Patterns from a Large Corpus

  2010cites this paper
• Low Resources Prepositional Phrase Attachment

  2010cites this paper
• A bi-threshold model for PP-attachment disambiguation through backing off to 2-tuples directly

  2009influential citation
• Data Analysis Project : Semi-Supervised Discovery of Named Entities and Relations from the Web

  2009cites this paper
• Semantic role labeling using lexicalized tree adjoining grammars

  2009cites this paper
• Automatic correction of grammatical errors in non-native English text

  2009cites this paper
• Natural language understanding in controlled virtual environments

  2009cites this paper
• Methodology for Designing Reasonably Expressive Mechanisms with Application to Ad Auctions

  2009cites this paper
• Prepositions in Applications: A Survey and Introduction to the Special Issue

  2009cites this paper
• Effects of prosodic and lexical constraints on parsing in young children (and adults).

  2008cites this paper
• Using Bilingual Chinese-English Word Alignments to Resolve PP-attachment Ambiguity in English

  2008cites this paper
• The Role of PP Attachment in Preposition Generation

  2008cites this paper
• On the use of natural language processing for automated conceptual data modeling

  2008cites this paper
• Algorithms for Information Retrieval and Natural Language Processing tasks

  2008cites this paper
• Grammar induction and PP attachment disambiguation

  2007influential citation
• Continuous Task-speciic Categories for Disambiguation: Putting Lexical Constraints (back) in the Lexicon

  2007influential citation
• Learning to parse and its implications for language acquisition

  2007cites this paper
• Sense Discriminative Patterns for Word Sense Disambiguation

  2007cites this paper
• Squibs: Prepositional Phrase Attachment without Oracles

  2007cites this paper
• Creating an Appropriate Corpus for PP Attachment Training

  2007influential citation
• Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models

  2007cites this paper
• FOR MUC-6 Breck

  2007cites this paper
• Memory-based Syntactic Processing Memory-based Syntactic Processing Background

  2007influential citation
• bcn Algorithms for Linguistic Processing

  2007cites this paper
• A Flexible Unsupervised PP-Attachment Method Using Semantic Information

  2007cites this paper
• Combining Dependency Parsing with PP Attachment

  2007cites this paper
• The development of interactive parsing : the role of prosody and lexical biases in children's (and adults') sentence processing

  2006cites this paper
• Evaluating State-of-the-Art Treebank-style Parsers for Coh-Metrix and Other Learning Technology Environments CHRISTIAN F. H EMPELMANN , V ASILE R US ,

  2006cites this paper
• The Effect of Corpus Size in Combining Supervised and Unsupervised Training for Disambiguation

  2006cites this paper
• Prepositional Phrase Attachment through Semantic Association using Connectionist Approach

  2006influential citation
• On The Duality of Semantics and Syntax The PP Attachment Case

  2006cites this paper
• The Notion of Argument in Prepositional Phrase Attachment

  2006cites this paper
• Phrasetable Smoothing for Statistical Machine Translation

  2006cites this paper
• Discriminative learning and spanning tree algorithms for dependency parsing

  2006cites this paper
• University of Pennsylvania: Description of the University of Pennsylvania System Used for MUC-6

  2005cites this paper
• The Notion of Argument in PP Attachment

  2005cites this paper
• Using the Web as an Implicit Training Set: Application to Structural Ambiguity Resolution

  2005influential citation
• PP-Attachment Disambiguation Boosted by a Gigantic Volume of Unambiguous Examples

  2005cites this paper
• Evaluating State-of-the-Art Treebank-style Parsers for Coh-Metrix and Other Learning Technology Environments

  2005cites this paper
• Latent Semantic Indexing as a Measure of Conceptual Association for the Unsupervised Resolution of Attachment Ambiguities

  2005influential citation
• Statistical models for case ambiguity resolution in Korean

  2005cites this paper