Work on prepositional phrase (PP) attachment resolution generally assumes that there is an oracle that provides the two hypothesized structures that we want to choose between. The information that there are two possible attachment sites and the information about the lexical heads of those phrases is usually extracted from gold-standard parse trees. We show that the performance of reattachment m...

We present several unsupervised statistical models for the prepositional phrase attachment task that approach the accuracy of the best supervised methods for this task. Our unsupervised approach uses a heuristic based on attachment proximity and trains from raw text that is annotated with only part-of-speech tags and morphological base forms, as opposed to attachment information. It is therefor...

This paper describes ongoing work, aimed at producing a lexicon of prepositions, i.e. relations denoted by prepositions, to be used for information retrieval purposes. The work is ontology based, which for this project means that the ontological types of the arguments of the preposition are considered, rather than the word forms. Thus, sense distinctions are made based on ontological constraint...

This document surveys the field of research in preposition phrase attachment resolution, looking back at the way the problem was approached in the 1990s, as well as at modern techniques for resolving this basic syntactic ambiguity problem. Techniques are described and compared, and their effectiveness is considered.

Prepositional phrases are a common source of ambiguity in natural language and many approaches have been devised to resolve this ambiguity automatically. In particular, several different machine learning approaches have now reached accuracy rates of around 84.5% on the benchmark dataset. Maximum entropy (maxent) models, despite their successful application in many other areas of natural languag...

This paper presents a detailed account of prepositional mismatch between our handcrafted verb lexicon and a semantically annotated corpus. The analysis of these mismatches allows us to re ne the lexicon and to create a more robust resource capable of better semantic predictions based on the verb-preposition relations.

In this paper interpretation principles for simple and complex frame-adverbial expressions are presented. Central to these principles is a distinction between p h a s e s and p e r i o d s together with the t e m p o r a l h i e rarchy , where multiple scales of time and relations can be expressed. A system, CLOCKWISE, has been implemented which interprets Swedish temporal expressions according...