Adriane Boyd

Discontinuity Revisited: An Improved Conversion to Context-Free Representations

This paper introduces a new, reversible method for converting syntactic structures with discontinuous constituents into traditional syntax trees. The method is applied to the Tiger Corpus of German and results for PCFG parsing requiring such context-free trees are provided. A labeled dependency evaluation shows that the new conversion method leads to better results by preserving local relationships and introducing fewer inconsistencies into the training data.

Identifying Non-Referential it: A Machine Learning Approach Incorporating Linguistically Motivated Patterns

In this paper, we present a machine learning system for identifying non-referential it. Types of non-referential it are examined to determine relevant linguistic patterns. The patterns are incorporated as features in a machine learning system which performs a binary classification of it as referential or non-referential in a POS-tagged corpus. The selection of relevant, generalized patterns leads to a significant improvement in performance.

Revisiting the Impact of Different Annotation Schemes on PCFG Parsing: A Grammatical Dependency Evaluation

Recent parsing research has started addressing the questions a) how parsers trained on different syntactic resources differ in their performance and b) how to conduct a meaningful evaluation of the parsing results across such a range of syntactic representations. Two German treebanks, Negra and TuBa-D/Z, constitute an interesting testing ground for such research given that the two treebanks make very different representational choices for this language, which also is of general interest given that German is situated between the extremes of fixed and free word order. We show that previous work comparing PCFG parsing with these two treebanks employed PARSEVAL and grammatical function comparisons which were skewed by differences between the two corpus annotation schemes. Focusing on the grammatical dependency triples as an essential dimension of comparison, we show that the two very distinct corpora result in comparable parsing performance.

Pronunciation Modeling in Spelling Correction for Writers of English as a Foreign Language

We propose a method for modeling pronunciation variation in the context of spell checking for non-native writers of English. Spell checkers, typically developed for native speakers, fail to address many of the types of spelling errors peculiar to non-native speakers, especially those errors influenced by differences in phonology. Our model of pronunciation variation is used to extend a pronouncing dictionary for use in the spelling correction algorithm developed by Toutanova and Moore (2002), which includes models for both orthography and pronunciation. The pronunciation variation modeling is shown to improve performance for misspellings produced by Japanese writers of English.