• Leveraging Training Data from High-Resource Languages to Improve Dependency Parsing for Low-Resource Languages 

  Jaja, Claire

  Dependency parsing is an important natural language processing (NLP) task with many downstream applications, and as is common in the field, high accuracy results can be obtained when using statistical methods and training ...
• Extracting Topically Related Synonyms from Twitter using Syntactic and Paraphrase Data 

  Antoniak, Maria Alexandra

  The goal of synonym extraction is to automatically gather synsets (groups of synonyms) from a corpus. This task is related to the tasks of normalization and paraphrase detection. We present a series of approaches for synonym ...
• Adjectives in the LinGO Grammar Matrix 

  Trimble, Thomas James

  The LinGO Grammar Matrix (Bender et al. 2002, 2010) provides a system for user-linguists to jump start the creation of starter Head-driven Phrase Structure Grammar precision grammars (Pollard and Sag 1994), with semantic ...
• Detection of Agreement and Disagreement: An investigation of linguistic coordination and conversational features 

  Alexandropoulou, Maria

  The focus of this thesis is detection of agreement and disagreement in multiparty conversations using existing transcripts from the ICSI corpus. We use an unsupervised lexicon-based method to create our baseline and then ...
• Automated Grammar Engineering for Verbal Morphology 

  Wax, David Allen (2014-04-30)

  This study examines the cross-linguistic potential for the automatic analysis of verbal morphology and creation of implemented formal grammars using the Grammar Matrix customization system and the rich linguistic resource ...
• A Grammar Library for Information Structure 

  Song, Sanghoun (2014-04-30)

  This dissertation makes substantial contributions to both the theoretical and computational treatment of information structure, with an eye toward creating natural language processing applications such as multilingual ...
• An Independent Assessment of Phonetic Distinctive Feature Sets used to Model Pronunciation Variation 

  Rolston, Leanne Elizabeth (2014-04-30)

  It has been consistently shown that Automatic Speech Recognition (ASR) performance on casual, spontaneous speech is much worse than on carefully planned or read speech by as much as double the word error rate, and that ...
• Comparative Analysis of DeepBank and the Penn Treebank 

  Schneider, Megan (2014-02-24)

  I examined the differences between the DeepBank and Penn Treebank and the effect of hand-created and grammar-derived annotations on dependency representations. The dependencies comparison involved transforming the DeepBank ...
• Investigation of sentence structure in domain adaptation for sentiment classification 

  Gentile, Anthony (2014-02-24)

  A popular use case of computational linguistics is the identification of sentiment in text. Many current methods for sentiment classification focus on word features within sentences of a text. These methods employ different ...
• The Semantics of Implicitly Relational Predicates 

  McCloy, Daniel Robert (2014-01-27)

  This thesis offers a semantic account of implicitly relational predicates — adjectival or nominal predicates such as to be popular and to be a wanted man. Implicitly relational predicates are characterized by unique ...
• Counterfactuals in Context: Felicity conditions for counterfactual conditionals containing proper names 

  Robinson, William Stephen (2013-11-14)

  This thesis provides felicity conditions for counterfactual conditionals containing proper names in which essential changes to an individual are counterfactually posited using contrastive focus in either the antecedent or ...
• Detecting Adverse Events in Clinical Trial Free Text 

  Lingren, Todd Gregory (2013-11-14)

  <bold>Introduction:</bold> In pharmacotherapy cancer clinical trials patients receive frequent outpatient evaluation and monthly inpatient evaluation, as required by the protocol or institutional guidelines. Detection of ...
• Prosody, intelligibility and familiarity in speech perception 

  McCloy, Daniel Robert (2013-07-25)

  This thesis concerns the relationship between speech intelligibility and speech prosody, and the role that speech prosody plays in the perceptual advantage that occurs when listening to a familiar talker. A parallel corpus ...
• Learning Board Game Rules from an Instruction Manual 

  Mills, Chad (2013-07-25)

  Board game rulebooks offer a convenient scenario for extracting a systematic logical structure from a passage of text since the mechanisms by which board game pieces interact must be fully specified in the rulebook and ...
• Markers of contrast in Russian: A corpus-based study 

  Gracheva, Varya (2013-07-25)

  Markers of contrast in Russian: A corpus-based study
• Using Lexical and Compositional Semantics to Improve HPSG Parse Selection 

  Pozen, Zinaida (2013-07-25)

  Accurate parse ranking is essential for deep linguistic processing applications and is one of the classic problems for academic research in NLP. Despite significant advances, there remains a big need for improvement, ...
• The Phonetics of Tone in Two Dialects of Dane-zaa (Athabaskan) 

  Miller, Julia Colleen (2013-07-25)

  This dissertation is an investigation of acoustic properties of lexical tone in two dialects of Dane-zaa (Athabaskan). The noteworthy mirror-image tone systems of the H-marked Doig and L-marked Halfway dialects provide a ...
• Loanwords, prominence and the basis for Mongolian vowel harmony 

  Puthuval, Sarala (2013-07-25)

  The standard analysis of Modern Mongolian vowel harmony is as rightward spreading of the features [pharyngeal] and [round] starting from the first syllable of the word. Because Mongolian has exclusively suffixing morphology ...
• The Syntactic Exponence of Sentential Negation: a model for the LinGO Grammar Matrix 

  Crowgey, Joshua David (2013-04-17)

  This thesis presents a revision of the LinGO Grammar Matrix library for sentential negation along with supporting arguments from syntactic and typological literature. A cross-linguistic model of representations in HPSG ...
• Unsupervised Morphological Word Clustering 

  Lushtak, Sergei A. (2013-04-17)

  This thesis describes a system which clusters the words of a given lexicon into conflation sets (sets of morphologically related words). The word clustering is based on clustering of suffixes, which, in turn, is based on ...

View more