Linguistics
Browse by
Recent Submissions
-
Parallel Sentence Detection in Comparable Corpora with Bilingual Word Embeddings for Low-resource Languages
In an emergency, machine translation systems can be useful in facilitating international cooperation during rescue efforts. Unfortunately, training resources (bitexts) for many language pairs are scarce and tend to comprise ... -
Evidence for DP in Chinese from Reduplicative Classifiers and DP-Internal Information Structural Phenomena
This dissertation argues in favor of the Universal DP Hypothesis, which claims that all languages have DPs which contain extended functional projections above the NP, as opposed to the Parameterized DP Hypothesis, which ... -
Labeling and Automatically Identifying Basic-Level Categories
Basic-level categories are the primary categories humans use to think and communicate; they are the first categories learned, with numerous psychological advantages including quick exemplar recognition time. They are ... -
Polyglot Text Classification with Neural Document Models
Sometimes, annotating data for text classification is expensive, so one must rely on techniques like parameter sharing and semi-supervised learning to improve classification performance in low-resource environments. In ... -
Cross-Linguistic Acoustic Characteristics of Phonation: A Machine Learning Approach
Phonation, the process of producing a quasi-periodic sound wave through vocal fold vibration, plays different roles in different languages. Phonation types, or voice qualities, are produced by adjusting the length, thickness, ... -
Semantic Operations for Transfer-based Machine Translation
This dissertation describes a new approach to the automatic extraction of semantic mappings (transfer rules) for rule-based machine translation. This approach continues previous work in combining HPSG rule-based grammars, ... -
Modeling Adnominal Possession in the LinGO Grammar Matrix
This thesis describes the expansion of the LinGO Grammar Matrix customization system with a library handling adnominal possession. This library extends the Grammar Matrix's ability to aid in the rapid prototyping of precision ... -
A Generative-Discriminative Framework for Title Generation in the E-commerce Domain
Multi-Engine (system combination) Machine Translation (MEMT) systems produce several outputs which will then be refined to produce a higher quality translation output. In the case where source sentences are absent in the ... -
A Parametric Implementation of Valence-changing Morphology in the LinGO Grammar Matrix
This thesis describes an analysis of valence-changing verbal morphology implemented as a library extending the LinGO Grammar Matrix customization system. This analysis is based on decomposition of these operations into ... -
Non-Nominative Subjects in Russian and Lithuanian: Case, Argument Structure, and Anaphor Binding
In this dissertation, I aim to provide a comprehensive view of subjects in Russian and Lithuanian that have a morphological case other than nominative. Non-nominative subjects (NNSs) provide a window into the notion of ... -
An Evidentiality Library for the LinGO Grammar Matrix
This thesis describes a library extending the LinGO Grammar Matrix to support evidentiality. Evidentiality refers to the linguistic phenomenon where elements of a language’s grammar express the source of information for a ... -
Um and Uh, and the Expression of Stance in Conversational Speech
Um and uh are some of the most frequent items in spoken American and British English (Biber et al., 1999). They have been traditionally treated as disfluencies but recent research has focused on their discursive functions ... -
Dependency Parsing for Tweets
This thesis concentrates on the problem of dependency parsing for Twitter texts. Twitter texts, also called tweets, are a typical kind of web domain language with many informal and specific linguistic phenomena (Eisenstein, ... -
The Role of Morphology in Word Recognition of Hebrew as a Templatic Language
Research on recognition of complex words has primarily focused on affixational complexity in concatenative languages. This dissertation investigates both templatic and affixational complexity in Hebrew, a templatic language, ... -
Modeling the Perceptual Learning of Novel Dialect Features
All language use reflects the user's social identity in systematic ways. While humans can easily adapt to this sociolinguistic variation, automatic speech recognition (ASR) systems continue to struggle with it. This ... -
The semantic variability of the emphatic construction koso -e in Old Japanese
There is an interesting emphatic construction (called a koso –e construction) in Old Japanese, in which the focus particle koso concords with the exclamatory (-e) sentence ending form. When koso focuses on an irrealis/subjunctive ... -
Language maintenance and shift across generations in Inner Mongolia
Language shift happens when a group of people stops using one language in favor of another, such that subsequent generations no longer acquire the original language. Research on the sociolinguistics of language shift has ... -
Three Cheers For Partisanship: Lexical Framing and Applause in U.S. Presidential Primary Debates
Polarization in American politics is at its highest levels in recent history. This polarization can be observed not only in the behaviors of citizens and the politicians who represent them, but also in the rhetoric that ... -
Information Retrieval for Clinical Decision Support
Within the field of clinical support, access to relevant, peer-reviewed information from medical journals and other research publications is critical to making informed decisions regarding the diagnosis and care of patients. ... -
Submodular data selection in ASR language modeling
Given the vast amount of textual data that we have available today, it is very beneficial to have an efficient methodology to filter and select important and relevant chunks of this data to improve current natural language ...
RSS 1.0