Linguistics
Browse by
Recent Submissions
-
The Suitability of Generative Adversarial Training for BERT Natural Language Generation
This thesis presents a study that was designed to test the effect of generative adversarial network (GAN) training on the quality of natural language generation (NLG) using a pre-trained language model architecture: ... -
Dialogical Signals of Stance Taking in Spontaneous Conversation
This is one of the first computational studies to investigate dialogical aspects of stance taking in spontaneous, spoken dialogue with a focus on lexical similarities. In any dialogic inter- action, each speaker influences ... -
An Analysis of Gender Bias in K-12 Assigned Literature Through Comparison of Non-Contextual Word Embedding Models
Word embeddings are mathematical representations of words computed from a group of texts that a machine learning model is trained on. Generally, words that are similar to each othersemantically will be closer together ... -
Using External Knowledge to Improve Brown Clustering
In recent years, semi-supervised learning methods that rely on using low-dimensional word representation gained interest in NLP, due to their ability take advantage of vastly available unlabeled data and reduce dependence ... -
Explorations In Curriculum Learning Methods For Training Language Models
Understanding language depending on the context of its usage has always been one of thecore goals of natural language processing. Recently, contextual word representations created by language models like ELMo, BERT, ELECTRA, ... -
Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining
This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained ... -
Human-assisted Neural Machine Translation: Harnessing Human Feedback for Machine Translation
Neural machine translation (NMT) is a promising approach to the task of machine translation that has led to state-of-the-art results in many settings. However, NMT translations are still far from sufficient for many practical ... -
A Finite-State Morphological Analyzer for Central Alaskan Yup'ik
This thesis presents a detailed description of the design and implementation of a finite-state morphological analyzer for Central Alaskan Yup'ik (ISO 639-3: esu). Using a dictionary and a grammatical description of the ... -
Speech to Text to Semantics: A Sequence-to-Sequence System for Spoken Language Understanding
Spoken language understanding entails both the automatic transcription of a speech utterance and the identification of one or more semantic concepts being conveyed by the utterance. Traditionally these systems are domain ... -
The Acoustic Cues at Prosodic Boundaries in Mandarin
Prosodic boundary labeling is an important task not only for its direct application in speech synthesis but also for constructing speech corpora for speech synthesis. However, due to the lack of quantitive study on Mandarin ... -
Inferring Grammars from Interlinear Glossed Text: Extracting Typological and Lexical Properties for the Automatic Generation of HPSG Grammars
This dissertation presents a grammar inference system that leverages linguistic knowledge recorded in the form of annotations in interlinear glossed text (IGT) and in a meta-grammar engineering system (the LinGO Grammar ... -
Stylistic variation in African American Language: examining the social meaning of linguistic features in a Seattle community
Linguistic features associated with African American Language (AAL) may have a large set of ideological and functional meanings beyond ethnic identity. While sociolinguists know a lot, comparatively, about regional and ... -
The Language of Law: An Analysis of Gender and Turn-Taking in U.S. Supreme Court Oral Arguments
In this study, I present a corpus of short exchanges between speakers in U.S. Supreme Court Oral Arguments. Each exchange is labeled on a spectrum of “cooperative” to “competitive” by a human annotator with legal experience ... -
Old Stereotypes "Live Free or Die": Addressing the Evaluation Problem of non-rhoticity in New Hampshire
Recent research examining New Hampshire English has demonstrated that the traditional Eastern New England features are dissipating among New Hampshirites (Nagy, 2001; Labov, Ash, & Boberg, 2005; Nagy & Irwin, 2010; Stanford, ... -
On the Statistical Significance Testing for Natural Language Processing
This thesis explores and compares statistical significance tests frequently used in comparing Natural Language Processing (NLP) system performance in several aspects. We begin by establishing the fundamentals of the NLP ... -
Enriching Scientific Paper Embeddings with Citation Context
Amid profusion of scientific literature, methods to organize and search available papers are quite valuable. Embedded representations of papers have potential to be used as input to a variety of tasks related to research ... -
Braiding Language (by Computer): Lushootseed Grammar Engineering
This dissertation describes the beginnings of the t̕əbšucid project. t̕əbšucid, literally the braiding of language, is a way to refer to "grammar" in Lushootseed (also known as Puget Salish, ISO-639-3:lut). The t̕əbšucid ... -
Productivity, influence, and evolution: The complex language shift of Modern Ladino
This dissertation uses data from interviews with Seattle Ladino speakers, an online forum in Ladino, and documents from the University of Washington Sephardic Studies Collection to investigate the language shift that Modern ... -
Issues in Named Entity Recognition on Early Modern English Letters
The influx of digitized historical documents into online collections has made the study of these documents much more accessible to researchers and the general public. This data, however, is frequently raw data sometimes ... -
Verb-linking and Events in Syntax: The Case of Uyghur -(i)p Constructions
This dissertation explores the syntactic structures of Uyghur multi-verb constructions formed using the verb-linking -(i)p suffix. In such constructions, only the final verb is inflected for tense, and -(i)p attaches to ...
RSS 1.0