Computational Linguistics Commons^™

G&P2p: A Multi-Source Approach To Grapheme To Phoneme Conversion, Chun-Yi Peng

Dissertations, Theses, and Capstone Projects

This thesis introduces G&P2P, a multi-source framework for grapheme-to-phoneme (G2P) conversion that integrates side pronunciations from multiple lexical resources. Unlike traditional single-source approaches, G&P2P fuses data from multi-sourced pronunciation dictionaries—including CELEX, PronLex, NETTalk, and WikiPron—through several fusion strategies. The goal is to improve model performance on out-of-vocabulary words through multi-source learning. Experiments were conducted with attentive LSTM, pointer-generator LSTM, and pointer-generator Transformer architectures. Models were trained on combinations of datasets and evaluated using word error rate (WER) across five random seeds.

Results show that fusing expert-curated dictionaries such as CELEX and PronLex consistently improves accuracy, achieving an 11.81-point absolute error …

A Machine Learning Approach To Disentangling Developmental Language Disorder From Typical Development In Russian-Speaking Children, Katsiaryna Aharodnik

Dissertations, Theses, and Capstone Projects

This study investigated a machine learning (ML) approach to identifying Developmental Language Disorder (DLD) in Russian-speaking children using narrative data. ML methods can capture subtle linguistic patterns that distinguish typical and atypical development, which is especially important in cross-linguistic contexts where morphosyntactic variation affects the manifestation of DLD. Diagnosis remains challenging in less-studied languages due to limited knowledge of language-specific deficits and a lack of validated assessment tools. This study evaluated whether ML algorithms can provide a more efficient alternative to traditional screening methods.

Two binary classification studies were conducted using corpus data: 1) classification of narratives told by Russian …

Mind The Gap: Morphological Defectivity And Suffixal Competition In Polish, Szymon E. Zuberek

Dissertations, Theses, and Capstone Projects

This study investigates morphological defectivity and suffixal competition in the genitive singular of Polish masculine inanimate nouns. Drawing on survey-based grammaticality judgments from native speakers, it examines how respondents select between the suffixes -a and -u or reject both as unacceptable, thereby signaling defectivity. Mixed-effects logistic regressions revealed that defectivity was rare overall but patterned systematically by age, education, and region, with additional baseline variability across lexical items. Suffix choice showed a strong preference for -a, modulated by age, education, and region, with additional baseline variability across lexical items. These findings inform our understanding of paradigm structure, sociolinguistic variation, and …

Alle Or Elle: Automatic Speech Recognition On Louisiana French, Emily Chiu

Dissertations, Theses, and Capstone Projects

Applications of automatic speech recognition largely serve the most commonly spoken languages, but can cause harm through bias when used for speakers of underrepresented language varieties who are not adequately supported. This experiment’s goal is to reveal how state-of-the-art end-to-end ASR systems perform with Louisiana French, a nonstandard variety of French that has suffered a history of state-sanctioned language oppression in Louisiana.

Improving Low-Resource Translation With Finite State Grammars, Nicholas J. Uva

Dissertations, Theses, and Capstone Projects

Scarcity of training data continues to pose a problem for the development of neural machine translation systems for low-resource languages. This study develops a method for the incorporation of linguistic information into the training of neural machine translation models for low-resource languages, using morphological grammars created using finite state transducers. This study explores the benefits, historical background, and effectiveness of this approach. This study incorporates morphological tags into a pre-trained multilingual neural machine translation model using a dual encoder structure. This study finds an improvement in performance in the Irish-English translation scenario. This method offers promising results with low computational …

Controlling Emotional Text To Speech Using Complex Adverbial Phrases, Zainab T. Akande

Dissertations, Theses, and Capstone Projects

This study investigates the usage of adverbial modifiers from audiobook data as a resource for training speech synthesizers with a greater range of speech descriptions. The Tacotron2 text-to-speech (TTS) model was used for the purposes of this study. Utilizing the LibriTTS dataset, the Tacotron2 model is trained under two experimental conditions: one incorporating adverbial modifiers into the input text and the other without. The dataset preprocessing involves embedding descriptions using word embeddings and encoding speaker IDs with machine learning techniques. Additionally, the model architecture includes a prosody encoder inspired by prior research. Evaluation of the trained models involves subjective assessments …

Uncovering The Mimicry Of Online Review Breadth And Depth And Its Subsequent Effect On Consumer Responses, Andrea Pelaez Martinez

Dissertations, Theses, and Capstone Projects

Word-of-mouth (WOM) in marketing occurs when consumers discuss a company's product or service or any consumption experience with their friends, family, and others with whom they have any relationship. With the advent of social media, this phenomenon has expanded rapidly into virtual environments where consumer conversation is enabled through chats, forums, social media posts, and online reviews. In response to this rapid growth of online WOM, academics and practitioners have focused their interest on this phenomenon and its implications on consumers, firms, and society. So far, the evidence of the critical role that online WOM plays in helping consumers make …

Computational Approaches To Linguistic Challenges In Arabic Speech Recognition, Enas Albasiri

Dissertations, Theses, and Capstone Projects

This dissertation aims to document the linguistic features of Arabic that pose challenges to speech and language technologies and advance these technologies by developing state-of-the-art computational tools focusing on automatic speech recognition (ASR), text normalization (TN), and corpus development. TN converts expressions such as numbers, dates, and times—named semiotic classes—from their written to their spoken domain, such as converting ‘$84.00’ to ‘eighty-four dollars’, while inverse text normalization (ITN) converts verbalized text to its written form. This conversion is an essential preprocessing step for text-to-speech (TTS), and post-processing step for ASR. Arabic presents a challenge for TN and ITN because one …

Expanding The Corpus Of Vocalized Hebrew Text: Compiling An Unvocalized Text Corpus And Building An Online Interface For Vocalization Annotation, Rachel Shanblatt Bloch

Dissertations, Theses, and Capstone Projects

Written modern Hebrew presents a unique challenge for training computational models for language processing because modern Hebrew text often lacks vocalization. The lack of available vocalized Hebrew data can lead to ambiguity in training these models and generally hinders work on natural language processing problems. The goal of this project is to contribute to the collection of vocalized Hebrew text by collecting and preprocessing a large corpus of unvocalized Hebrew text and building an online annotation tool. The annotation tool allows people to upload unvocalized Hebrew text, to annotate by adding Hebrew vocalization, and to download comma-separated values files of …

Consonant (De)Gradation In Ingrian?, Andrea M. Harrison

Dissertations, Theses, and Capstone Projects

This paper will present a dual method toward data enrichment for low-resource languages. Using Yoyodyne -- a Fairseq-inspired neural library for small-vocabulary sequence-to-sequence generation -- a morphological generation task was tested across labeled data encompassing multiple stages of enrichment for the low-resource language Ingrian. Due to limitations in the available data for Ingrian, weighted finite-state transducers (WFSTs) were used to generate an expanded vocabulary via HFST's toolkit for Uralic languages, and GiellaLT, a source for FST-driven lexica for low-resource languages. Further stages of experimentation used labeled data from related, higher-resource languages (Finnish, Estonian) to encourage cross-lingual transfer in the interest …

How Do We Learn What We Cannot Say?, Daniel Yakubov

Dissertations, Theses, and Capstone Projects

The contributions of this thesis are two-fold. First, this thesis presents UDTube, an easily usable software developed to perform morphological analysis in a multi-task fashion. This work shows the strong performance of UDTube versus the current state-of-the-art, UDPipe, across eight languages, primarily in the annotation of morphological features. The second contribution of this thesis is a exploration into the study of defectivity. UDTube is used to annotate a large amount of data in Greek and Russian which is ultimately used to investigate the plausibility of Indirect Negative Evidence (INE), a popular approach to the acquisition of morphological defectivity. The reported …

Towards Interpretable Machine Reading Comprehension With Mixed Effects Regression And Exploratory Prompt Analysis, Luca Del Signore

Dissertations, Theses, and Capstone Projects

We investigate the properties of natural language prompts that determine their difficulty in machine reading comprehension tasks. While much work has been done benchmarking language model performance at the task level, there is considerably less literature focused on how individual task items can contribute to interpretable evaluations of natural language understanding. Such work is essential to deepening our understanding of language models and ensuring their responsible use as a key tool in human machine communication. We perform an in depth mixed effects analysis on the behavior of three major generative language models, comparing their performance on a large reading comprehension …

Neural Network Vs. Rule-Based G2p: A Hybrid Approach To Stress Prediction And Related Vowel Reduction In Bulgarian, Maria Karamihaylova

Dissertations, Theses, and Capstone Projects

An effective grapheme-to-phoneme (G2P) conversion system is a critical element of speech synthesis. Rule-based systems were an early method for G2P conversion. In recent years, machine learning tools have been shown to outperform rule-based approaches in G2P tasks. We investigate neural network sequence-to-sequence modeling for the prediction of syllable stress and resulting vowel reductions in the Bulgarian language. We then develop a hybrid G2P approach which combines manually written grapheme-to-phoneme mapping rules with neural network-enabled syllable stress predictions by inserting stress markers in the predicted stress position of the transcription produced by the rule-based finite-state transducer. Finally, we apply vowel …

Evaluating Neural Networks As Cognitive Models For Learning Quasi-Regularities In Language, Xiaomeng Ma

Dissertations, Theses, and Capstone Projects

Many aspects of language can be categorized as quasi-regular: the relationship between the inputs and outputs is systematic but allows many exceptions. Common domains that contain quasi-regularity include morphological inflection and grapheme-phoneme mapping. How humans process quasi-regularity has been debated for decades. This thesis implemented modern neural network models, transformer models, on two tasks: English past tense inflection and Chinese character naming, to investigate how transformer models perform quasi-regularity tasks. This thesis focuses on investigating to what extent the models' performances can represent human behavior. The results show that the transformers' performance is very similar to human behavior in many …

Topics For He But Not For She: Quantifying And Classifying Gender Bias In The Media, Tyler J. Lanni

Dissertations, Theses, and Capstone Projects

In this study, we used computational techniques to analyze the language used in news articles to describe female and male politicians. Our corpus included 370 subtexts for male candidates and 374 subtexts for female candidates, gathered through the New York Times API. We conducted two experiments: an LDA topic analysis to explore the data, and a logistic regression to classify the subtexts as either male or female. Our analysis revealed some noteworthy findings that suggest the possibility of developing a gender bias classifier in the future. However, to create a more robust understanding of bias, additional research and data are …

Analysis Of The Inter-Annotators Agreement And Its Effect On The System Of Anti-Asian Hate Crime Detection On Twitter During Covid-19, Amir Toliyat

Dissertations, Theses, and Capstone Projects

Coronavirus disease 2019 (COVID-19) started in Wuhan, China, in late 2019, and after being utterly contagious in Asian countries, it rapidly spread to other countries. This disease caused governments worldwide to declare a public health crisis with severe measures taken to reduce the speed of the spread of the disease. This pandemic affected the lives of millions of people. Many citizens that lost their loved ones and jobs experienced a wide range of emotions, such as disbelief, shock, concerns about health, fear about food supplies, anxiety, and panic. All of the aforementioned phenomena led to the spread of racism and …

A Sentiment Analysis Of "Filipinx" On Twitter Using A Multinomial Naïve Bayes Classification Model, Clarisse Taboy

Dissertations, Theses, and Capstone Projects

On social media, the use of “Filipinx” as a gender neutral, inclusive term for “Filipino” tends to generate high user engagement, at times without regard for the original context in which the word appears. This project applies computational methods to collect a large dataset in English/Filipino from Twitter containing “Filipinx”, and to train a Naïve Bayes model to classify tweets into three sentiments: positive, neutral, and negative. My methodology takes inspiration from that of four related studies that similarly conducted sentiment analysis on English/Filipino tweets involving various topics, and whose resulting accuracy scores were compared side-by-side. Conducting sentiment analysis on …

Predicting Stress In Russian Using Modern Machine-Learning Tools, John Schriner

Dissertations, Theses, and Capstone Projects

In the Russian language, stress on a word is determined via often complex patterns and rules. In this paper, after examining nearly a century of research in stress rules and methods in Russian, we turn to see if modern machine learning tools can aid in predicting stress. Using A.A. Zaliznyak’s dictionary grammar and over 300,000 word forms, we derived stress codes to aid in predicting which syllable primary stress falls on. We trained an LSTM neural network on the data and conducted eight experiments with added features such as lemma, part of speech, and morphology. While the model performed better …

A Study Of Entrainment In Speech As A Possible Predictor Of Perceived Trust, Mariana Graterol Fuenmayor

Dissertations, Theses, and Capstone Projects

This thesis explores the possibility of using features of speech as possible predictors of perceived trust. It specifically focuses on entrainment, the tendency of participants in a conversation to unconsciously adapt their manner of talking to become more or less similar to each other. We compile a corpus of interviews conducted in English, with different levels of formality and discussing different topics. With it, we distribute a set of surveys to assess raters’ judgment of the participants, focusing on whether they believe the interviewee is trusted by their conversational partner, and whether they find the interlocutors themselves trustworthy. We also …

Towards Explaining Variation In Entrainment, Andreas Weise

Dissertations, Theses, and Capstone Projects

Entrainment refers to the tendency of human speakers to adapt to their interlocutors to become more similar to them. This affects various dimensions and occurs in many contexts, allowing for rich applications in human-computer interaction. However, it is not exhibited by every speaker in every conversation but varies widely across features, speakers, and contexts, hindering broad application. This variation, whose guiding principles are poorly understood even after decades of entrainment research, is the subject of this thesis. We begin with a comprehensive literature review that serves as the foundation of our own work and provides a reference to guide future …

From Sesame Street To Beyond: Multi-Domain Discourse Relation Classification With Pretrained Bert, Isaac R. Raff

Dissertations, Theses, and Capstone Projects

Research efforts in transfer learning have gained massive popularity in recent years. Pretrained language models have demonstrated the most successful results in producing high quality neural networks capable of quality inference after training across domains via transfer learning. This study expands on the domain transfer introduced in \cite{ferracane-etal-2019-news} exploring neural methods for transfer learning of discourse parsing between a news source domain and a medical target domain. \cite{ferracane-etal-2019-news} specifically discuss transfer learning from news articles to PubMed medical journal articles. Experiments in transfer learning in the current work expand to include three domains: Wall Street Journal articles previously annotated with …

Linguistic Abstractions In Children’S Very Early Utterances, Qihui Xu

Dissertations, Theses, and Capstone Projects

How early do children produce multiword utterances? Do children's early utterances reflect abstract syntactic knowledge or are they the result of data-driven learning? We examine this issue through corpus analysis, computational modeling, and adult simulation experiments. Chapter 1 investigates when children start producing multiword utterances; we use corpora to establish the development of multiword utterances and a probabilistic computational model to account for the quantitative change of early multiword utterances. We find that multiword utterances of different lengths appear early in acquisition and increase together, and the length growth pattern can be viewed as a probabilistic and dynamic process.

Chapter …

A Machine Learning Approach To Text-Based Sarcasm Detection, Lara I. Novic

Dissertations, Theses, and Capstone Projects

Sarcasm and indirect language are commonplace for humans to produce and recognize but difficult for machines to detect. While artificial intelligence can accurately analyze sentiment and emotion in speech and text, it may struggle with insincere and sardonic content, although it is possible to train a machine to identify uttered and written sarcasm. This paper aims to detect sarcasm using logistic regression and a support vector machine (SVM) and compare their results to a baseline.

The models are trained on headlines from a Kaggle dataset containing headlines from the satirical news website The Onion and serious news website Huffpost (formerly …

Covert Determiners In Appalachian English Narrative Declarative Sentences, William Oliver

Dissertations, Theses, and Capstone Projects

In this thesis, I explore the syntax and semantics of covert determiners (Ds) in matrix subject determiner phrases (DPs) with definite specific interpretations. To conduct my investigation, I used the Audio-Aligned and Parsed Corpus of Appalachian English (AAPCAppE), a million-word Penn Treebank corpus, and the software CorpusSearch, a Java program that searches Penn Treebank corpora. My research shows that Appalachian English contains a linguistic phenomenon where speakers drop the D, replacing overt Ds with covert Ds, in definite specific DPs. For example, where Standard English speakers say The doctor came by horseback, Appalachian speakers may use a covert D …

From An Art To A Science: Features And Methodology In Computational Authorship Identification, Jonathan I. Manczur

Dissertations, Theses, and Capstone Projects

Nearly thirty years ago, the United States Supreme Court revaluated the criteria for accepting forensic science and expert testimony, challenging Forensic Linguistics to assert itself as a reputable science. Much work has been produced in the interim to that end, but much still needs to be accomplished to satisfy the judicial standards. Computational linguistics has the potential to provide that necessary analytical framework. This paper’s intent is two-fold. First, there are two competing theories on the proper features necessary to identify an unknown author. Four features were drawn from the syntactic computational linguistics tradition and four from computational stylometry to …

Label Imputation For Homograph Disambiguation: Theoretical And Practical Approaches, Jennifer M. Seale

Dissertations, Theses, and Capstone Projects

This dissertation presents the first implementation of label imputation for the task of homograph disambiguation using 1) transcribed audio, and 2) parallel, or translated, corpora. For label imputation from parallel corpora, a hypothesis of interlingual alignment between homograph pronunciations and text word forms is developed and formalized. Both audio and parallel corpora label imputation techniques are tested empirically in experiments that compare homograph disambiguation model performance using: 1) hand-labeled training data, and 2) hand-labeled training data augmented with label-imputed data. Regularized, multinomial logistic regression and pre-trained ALBERT, BERT, and XLNet language models fine-tuned as token classifiers are developed for homograph …

Detection And Morphological Analysis Of Novel Russian Loanwords, Yulia Spektor

Dissertations, Theses, and Capstone Projects

This paper investigates recent English loanwords in Russian and explores ways in which computational methods can help further theoretical research. The goal of the study is two-fold: to find new, previously unattested loanwords borrowed over the last decade and to examine the rate of adaptation of the new borrowings, attested by the degree to which they conform to the constraints of the Russian language. First, we train a finite-state pipeline that combines character n-gram language models, which encode phonotactic and lexical properties of loanwords, with a binary classifier to detect loanwords. The model achieves state-of-the-art performance results during evaluation, surpassing …

Predicting Stock Price Movements Using Sentiment And Subjectivity Analyses, Andrew Kirby

Dissertations, Theses, and Capstone Projects

In a quick search online, one can find many tools which use information from news headlines to make predictions concerning the trajectory of a given stock. But what if we went further, looking instead into the text of the article, to extract this and other information? Here, the goal is to extract the sentence in which a stock ticker symbol is mentioned from a news article, then determine sentiment and subjectivity values from that sentence, and finally make a prediction on whether or not the value of that stock will go up or not in a 24-hour timespan. Bloomberg News …

The Public Innovations Explorer: A Geo-Spatial & Linked-Data Visualization Platform For Publicly Funded Innovation Research In The United States, Seth Schimmel

Dissertations, Theses, and Capstone Projects

The Public Innovations Explorer (https://sethsch.github.io/innovations-explorer/app/index.html) is a web-based tool created using Node.js, D3.js and Leaflet.js that can be used for investigating awards made by Federal agencies and departments participating in the Small Business Innovation Research (SBIR) and Small Business Technology Transfer (STTR) grant-making programs between 2008 and 2018. By geocoding the publicly available grants data from SBIR.gov, the Public Innovations Explorer allows users to identify companies performing publicly-funded innovative research in each congressional district and obtain dynamic district-level summaries of funding activity by agency and year. Applying spatial clustering techniques on districts' employment levels across major economic sectors provides users …

A Computational Study In The Detection Of English–Spanish Code-Switches, Yohamy C. Polanco

Dissertations, Theses, and Capstone Projects

Code-switching is the linguistic phenomenon where a multilingual person alternates between two or more languages in a conversation, whether that be spoken or written. This thesis studies the automatic detection of code-switching occurring specifically between English and Spanish in two corpora.

Twitter and other social media sites have provided an abundance of linguistic data that is available to researchers to perform countless experiments. Collecting the data is fairly easy if a study is on monolingual text, but if a study requires code-switched data, this becomes a complication as APIs only accept one language as a parameter. This thesis focuses on …