Thesis (Ph. D.)--University of Texas at Austin, 2007. / Vita. Includes bibliographical references.

Thesis (M.S.)--University of Texas at Dallas, 2007. / Includes vita. Includes bibliographical references (leaves 81-84)

Thesis (Ph. D.)--University of Texas at Austin, 2006. / Vita. Includes bibliographical references.

Thesis (Ph.D.)--University of Texas at Dallas, 2007. / Includes vita. Includes bibliographical references (leaves 154-160)

In human-human dialogues, face-to-face meetings are often preferred over phone conversations.One explanation is that non-verbal modalities such as gesture provide additionalinformation, making communication more efficient and accurate. If so, computerprocessing of natural language could improve by attending to non-verbal modalitiesas well. We consider the problem of sentence segmentation, using hand-annotatedgesture features to improve recognition. We find that gesture features correlate wellwith sentence boundaries, but that these features improve the overall performance of alanguage-only system only marginally. This finding is in line with previous research onthis topic. We provide a regression analysis, revealing that for sentence boundarydetection, the gestural features are largely redundant with the language model andpause features. This suggests that gestural features can still be useful when speech recognition is inaccurate.

Social media users generate a large volume of data, which can contain meaningful and useful information. One such example is information about locations, which may be useful in applications such as marketing and security monitoring. There are two types of locations: location entities mentioned in the text of the messages and the physical locations of users. Extracting the first type of locations is not trivial because the location entities in the text are often ambiguous. In this thesis, we implement a sequential classification model with conditional random fields followed by a rule-based disambiguation model, we apply them to Twitter messages (tweets) and we show that they handle the ambiguous location entities in our dataset reasonably well. Only very few users disclose their physical locations; in order to automatically detect their locations, many approaches have been proposed using various types of information, including the tweets posted by the users. It is not easy to infer the original locations from text data, because text tends to be noisy, particularly in social media. Recently, deep learning techniques have been shown to reduce the error rate of many machine learning tasks, due to their ability to learn meaningful representations of input data. We investigate the potential of building a deep-learning architecture to infer the location of Twitter users based merely on their tweets. We find that stacked denoising auto-encoders are well suited for this task, with results comparable to state-of-the-art models. Finally, we combine the two models above with a third-party sentiment analysis tool and obtain a intelligent social media monitoring system. We show a demo of the system and that it is able to predict and visualize the locations and sentiments contained in a stream of tweets related to mobile phone brands - a typical real world e-business application.

Text classification is a wide research field with existing ready-to-use solutions for supervised training of text classifiers. The task of classifying short texts puts dif-ferent demands on the invoked learning system that general text classification does not. This thesis explores this challenge by experimenting on how to design the clas-sification system and what text features granted the best results. In the experimental study, a hierarchical versus a flat design was compared, along with different aspects of text features. The method consisted of training and testing on a dataset of 3.2 million samples in total. The test results were evaluated with the quality measures: precision, recall, F1-score and ROC analysis with a modification to target multi-class classification. The result of the experimental study was: 2-level hierarchical designed classifier gave better results than a flat designed classifier in 11 out of 13 occasions; integer represented terms outperformed TFIDF weighted terms of BOW features; lowercase conversion improved the classification results; bigram and tri-gram BOW features achieved better results than unigram BOW features. The results of the experimental study were used in a case study together with Thingmap, which maps natural language queries with users. The case study showed an improvement over earlier solutions of Thingmap’s system.

Recent innovations and progress in machine learning algorithms from the Natural Language Processing (NLP) community have motivated efforts to apply these models and concepts to proteins. The representations generated by trained NLP models have been shown to capture important semantic and structural understanding of proteins encompassing biochemical and biophysical properties, among other key concepts. In turn, these representations have demonstrated application to protein engineering tasks including mutation analysis and design of novel proteins. Here we use this NLP paradigm in a protein engineering effort to further red shift the emission wavelength of the red fluorescent protein mNeptune684 using only a small number of functional training variants ('Low-N' scenario). The collaborative nature of this thesis with the Department of Chemistry and Biomolecular Sciences explores using these tools and methods in the rational design process.

Submitted to the Health Informatics Graduate Program Faculty, Indiana University, in partial fulfillment of the requirements for the degree of Master of Science in Health Informatics.May 2006 / The purpose of this study is to examine the current use of natural language processing for extracting meaningful data from free text in medical reports. The use of natural language processing has been used to process information from various genres. To evaluate the use of natural language processing, a synthesized review of primary research papers specific to natural language processing and extracting data from medical reports. A three phased approach is used to describe the process of gathering the final metrics for validating the use of natural language processing. The main purpose of any NLP is to extract or understand human language and to process it into meaning for a specified area of interest or end-user. There are three types of approaches: symbolic, statistical, and connectionist. There are identified problems with natural language processing and the different approaches. Problems noted about natural language processing in the research are: acquisition, coverage, robustness, and extensibility. Metrics were gathered from primary research papers to evaluate the success of the natural language processors. Recall average of the four papers was 85%. Precision average of five papers was 87.7%. Accuracy average was 97%. Sensitivity average was 84%, while specificity was 97.4%. Based on the results of the primary research there was no definitive way to validate one NLP approach as an industry standard The research reviewed it is clear that there has been at least limited success with information extraction from free text with use of natural language processing. It is important to understand the continuum of data, information, and knowledge in the previous and future research of natural language processing. In the industry of health informatics this is a technology necessary for improving healthcare and research.

abstract: Question answering is a challenging problem and a long term goal of Artificial Intelligence. There are many approaches proposed to solve this problem, including end to end machine learning systems, Information Retrieval based approaches and Textual Entailment. Despite being popular, these methods find difficulty in solving problems that require multi level reasoning and combining independent pieces of knowledge, for example, a question like "What adaptation is necessary in intertidal ecosystems but not in reef ecosystems?'', requires the system to consider qualities, behaviour or features of an organism living in an intertidal ecosystem and compare with that of an organism in a reef ecosystem to find the answer. The proposed solution is to solve a genre of questions, which is questions based on "Adaptation, Variation and Behavior in Organisms", where there are various different independent sets of knowledge required for answering questions along with reasoning. This method is implemented using Answer Set Programming and Natural Language Inference (which is based on machine learning ) for finding which of the given options is more probable to be the answer by matching it with the knowledge base. To evaluate this approach, a dataset of questions and a knowledge base in the domain of "Adaptation, Variation and Behavior in Organisms" is created. / Dissertation/Thesis / Masters Thesis Computer Science 2019