Computer Sciences Commons^™

Suggesting Missing Information In Text Documents, Grant Michael Hodgson

Theses and Dissertations

A key part of contract drafting involves thinking of issues that have not been addressedand adding language that will address the missing issues. To assist attorneys with this task, we present a pipeline approach for identifying missing information within a contract section. The pipeline takes a contract section as input and includes 1) identifying sections that are similar to the input section from a corpus of contract sections; and 2) identifying and suggesting information from the similar sections that are missing from the input section. By taking advantage of sentence embedding and principal component analysis, this approach suggests sentences that …

A Study Into The Feasibility Of Using Natural Language Processing And Machine Learning For The Identification Of Alcohol Misuse In Trauma Patients, Andrew Phillips

Master's Theses

Alcohol misuse is a leading cause of premature death in the United States, with nearly a third of trauma patients found to have elevated blood alcohol levels upon admission. However, timely intervention has been shown to reduce this. It is thus important to be able to quickly screen patients to identify alcohol misuse. Many medical centers use standardized questionnaires to identify alcohol misuse, but since these instruments are not usually a part of routine care, there are many cases where it is not done.

In this study, large quantities of notes were processed with natural language processing and machine learning …

Relation Extraction Via One-Shot Dependency Parsing On Intersentential, Higher-Order, And Nested Relations, Gözde Gül Şahi̇n, Erdem Emekli̇gi̇l, Seçi̇l Arslan, Onur Ağin, Gülşen Eryi̇ği̇t

Turkish Journal of Electrical Engineering and Computer Sciences

Despite the emergence of digitalization, people still interact with institutions via traditional means such as submitting free formatted petitions, orders, or applications. These noisy documents generally consist of complex relations that are nested, higher-order, and intersentential. Most of the current approaches address extraction of only sentence-level and binary relations from grammatically correct text and generally require high-level linguistic features coming from preprocessors such as a parts-of-speech tagger, chunker, or syntactic parser. In this article, we focus on extracting complex relations in order to automate the task of understanding user intentions. We propose a novel language-agnostic and noise-immune approach that does …

Implementing Universal Dependency, Morphology, And Multiword Expression Annotation Standards For Turkish Language Processing, Umut Sulubacak, Gülşen Eryi̇ği̇t

Turkish Journal of Electrical Engineering and Computer Sciences

Released only a year ago as the outputs of a research project (``Parsing Web 2.0 Sentences'', supported in part by a TÜBİTAK 1001 grant (No. 112E276) and a part of the ICT COST Action PARSEME (IC1207)), IMST and IWT are currently the most comprehensive Turkish dependency treebanks in the literature. This article introduces the final states of our treebanks, as well as a newly integrated hierarchical categorization of the multiheaded dependencies and their organization in an exclusive deep dependency layer in the treebanks. It also presents the adaptation of recent studies on standardizing multiword expression and named entity annotation schemes …

Choosing An Nlp Library For Analyzing Software Documentation: A Systematic Literature Review And A Series Of Experiments, Fouad N. A. Al Omran, Christoph Treude

Research Collection School Of Computing and Information Systems

To uncover interesting and actionable information from natural language documents authored by software developers, many researchers rely on "out-of-the-box" NLP libraries. However, software artifacts written in natural language are different from other textual documents due to the technical language used. In this paper, we first analyze the state of the art through a systematic literature review in which we find that only a small minority of papers justify their choice of an NLP library. We then report on a series of experiments in which we applied four state-of-the-art NLP libraries to publicly available software artifacts from three different sources. Our …

A Compare-Aggregate Model For Matching Text Sequences, Shuohang Wang, Jing Jiang

Research Collection School Of Computing and Information Systems

Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks. We particularly focus on the different comparison functions we can use to match two vectors. We use four different datasets to evaluate the model. We find that some simple comparison functions based on element-wise operations can work better than standard neural network and neural tensor network.

Tandem 2.0: Image And Text Data Generation Application, Christopher J. Vitale

Dissertations, Theses, and Capstone Projects

First created as part of the Digital Humanities Praxis course in the spring of 2012 at the CUNY Graduate Center, Tandem explores the generation of datasets comprised of text and image data by leveraging Optical Character Recognition (OCR), Natural Language Processing (NLP) and Computer Vision (CV). This project builds upon that earlier work in a new programming framework. While other developers and digital humanities scholars have created similar tools specifically geared toward NLP (e.g. Voyant-Tools), as well as algorithms for image processing and feature extraction on the CV side, Tandem explores the process of developing a more robust and user-friendly …

An Annotated Corpus With Nanomedicine And Pharmacokinetic Parameters, Nastassja Lewinski, Ivan Jimenez, Bridget Mcinnes

Chemical and Life Science Engineering Publications

A vast amount of data on nanomedicines is being generated and published, and natural language processing (NLP) approaches can automate the extraction of unstructured text-based data. Annotated corpora are a key resource for NLP and information extraction methods which employ machine learning. Although corpora are available for pharmaceuticals, resources for nanomedicines and nanotechnology are still limited. To foster nanotechnology text mining (NanoNLP) efforts, we have constructed a corpus of annotated drug product inserts taken from the US Food and Drug Administration’s Drugs@FDA online database. In this work, we present the development of the Engineered Nanomedicine Database corpus to support the …

Cse: U: Mixed-Initiative Personal Assistant Agents, Joshua W. Buck, Saverio Perugini, Tam Nguyen

Computer Science Faculty Publications

Specification and implementation of flexible human-computer dialogs is challenging because of the complexity involved in rendering the dialog responsive to a vast number of varied paths through which users might desire to complete the dialog. To address this problem, we developed a toolkit for modeling and implementing task-based, mixed-initiative dialogs based on metaphors from lambda calculus. Our toolkit can automatically operationalize a dialog that involves multiple prompts and/or sub-dialogs, given a high-level dialog specification of it. The use of natural language with the resulting dialogs makes the flexibility in communicating user utterances commensurate with that in dialog completion paths—an aspect …

Unsupervised Learning Of Allomorphs In Turkish, Burcu Can

Turkish Journal of Electrical Engineering and Computer Sciences

One morpheme may have several surface forms that correspond to allomorphs. In English, ed and $d$ are surface forms of the past tense morpheme, and $s$, es, and ies are surface forms of the plural or present tense morpheme. Turkish has a large number of allomorphs due to its morphophonemic processes. One morpheme can have tens of different surface forms in Turkish. This leads to a sparsity problem in natural language processing tasks in Turkish. Detection of allomorphs has not been studied much because of its difficulty. For example, tü and di are Turkish allomorphs (i.e. past tense morpheme), but …

Aspect-Based Helpfulness Prediction For Online Product Reviews, Yinfei Yang, Cen Chen, Forrest Sheng Bao

Research Collection School Of Computing and Information Systems

Product reviews greatly influence purchase decisions in online shopping. A common burden of online shopping is that consumers have to search for the right answers through massive reviews, especially on popular products. Hence, estimating and predicting the helpfulness of reviews become important tasks to directly improve shopping experience. In this paper, we propose a new approach to helpfulness prediction by leveraging aspect analysis of reviews. Our hypothesis is that a helpful review will cover many aspects of a product at different emphasis levels. The first step to tackle this problem is to extract proper aspects. Because related products share common …

Knowledge Modeling Of Phishing Emails, Courtney Falk

Open Access Dissertations

This dissertation investigates whether or not malicious phishing emails are detected better when a meaningful representation of the email bodies is available. The natural language processing theory of Ontological Semantics Technology is used for its ability to model the knowledge representation present in the email messages. Known good and phishing emails were analyzed and their meaning representations fed into machine learning binary classifiers. Unigram language models of the same emails were used as a baseline for comparing the performance of the meaningful data. The end results show how a binary classifier trained on meaningful data is better at detecting phishing …

A Framework For Collecting, Extracting And Managing Event Identity Information From Textual Content In Social Media, Debanjan Mahata

Theses and Dissertations

With the popularity of social media platforms such as Facebook, Twitter and Google Plus, there has been voluminous growth in the digital footprints of real-life events on the Internet. The user-generated colloquial and concise textual content related to different types of real-life events, available in these websites, acts as an extremely useful source for researchers and organizations for extracting valuable and insightful information. There has been significant improvement in natural language processing techniques for mining formal and long textual content commonly found in newspapers. It is still a challenging task to mine textual information from the social media channels producing …

Skewer: Sentiment Knowledge Extraction With Entity Recognition, Christopher James Wu

Master's Theses

The California state legislature introduces approximately 5,000 new bills each legislative session. While the legislative hearings are recorded on video, the recordings are not easily accessible to the public. The lack of official transcripts or summaries also increases the effort required to gain meaningful insight from those recordings. Therefore, the news media and the general population are largely oblivious to what transpires during legislative sessions.

Digital Democracy, a project started by the Cal Poly Institute for Advanced Technology and Public Policy, is an online platform created to bring transparency to the California legislature. It features a searchable database of state …

Categorizing Blog Spam, Brandon Bevans

Master's Theses

The internet has matured into the focal point of our era. Its ecosystem is vast, complex, and in many regards unaccounted for. One of the most prevalent aspects of the internet is spam. Similar to the rest of the internet, spam has evolved from simply meaning ‘unwanted emails’ to a blanket term that encompasses any unsolicited or illegitimate content that appears in the wide range of media that exists on the internet.

Many forms of spam permeate the internet, and spam architects continue to develop tools and methods to avoid detection. On the other side, cyber security engineers continue to …

Cest: City Event Summarization Using Twitter, Deepa Mallela

Computer Science Graduate Projects and Theses

Twitter, with 288 million active users, has become the most popular platform for continuous real-time discussions. This leads to huge amounts of information related to the real-world, which has attracted researchers from both academia and industry. Event detection on Twitter has gained attention as one of the most popular domains of interest within the research community. Unfortunately, existing event detection methodologies have yet to fully explore Twitter metadata and instead rely solely on identifying events based on prior information or focus on events that belong to specific categories. Given the heavy volume of tweets that discuss events, summarization techniques can …

A Comparative Approach To Question Answering Systems, Josue Balandrano Coronel

Theses and Dissertations

In this paper I will analyze three different algorithms and approaches to implement Question Answering Systems (QA-Systems). I will analyze the efficiency, strengths, and weaknesses of multiple algorithms by explaining them in detail and comparing them with each other. The overarching aim of this thesis is to explore ideas that can be used to create a truly open context QA-System. Open context QA-Systems remain an open problem.

The various algorithms and approaches presented in this work will be focused on complex questions. Complex questions are usually verbose and the context of the question is equally important to answer the query …

Grounding Robot Motion In Natural Language And Visual Perception, Scott Alan Bronikowski

Open Access Dissertations

The current state of the art in military and first responder ground robots involves heavy physical and cognitive burdens on the human operator while taking little to no advantage of the potential autonomy of robotic technology. The robots currently in use are rugged remote-controlled vehicles. Their interaction modalities, usually utilizing a game controller connected to a computer, require a dedicated operator who has limited capacity for other tasks.

I present research which aims to ease these burdens by incorporating multiple modes of robotic sensing into a system which allows humans to interact with robots through a natural-language interface. I conduct …

Evaluating Distributed Word Representations For Predicting Missing Words In Sentences, Saniya Saifee

Dissertations and Theses

In recent years, the distributed representation of words in vector space or word embeddings have become very popular as they have shown significant improvements in many statistical natural language processing (NLP) tasks as compared to traditional language models like Ngram. In this thesis, we explored various state-of-the-art methods like Latent Semantic Analysis, word2vec, and GloVe to learn the distributed representation of words. Their performance was compared based on the accuracy achieved when tasked with selecting the right missing word in the sentence, given five possible options. For this NLP task we trained each of these methods using a training corpus …

Challenges In Analyzing Software Documentation In Portuguese, Christoph Treude, Carlos A. Prolo, Fernando Figueira Filho

Research Collection School Of Computing and Information Systems

Many tools that automatically analyze, summarize, or transform software artifacts rely on natural language processing tooling for the interpretation of natural language text produced by software developers, such as documentation, code comments, commit messages, or bug reports. Processing natural language text produced by software developers is challenging because of unique characteristics not found in other texts, such as the presence of code terms and the systematic use of incomplete sentences. In addition, texts produced by Portuguese-speaking developers mix languages since many keywords and programming concepts are referred to by their English name. In this paper, we provide empirical insights into …

Enabling Real Time In-Situ Context Based Experimentation To Observe User Behaviour, Kartik Muralidaran

Dissertations and Theses Collection (Open Access)

Today’s mobile phones represent a rich and powerful computing platform, given their sensing, processing and communication capabilities. These devices are also part of the everyday life of millions of people, and coupled with the unprecedented access to personal context, make them the ideal tool for conducting behavioural experiments in an unobtrusive way. Transforming the mobile device from a mere observer of human context to an enabler of behavioural experiments however, requires not only providing experimenters access to the deep, near-real time human context (e.g., location, activity, group dynamics) but also exposing a disciplined scientific experimentation service that frees them from …

Extracting Development Tasks To Navigate Software Documentation, Christoph Treude, Martin P. Robillard, Barthélémy Dagenais

Research Collection School Of Computing and Information Systems

Knowledge management plays a central role in many software development organizations. While much of the important technical knowledge can be captured in documentation, there often exists a gap between the information needs of software developers and the documentation structure. To help developers navigate documentation, we developed a technique for automatically extracting tasks from software documentation by conceptualizing tasks as specific programming actions that have been described in the documentation. More than 70 percent of the tasks we extracted from the documentation of two projects were judged meaningful by at least one of two developers. We present TaskNavigator, a user interface …

Characterization Of Prose By Rhetorical Structure For Machine Learning Classification, James Java

CCAC Theses and Dissertations

Measures of classical rhetorical structure in text can improve accuracy in certain types of stylistic classification tasks such as authorship attribution. This research augments the relatively scarce work in the automated identification of rhetorical figures and uses the resulting statistics to characterize an author's rhetorical style. These characterizations of style can then become part of the feature set of various classification models.

Our Rhetorica software identifies 14 classical rhetorical figures in free English text, with generally good precision and recall, and provides summary measures to use in descriptive or classification tasks. Classification models trained on Rhetorica's rhetorical measures paired with …

Temporal Logic Extension For Self-Referring, Nonexistence, Multiple Recurrence, And Anterior Past Events, Şadi̇ Evren Şeker

Turkish Journal of Electrical Engineering and Computer Sciences

This study focuses on the possible extensions of current temporal logics. In this study, 4 extensions are proposed: self-referring events, nonexisting events, multiple recurrence of events, and an improvement on anterior past events. Each of these extensions is on a different level of temporal logics. The main motivation behind the extensions is the temporal analysis of Turkish. Similar to temporal logic studies built on other natural languages, like French, Ukrainian, Italian, Korean, English, or Romanian, this is the first time that the Turkish language has been deeply questioned in the sense of computable temporal logic using the view of a …

The Application Of P-Bar Theory In Transformation-Based Error-Driven Learning, Bryant Harold Walley

Master's Theses

In P-bar Theory, Perkins et al. (2014) proposed a rule based method for determining the context of a partext (i.e., a part of a text document).

In Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging Brill (1995) demonstrates a method of error-driven learning applied to individual words at the sentence level to determine the part of speech each word represents.

We combine these two concepts providing a transformation-based error-driven learning algorithm to improve the results obtained from the static rules Perkins proposed and determine if the rule order prediction will provide additional metadata.

Systematic Comparison Of Cross-Lingual Projection Techniques For Low-Density Nlp Under Strict Resource Constraints, Joshua Waxman

Dissertations, Theses, and Capstone Projects

The field of low-density NLP is often approached from an engineering perspective, and evaluations are typically haphazard - considering different architectures, given different languages, and different available resources - without a systematic comparison. The resulting architectures are then tested on the unique corpus and language for which this approach has been designed. This makes it difficult to truly evaluate which approach is truly the "best," or which approaches are best for a given language.

In this dissertation, several state-of-the-art architectures and approaches to low-density language Part-Of-Speech Tagging are reimplemented; all of these techniques exploit a relationship between a high-density (HD) …

Compositional Vector Space Models For Improved Bug Localization, Shaowei Wang, David Lo, Julia Lawall

Research Collection School Of Computing and Information Systems

Software developers and maintainers often need to locate code units responsible for a particular bug. A number of Information Retrieval (IR) techniques have been proposed to map natural language bug descriptions to the associated code units. The vector space model (VSM) with the standard tf-idf weighting scheme (VSMnatural), has been shown to outperform nine other state-of-the-art IR techniques. However, there are multiple VSM variants with different weighting schemes, and their relative performance differs for different software systems. Based on this observation, we propose to compose various VSM variants, modelling their composition as an optimization problem. We propose a genetic algorithm …

Opinion Mining Of Sociopolitical Comments From Social Media, Swapna Gottipati

Dissertations and Theses Collection (Open Access)

Opinions are central to almost all human activities by influencing greatly the decision making process. In this thesis, we present the problems of mining issues, extracting entities and suggestive opinions towards the entities, detecting thoughtful comments, and extracting stances and ideological expressions from online comments in the sociopolitical domain. This study is essential for opinion mining applications that are beneficial for policy makers, government sectors and social organizations. Much work has been done to try to uncover consumer sentiments from online comments to help businesses improve their products and services. However, sociopolitical opinion mining poses new challenges due to complex …

“Time For Some Traffic Problems”: Enhancing E-Discovery And Big Data Processing Tools With Linguistic Methods For Deception Detection, Erin S. Crabb

Journal of Digital Forensics, Security and Law

Linguistic deception theory provides methods to discover potentially deceptive texts to make them accessible to clerical review. This paper proposes the integration of these linguistic methods with traditional e-discovery techniques to identify deceptive texts within a given author’s larger body of written work, such as their sent email box. First, a set of linguistic features associated with deception are identified and a prototype classifier is constructed to analyze texts and describe the features’ distributions, while avoiding topic-specific features to improve recall of relevant documents. The tool is then applied to a portion of the Enron Email Dataset to illustrate how …

What You Want Is Not What You Get: Predicting Sharing Policies For Text-Based Content On Facebook, Arunesh Sinha, Li Yan, Lujo Bauer

Research Collection Lee Kong Chian School Of Business

As the amount of content users publish on social networking sites rises, so do the danger and costs of inadvertently sharing content with an unintended audience. Studies repeatedly show that users frequently misconfigure their policies or misunderstand the privacy features offered by social networks. A way to mitigate these problems is to develop automated tools to assist users in correctly setting their policy. This paper explores the viability of one such approach: we examine the extent to which machine learning can be used to deduce users' sharing preferences for content posted on Facebook. To generate data on which to evaluate …