169 research outputs found
Performing Gender: Automatic Stylistic Analysis of Shakespeare's Characters
No full texthotasob @ iit.edu, argamon @ iit.edu koppel @ cs.biu.ac.il, iriszigdon @ walla.co
PAN11 Author Identification: Attribution
No full textWe provide you with a training corpus that comprises several different common attribution and verification scenarios. There are five training collections consisting of real-world texts (for authorship attribution), and three each with a single author (for authorship verification)
AUTOMATIC SUMMARIZATION OF CLINICAL ABSTRACTS FOR EVIDENCE-BASED MEDICINE
No full textThe practice of evidence-based medicine (EBM) encourages health professionals to make informed treatment decisions based on a careful analysis of current research. However, after caring for their patients, medical practitioners have little time to spend reading even a small fraction of the rapidly growing body of medical research literature. As a result, physicians must often rely on potentially outdated knowledge acquired in medical school. Systematic reviews of the literature exist for speci c clinical questions, but these must be manually created and updated as new research is published. Abstracts from well-written clinical research papers contain key information regarding the design and results of clinical trials. Unfortunately, the free text nature of abstracts makes it di cult for computer systems to use and time consuming for humans to read. I present a software system that reads abstracts from randomized controlled trials, extracts key clinical entities, computes the e ectiveness of the proposed interventions and compiles this information into machine readable and human readable summaries. This system uses machine learning and natural language processing techniques to extract the key clinical information describing the trial and its results. It extracts the names and sizes of treatment groups, population demographics, outcome measured in the trial and outcome results for each treatment group. Using the extracted outcome measurements, the system calculates key summary measures used by physicians when evaluating the e ectiveness of treatments. It computes absolute risk reduction (ARR) and number needed to treat (NNT) values complete with con dence intervals. The extracted information and computed statistics are automatically compiled into XML and HTML summaries that describe the details and results of the trial. xiii Extracting the necessary information needed to calculate these measures is not trivial. While there have been various approaches to generating summaries of medical research, this work has mostly focused on extracting trial characteristics (e.g. population demographics, intervention/outcome information). No one has attempted to extract all of the information needed, nor has anyone attempted to solve many of the tasks needed to reliably calculate the summary statistics.PH.D in Computer Science, December 201
Methods for Genre Analysis Applied to Formal Scientific Writing
No full textGenre and its relation to textual style has long been studied, but only recently has it been a candidate for computational analysis. In this paper, we apply computational stylistics techniques to the study of genre, which allows us to analyze large amounts of text efficiently. Such techniques enable us to compare rhetorical styles between different genres; in particular, we are studying the communication of scientists through their publications in peer-reviewed journals. Our work examines possible genre/stylistic distinctions between articles in different fields of science, and seeks to relate them to methodological differences between the fields. We follow Cleland’s (2002) work in this area and divide the sciences broadly into Experimental and Historical sciences. According to this and other work in the philosophy of science, Experimental science attempts to formulate general predictive laws, and so relies on repeatable series of controlled experiments that test specific hypotheses (Diamond 2002), whereas Historical science deals more with contingent phenomena (Mayr 1976), studying unique events in the past in an attempt to find unifying explanations for their effects. We consider the four fundamental dimensions outlined by Diamond (2002, pp. 420-424): 1. Is the goal of the research to find general laws or statements or ultimate (and contingent) causes? DIGITAL HUMANITIES 2006 2. Is evidence gathered by manipulation or by observation? 3. Is research quality measured by accurate prediction or effective explanation? 4. Are the objects of study uniform entities (which are interchangeable) or are they complex entities (which are ultimately unique)? The present experiment was designed to see if language features support these philosophical points. These linguistic features should be topic independent and representative of the underlying methodology; we are seeking textual clues to the actual techniques used by the writers of these scientific papers. This paper is partially based on our previously presented results (Argamon
SENTIMENT ANALYSIS BASED ON APPRAISAL THEORY AND FUNCTIONAL LOCAL GRAMMARS
No full textMuch of the past work in structured sentiment extraction has been evaluated in ways that summarize the output of a sentiment extraction technique for a particular application. In order to get a true picture of how accurate a sentiment extraction system is, however, it is important to see how well it performs at nding individual mentions of opinions in a corpus. Past work also focuses heavily on mining opinion/product-feature pairs from product review corpora, which has lead to sentiment extraction systems assuming that the documents they operate on are review-like | that each document concerns only one topic, that there are lots of reviews on a particular product, and that the product features of interest are frequently recurring phrases. Based on existing linguistics research, this dissertation introduces the concept of an appraisal expression, the basic grammatical unit by which an opinion is expressed about a target. The IIT sentiment corpus, intended to present an alternative to both of these assumptions that have pervaded sentiment analysis research, consists of blog posts annotated with appraisal expressions to enable the evaluation of how well sentiment analysis systems nd individual appraisal expressions. This dissertation introduces FLAG, an automated system for extracting appraisal expressions. FLAG operates using a three step process: (1) identifying attitude groups using a lexicon-based shallow parser, (2) identifying potential structures for the rest of the appraisal expression by identifying patterns in a sentence's dependency parse tree, (3) selecting the best appraisal expression for each attitude group using a discriminative reranker. FLAG achieves an overall accuracy of 0.261 F1 at identifying appraisal expressions, which is good considering the difficulty of the task.Ph.D. in Computer Science, December 201
REVEALING LINGUISTIC BIAS
No full textReaders currently face bias in articles written by writers who focus more on partiality towards any person or organization than showing the real facts. The study aims to detect and reveal such bias against them and try to portray real facts without any partiality against any person or organization. The data is fetched by selecting various articles from Google, especially those containing some bias in them. The bias was checked by measuring the subjectivity and polarity of the article using multiple libraries such as NLTK etc. We created a google form to take readers’ views showing them randomly either the biased article or the improved article after changing bias and getting their opinions
Towards Assisting Human-Human Conversations
No full textThe idea of the research is to understand the open-topic conversations and ways to provide assistance to humans who face difficulties in initiating conversations and overcome social anxiety so as to be able to talk and have successful conversations. By providing humans with assistive conversational support, we can augment the conversation that can be carried out. The AdvisorBot can also help to reduce the time taken to type and convey the message if the AdvisorBot is context aware and capable of providing good responses.There has been a significant research for creating conversational chatbots in open-domain conversations that have claimed to have passed the Turing Test and can converse with humans while not seeming like a bot. However, if these chatbots can converse like humans, can they provide actual assistance in human conversations? This research study observes and improves the advanced open-domain conversational chatbots that are put in practice for providing conversational assistance.While performing this thesis research, the chatbots were deployed to provide conversational assistance and a human study was performed to identify and improve the ways to tackle social anxiety by connecting strangers to perform conversations that would be aided by AdvisorBot. Through the questionnaires that the research subjects filled during their participation, and by performing linguistic analysis, the quality of the AdvisorBot can be improved so that humans can achieve better conversational skills and are able to clearly convey their message while conversing. The results were further enhanced by using transfer learning techniques and quickly improve the quality of the AdvisorBot
Identification of Sensitive Unclassified Information
No full textSensitive Unclassified information is defined as any unclassified information that may cause adverse consequences against the government facilities. In this chapter, we explore the use of categorization techniques and information extraction to discover this kind of information in scanned documents.
We show here that the combined use of a K-Dependence Bayesian categorization engine and a semi-automated review application reduce by nearly 95% the number of man hours required to redact sensitive unclassified information. We also discuss and provide statistics on how OCR errors can affect the information extraction tasks
N-grams et identification des auteurs
No full textCes derniers temps, les études dans le domaine de l'authorship attribution ou de la classification des textes ont pris un souffle nouveau par le biais de l'utilisation de n-grams ((Voir notamment V. Kešelj, F. Peng, N. Cercone et C. Thomas, « N-gram-based author profiles for authorship attribution », in Proceedings of the Conference Pacific Association for Computational Linguistics, PACLING, 2003, 3, p. 255–264 [en ligne] ; voir également les synthèses proposées dans Shlomo Argamon, Moshe Ko..
The whys and wherefores for studying textual genre computationally
No full textThis brief paper gives an example of statistical stylistic experimentation and argues for more informed measures of variation and choice and more informed measures of readership analysis to be able to posit dimensions of textual variation usefully.Published in Style and Meaning in Language, Art, Music, and Design: Papers from the AAAI Fall Symposium. Eds. Shlomo Argamon, Shlomo Dubnov, and Julie Jupp. AAAI Technical Report Series FS-04-08. Menlo Park: AAAI Press,ISBN 978-1-57735-218-1</p
- …
