In this paper, the authors discuss research on whether they can use Mechanical Turk (MTurk) to acquire good annotations with respect to gold-standard data, whether they can filter out low-quality workers (spammers), and whether there is a learning effect associated with repeatedly completing the same kind of task.

This paper discusses enhancing the undergraduate research experience in a senior design context.

This paper presents a methodology to extract positive interpretations from negated statements.

This paper discusses explorations in automatic book summarization.

This paper analyzes the topic identification stage of single-document automatic text summarization across four different domains, consisting of newswire, literary, scientific and legal documents.

This paper discusses measuring the semantic similarity of texts.

This paper discusses linguistically motivated features for enhanced back-of-the-book indexing.

This paper proposes a new shared task on grading student answers with the goal of enabling well-targeted and flexible feedback in a tutorial dialogue setting.

This paper presents the results of the Joint Student Response Analysis and 8th Recognizing Textual Entailment Challenge, aiming to bring together researchers in educational NLP technology and textual entailment.

This paper discusses Tantra. Tantra is a novel Pseudorandom number generator (PRNG) design that provides a long sequence high quality pseudorandom numbers at very high rate both in software and hardware implementations.

This paper describes the University of North Texas SubFinder system. The system is able to provide the most likely set of substitutes for a word in a given context, by combining several techniques and knowledge sources. SubFinder has successfully participated in the best and out of ten (oot) tracks in the SEMEVAL lexical substitution task, consistently ranking in the first or second place.

This paper shows results from an investigation whether a classifier can be taught to identify these constructions and consideration of the hypothesis that identifying construction types can improve the semantic interpretation of previously unseen predicate uses.

This paper discusses efforts to attract and retain students in computer science and engineering fields.

This paper describes the use of a content analysis with the lens of information architecture to better understand how research data services are organize in North American academic library websites, and to what extent the research data lifecycle is supported within these services.

This paper presents the task definition, resources, participating systems, and comparative results for the shared task on word alignment which was organized as part of the Association for Computational Linguistics (ACL) 2005 Workshop on Building and Using Parallel Texts. The shared task included English-Inuktitut, Romanian-English, and English-Hindi sub-tasks, and drew the participation of ten teams from around the world with a total of 50 systems.

This paper describes an automatic question generator that uses semantic pattern recognition to create questions of varying depth and type for self-study or tutoring.

This paper describes SenseLearner, a minimally supervised word sense disambiguation system that attempts to disambiguate all content words in a text using WordNet senses.

This paper discusses automatic generation of a coarse grained WordNet.

This paper discusses eXtended WordNet.

This paper discusses a method for word sense disambiguation of unrestricted text.

This paper discusses learning multilingual subjective language via cross-lingual projections.

This paper discusses combining SenseLearner with SuperSence and other coarse semantic features.

This paper describes on-going efforts to annotate a corpus of almost 16,000 answer pairs with an estimated 69,000 fine-grained entailment relationships.

This paper presents a domain-independent technique for assessing learners' constructed responses.