UNT Scholarly Works - 171 Matching Results
Search Results
- Using Encyclopedic Knowledge for Automatic Topic Identification
- This paper presents a method for automatic topic identification using an encyclopedic graph derived from Wikipedia. The system is found to exceed the performance of previously proposed machine learning algorithms for topic identification, with an annotation consistency comparable to human annotations.
- Open Text Semantic Parsing Using FrameNet and WordNet
- This article discusses open text semantic parsing using FrameNet and WordNet.
- Using Wikipedia for Automatic Word Sense Disambiguation
- This paper describes a method for generating sense-tagged data using Wikipedia as a source of sense annotations. Through word sense disambiguation experiments, the authors show that the Wikipedia-based sense annotations are reliable and can be used to construct accurate sense classifiers.
- Unsupervised Graph-based Word Sense Disambiguation Using Measures of Word Semantic Similarity
- This paper describes an unsupervised graph-based method for word sense disambiguation, and presents comparative evaluations using several measures of word semantic similarity and several algorithms for graph centrality. The results indicate that the right combination of similarity metrics and graph centrality algorithms can lead to a performance competing with the state-of-the-art in unsupervised word sense disambiguation, as measured on standard data sets.
- Random-Walk Term Weighting for Improved Text Classification
- This paper describes a new approach for estimating term weights in a document, and shows how the new weighting scheme can be used to improve the accuracy of a text classifier.
- A Language Independent Algorithm for Single and Multiple Document Summarization
- This paper discusses a language independent algorithm for single and multiple document summarization.
- Of Men, Women, and Computers: Data-Driven Gender Modeling for Improved User Interfaces
- This paper discusses data-driven gender modeling for improved user interfaces.
- Multilingual Subjectivity: Are More Languages Better?
- This paper discusses multilingual subjectivity.
- Combining Lexical Resources for Contextual Synonym Expansion
- This paper discusses combining lexical resources for contextual synonym expansion.
- Linking Educational Materials to Encyclopedic Knowledge
- This paper discusses linking educational materials to encyclopedic knowledge.
- Explorations in Automatic Book Summarization
- This paper discusses explorations in automatic book summarization.
- Making Computers Laugh: Investigations in Automatic Humor Recognition
- This paper discusses investigations in automatic humor recognition.
- Unsupervised Large-Vocabulary Word Sense Disambiguation with Graph-based Algorithms for Sequence Data Labeling
- This paper introduces a graph-based algorithm for sequence data labeling, using random walks on graphs encoding label dependencies. The algorithm is illustrated and tested in the context of an unsupervised word sense disambiguation problem, and shown to significantly outperform the accuracy achieved through individual label assignment, as measured on standard sense-annotated data sets.
- Text Mining for Automatic Image Tagging
- This paper introduces several extractive approaches for automatic image tagging, relying exclusively on information mined from texts. Through evaluations on two datasets, the authors show that their methods exceed competitive baselines by a large margin, and compare favorably with the state-of-the-art that uses both textual and image features.
- An Evaluation Exercise for Romanian Word Sense Disambiguation
- This paper discusses an evaluation exercise for Romanian word sense disambiguation.
- Exploiting Agreement and Disagreement of Human Annotators for Word Sense Disambiguation
- This paper discusses word sense disambiguation.
- PageRank on Semantic Networks, with Application to Word Sense Disambiguation
- This article discusses PageRank on semantic networks, with application to word sense disambiguation.
- Amazon Mechanical Turk for Subjectivity Word Sense Disambiguation
- 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.
- Automatic Keyword Extraction for Learning Object Repositories
- This article discusses automatic keyword extraction for learning object repositories.
- Quantifying the Limits and Success of Extractive Summarization Systems Across Domains
- 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.
- Word Alignment for Languages with Scarce Resources
- 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.
- Linguistically Motivated Features for Enhanced Back-of-the-Book Indexing
- This paper discusses linguistically motivated features for enhanced back-of-the-book indexing.
- The SENSEVAL-3 English Lexical Sample Task
- This paper presents the task definition, resources, participating systems, and comparative results for the English lexical sample task, which was organized as part of the SENSEVAL-3 evaluation exercise.
- The SENSEVAL-3 Multilingual English-Hindi Lexical Sample Task
- This paper describes the English-Hindi Multilingual lexical sample task in SENSEVAL-3.
- SenseLearner: Minimally Supervised Word Sense Disambiguation for All Words in Open Text
- This paper introduces SenseLearner - a minimally supervised sense tagger that attempts to disambiguate all content words in a text using the sense from WordNet. SenseLearner participated in the SENSEVAL-3 English all words task, and achieved an average accuracy of 64.6%.
- Measuring the Semantic Similarity of Texts
- This paper discusses measuring the semantic similarity of texts.
- SemEval-2010 Task 2: Cross-Lingual Lexical Substitution
- This article describes the SemEval-2010 Cross-Lingual Lexical Substitution task.
- Integrating Knowledge for Subjectivity Sense Labeling
- This paper discusses integrating knowledge for subjectivity sense labeling.
- Semantic Document Engineering with WordNet and PageRank
- This article discusses semantic document engineering with WordNet and PageRank.
- An Evaluation Exercise for Word Alignment
- This paper discusses an evaluation exercise for word alignment.
- Wikify! Linking Documents to Encyclopedic Knowledge
- This paper introduces the use of Wikipedia as a resource for automatic keyword extraction and word sense disambiguation, and shows how this online encyclopedia can be used to achieve state-of-the-art results on both these tasks.
- Computational Laughing: Automatic Recognition of Humorous One-liners
- This paper discusses automatic recognition of humor.
- Learning to Identify Educational Materials
- This paper discusses learning to identify educational materials.
- Word Sense and Subjectivity
- This paper discusses word sense and subjectivity.
- Computational Models for Incongruity Detection in Humour
- In this paper, the authors explore several computational models for incongruity resolution.
- Creating a Testbed for the Evaluation of Automatically Generated Back-of-the-book Indexes
- This paper discusses automatic generating of back-of-the-book indexes.
- Characterizing Humour: An Exploration of Features in Humorous Texts
- This paper investigates the problem of automatic humor recognition, and provides an in-depth analysis of two of the most frequently observed features of humorous text: human-centeredness and negative polarity. Through experiments performed on two collections of humorous texts, the authors show that these properties of verbal humor are consisted across different data sets.
- TextRank: Bringing Order into Texts
- In this paper, the authors introduce TextRank, a graph-based ranking model for text processing, and show how this model can be successfully used in natural language applications.
- Multilingual Subjectivity Analysis Using Machine Translation
- This paper discusses multilingual subjectivity analysis using machine translation.
- Co-training and Self-training for Word Sense Disambiguation
- This paper investigates the application of co-training and self-training to word sense disambiguation. Optimal and empirical parameter selection methods for co-training and self-training are investigated, with various degrees of error reduction. A new method that combines co-training with majority voting is introduced, with the effect of smoothing the bootstrapping learning curves, and improving the average performance.
- The Decomposition of Human-Written Book Summaries
- In this paper, the authors evaluate the extent to which human-written book summaries can be obtained through cut-and-paste operations from the original book. The authors analyze the effect of the parameters involved in the decomposition algorithm, and highlight the distinctions in coverage obtained for different summary types.
- Linguistic Ethnography: Identifying Dominant Word Classes in Text
- This paper discusses linguistic ethnography.
- The Role of Non-Ambiguous Words in Natural Language Disambiguation
- This article discusses the role of non-ambiguous words in natural language disambiguation.
- Subjectivity Word Sense Disambiguation
- This paper investigates a new task, subjectivity word sense disambiguation (SWSD), which is to automatically determine which word instances in a corpus are being used with subjective senses, and which are being used with objective senses.
- Using the Essence of Texts to Improve Document Classification
- This article discusses using the essence of texts to improve document classification.
- Cross-lingual Semantic Relatedness Using Encyclopedic Knowledge
- This paper discusses cross-lingual semantic relatedness using encyclopedic knowledge.
- Corpus-based and Knowledge-based Measures of Text Semantic Similarity
- This article discusses corpus-based and knowledge-based measures of text semantic similarity.
- A Corpus-based Approach to Finding Happiness
- This paper discusses how to locate emotions.
- Classifier Stacking and Voting for Text Filtering
- This article discusses classifier stacking and voting for text filtering.
- Multi-Document Summarization with Iterative Graph-based Algorithms
- This paper discusses multi-document synchronization with iterative graph-based algorithms.