UNT: SubFinder: Combining Knowledge Sources for Automatic Lexical Substitution (2009)
Samer Hassan, Andras Csomai, Carmen Banea, Ravi Sinha, Rada Mihalcea
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...
Rada Mihalcea, Andras Csomai, Massimiliano Ciaramita
We describe the SUPERSENSELEARNER system that participated in the English allwords disambiguation task. The system relies on automatically-learned semantic models using collocational features coupled...
Multilingual Subjectivity Analysis Using Machine Translation (2009)
Although research in other languages is increasing, much of the work in subjectivity analysis has been applied to English data, mainly due to the large body of electronic resources and tools that are...
A language independent algorithm for single and multiple document summarization (2009)
This paper describes a method for language independent extractive summarization that relies on iterative graph-based ranking algorithms. Through evaluations performed on a single-document...
An Evaluation Exercise for Romanian Word Sense Disambiguation (2008)
Rada Mihalcea, Timothy Chklovski, Dan Tufis
This paper presents the task definition, resources, participating systems, and comparative results for a Romanian Word Sense Disambiguation task, which was organized as part of the SENSEVAL-3...
RSDNET: A WEB-BASED COLLABORATIVE FRAMEWORK FOR BUILDING MULTILINGUAL SEMANTIC NETWORKS (2008)
Nathaniel Ayewah, Rada Mihalcea, Vivi Năstase, Doina Tătar
Abstract. We present a system (RSDnet) that allows non-expert Web users to contribute towards building a multilingual lexical resource. Our study focuses on the Romanian-English language pair, and...
Word Sense Disambiguation Tutorial at ESSLLI 2006 (2008)
Note: these tutorial notes were created in collaboration with Ted Pedersen,
A language independent algorithm for single and multiple document summarization (2008)
This paper describes a method for language independent extractive summarization that relies on iterative graph-based ranking algorithms. Through evaluations performed on a single-document...
Classifier Stacking and Voting for Text Filtering (2008)
This paper summarizes the approach and the results of the TextCat system participating in the Filtering track in the Text Retrieval Conference 2002. The system relies primarily on statistical...
for Robust Semantic Parsing (2008)
1 Introduction The goal of a semantic parser is to identify semantic relations between words in a text, resulting in structures that reflect various levels of semantic interpretation. Such structures...
Romanian–English, and English–Hindi (2008)
Joel Martin, Rada Mihalcea, Ted Pedersen
This paper presents the task definition, resources, participating systems, and comparative results for the shared task on word alignment, which was organized
An Evaluation Exercise for Romanian Word Sense Disambiguation (2008)
Rada Mihalcea, Timothy Chklovski, Dan Tufis
This paper presents the task definition, resources, participating systems, and comparative results for a Romanian Word Sense Disambiguation task, which was organized as part of the SENSEVAL-3...
An Evaluation Exercise for Romanian Word Sense Disambiguation (2008)
Rada Mihalcea, Timothy Chklovski, Dan Tufis
This paper presents the task definition, resources, participating systems, and comparative results for a Romanian Word Sense Disambiguation task, which was organized as part of the SENSEVAL-3...
NLP (Natural Language Processing) for NLP (Natural Language Programming) (2008)
Rada Mihalcea, Hugo Liu, Henry Lieberman
Abstract. Natural Language Processing holds great promise for making computer interfaces that are easier to use for people, since people will (hopefully) be able to talk to the computer in their own...
A language independent algorithm for single and multiple document summarization (2008)
This paper describes a method for language independent extractive summarization that relies on iterative graph-based ranking algorithms. Through evaluations performed on a single-document...
UNT: SubFinder: Combining Knowledge Sources for Automatic Lexical Substitution (2008)
Samer Hassan, Andras Csomai, Carmen Banea, Ravi Sinha, Rada Mihalcea
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...
We describe the SUPERSENSELEARNER system that participated in the English allwords disambiguation task. The system relies on automatically-learned semantic models using collocational features coupled...
Finding Semantic Associations on Express Lane (2008)
We introduce a new codification scheme for efficient computation of measures in semantic networks. The scheme is particularly useful for fast computation of semantic associations between words and...
Creating a testbed for the evaluation of automatically generated back-of-the-book indexes (2008)
"Knowledge is of two kinds. We know a subject ourselves, or we know where we can find information on it. " (Samuel Johnson)
Creating a testbed for the evaluation of automatically generated back-of-the-book indexes (2008)
Abstract. The automatic generation of back-of-the book indexes seems to be out of sight of the Information Retrieval and Natural Language Processing communities, although the increasingly large...
for Robust Semantic Parsing (2008)
Abstract. This paper describes our work in integrating three different lexical resources: FrameNet, VerbNet, and WordNet, into a unified, richer knowledge-base, to the end of enabling more robust...
Characterizing Humour: An Exploration of Features in Humorous Texts (2008)
Abstract. This paper investigates the problem of automatic humour recognition, and provides and in-depth analysis of two of the most frequently observed features of humorous text: human-centeredness...
Romanian–English, and English–Hindi (2008)
Joel Martin, Rada Mihalcea, Ted Pedersen
This paper presents the task definition, resources, participating systems, and comparative results for the shared task on word alignment, which was organized
Classifier Stacking and Voting for Text Filtering (2008)
This paper summarizes the approach and the results of the TextCat system participating in the Filtering track in the Text Retrieval Conference 2002. The system relies primarily on statistical...
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Lasso: A Tool for Surng the Answer Net (2007)
Dan Moldovan, A Harabagiu, Rada Mihalcea, Richard Goodrum, Vasile Rus
This paper presents the architecture, operation and results obtained with the Lasso system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of...
Answering complex list and context questions with LCCs (2007)
Question-answering Server, A Harabagiu, Dan Moldovan, Marius Paca, Mihai Surdeanu, Rada Mihalcea, ...
Corporation*
Dan Moldovan, A Harabagiu, Marius Paca, Rada Mihalcea, Richard Goodrum, Roxana Girju, ...
This paper presents the architecture, operation and results obtained with the LASSO system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of...
Classifier Stacking and Voting for Text Filtering (2007)
This paper summarizes the approach and the results of the TextCat system participating in the Filtering track in the Text Retrieval Conference 2002. The system relies primarily on statistical...
Answering complex, list and context questions with LCC's (2007)
Question-answering Server, Sanda Harabagiu, Dan Moldovan, Mihai Surdeanu, Rada Mihalcea, Vasile Rus
This paper presents the architecture of the QuestionAnswering Server (QAS) developed at the Language Computer Corporation (LCC) and used in the TREC10 evaluations. LCC's QAS TM extracts answers...
Finding Semantic Associations on Express Lane (2007)
We introduce a new codification scheme for efficient computation of measures in semantic networks. The scheme is particularly useful for fast computation of semantic associations between words and...
Building multilingual semantic networks with non-expert contributions over the Web (2007)
Nathaniel Ayewah, Rada Mihalcea, Vivi N Astase
We present a system that allows non-expert Web users to contribute towards building a multilingual lexical resource. Our study focuses on the Romanian-English language pair, and the target resource...
Learning Multilingual Subjective Language via Cross-Lingual Projections (2007)
This paper explores methods for generating subjectivity analysis resources in a new language by leveraging on the tools and resources available in English. Given a bridge between English and the...
Bibliography Published Papers by Dragomir R. Radev References (2007)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, Bruce Croft, ...
[5] Suresh Bhavnani, Karen Drabenstott, and Dragomir Radev. Towards a unified framework of IR tasks and strategies. In 2001 ASIST Annual
Learning Multilingual Subjective Language via Cross-Lingual Projections (2007)
Rada Mihalcea, Carmen Banea, Janyce Wiebe
This paper explores methods for generating subjectivity analysis resources in a new language by leveraging on the tools and resources available in English. Given a bridge between English and the...
Corpus-based and knowledge-based measures of text semantic similarity (2006)
Rada Mihalcea, Courtney Corley
This paper presents a method for measuring the semantic similarity of texts, using corpus-based and knowledge-based measures of similarity. Previous work on this problem has focused mainly on either...
Random-Walk Term Weighting for Improved Text Classification (2006)
Samer Hassan, Rada Mihalcea, Carmen Banea
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. The method uses term...
A corpus-based approach to finding happiness (2006)
What are the sources of happiness and sadness in everyday life? In this paper, we employ ‘linguistic ethnography ’ to seek out where happiness lies in our everyday lives by considering a corpus...
Word sense and subjectivity (2006)
Subjectivity and meaning are both important properties of language. This paper explores their interaction, and brings empirical evidence in support of the hypotheses that (1) subjectivity is a...
Word Alignment for Languages with Scarce Resources (2005)
Joel Martin, Rada Mihalcea, Ted Pedersen
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 ACL 2005 Workshop on...
Making computers laugh: Investigations in automatic humor recognition (2005)
Humor is one of the most interesting and puzzling aspects of human behavior. Despite the attention it has received in fields such as philosophy, linguistics, and psychology, there have been only few...
Making computers laugh: Investigations in automatic humor recognition (2005)
Humor is one of the most interesting and puzzling aspects of human behavior. Despite the attention it has received in fields such as philosophy, linguistics, and psychology, there have been only few...
Language independent extractive summarization (2005)
We demonstrate TextRank – a system for unsupervised extractive summarization that relies on the application of iterative graphbased ranking algorithms to graphs encoding the cohesive structure of a...
SenseLearner: Word Sense Disambiguation for All Words (2005)
This paper describes SENSELEARNER – a minimally supervised word sense disambiguation system that attempts to disambiguate all content words in a text using WordNet senses. We evaluate the accuracy...
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...
Making computers laugh: Investigations in automatic humor recognition (2005)
Humor is one of the most interesting and puzzling aspects of human behavior. Despite the attention it has received in fields such as philosophy, linguistics, and psychology, there have been only few...
Co-training and self-training for word sense disambiguation (2004)
This paper investigates the application of cotraining and self-training to word sense disambiguation. Optimal and empirical parameter selection methods for co-training and self-training are...
SenseLearner: Minimally supervised word sense disambiguation for all words in open text (2004)
Rada Mihalcea, Ehsanul Faruque
This paper introduces SENSELEARNER-- a minimally supervised sense tagger that attempts to disambiguate all content words in a text using the senses from WordNet. SENSELEARNER participated in the...
An Algorithm for Open Text Semantic Parsing (2004)
Lei Shi And, Lei Shi, Rada Mihalcea
This paper describes an algorithm for open text shallow semantic parsing. The algorithm relies on a frame dataset (FrameNet) and a semantic network (WordNet), to identify semantic relations between...
The SENSEVAL-3 Multilingual English-Hindi Lexical Sample Task (2004)
Timothy Chklovski, Rada Mihalcea, Ted Pedersen, Amruta Purandare
This paper describes the English--Hindi Multilingual lexical sample task in SENSEVAL--3. Rather than tagging an English word with a sense from an English dictionary, this task seeks to assign the...
Co-training and Self-training for Word Sense Disambiguation (2004)
This paper investigates the application of cotraining and self-training to word sense disambiguation.
The Senseval-3 English lexical sample task (2004)
Rada Mihalcea, Timothy Chklovski, Adam Kilgarriff
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...
The Senseval-3 English lexical sample task (2004)
Rada Mihalcea, Timothy Chklovski, Adam Kilgarriff
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...
Open Mind Word Expert: Creating Large Annotated Data Collections with Web Users' Help (2004)
Rada Mihalcea, Timothy Chklovski
Open Mind Word Expert is an implemented active learning system that aims to create large annotated corpora by tapping into the world's vast pool of knowledge.
Making Sense Out of the Web (2004)
Abstract. In the past few years, we have witnessed a tremendous growth of the World Wide Web, both in terms of number of Web pages accessible online – resulting in what represents today the largest...
The Role of Non-Ambiguous Words in Natural Language Disambiguation (2003)
This paper describes an unsupervised approach for natural language disambiguation, applicable to ambiguity problems where classes of equivalence can be defined over the set of words in a lexicon....
An Evaluation Exercise for Word Alignment (2003)
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 HLT/NAACL 2003 Workshop on...
An Evaluation Exercise for Word Alignment (2003)
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 HLT/NAACL 2003 Workshop on...
Exploiting Agreement and Disagreement of Human Annotators for Word Sense Disambiguation (2003)
Timothy Chklovski, Rada Mihalcea
It is generally agreed that the success of a Word Sense Disambiguation (WSD) system depends, in large, on having enough sense annotated data available at hand, and a well-motivated sense inventory...
An Evaluation Exercise for Word Alignment (2003)
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 HLT/NAACL 2003 Workshop on...
An Evaluation Exercise for Word Alignment (2003)
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 HLT/NAACL 2003 Workshop on...
An evaluation exercise for word alignment (2003)
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
Open mind word expert: Creating large annotated data collections with web users’ help (2003)
Open Mind Word Expert is an implemented active learning system that aims to create large annotated corpora by tapping into the world’s vast pool of knowledge. It does this by relying on the vast...
V.: Letter level learning for language independent diacritics restoration (2002)
This paper presents a method for diacritics restoration based on learning mechanisms that act at letter level. The method requires no additional tagging tools or resources other than raw text, which...
Building a Sense Tagged Corpus with Open Mind Word Expert (2002)
Timothy Chklovski, Rada Mihalcea
Open Mind Word Expert is an implemented active learning system for collecting word sense tagging from the general public over the Web. It is available at
V.: Letter level learning for language independent diacritics restoration (2002)
This paper presents a method for aliacritics restoration based on learning mechanisms that act at letter level. The method requires no additional tagging tools or resources other than raw text, which...
V.: Letter level learning for language independent diacritics restoration (2002)
This paper presents a method for aliacritics restoration based on learning mechanisms that act at letter level. The method requires no additional tagging tools or resources other than raw text, which...
Instance Based Learning with Automatic Feature Selection Applied to Word Sense Disambiguation (2002)
We describe an algorithm for Word Sense Disambiguation (WSD) that relies on a lazy learner improved with automatic feature selection. The algorithm was implemented in a system that achieves excellent...
Document Indexing Using Named Entities (2001)
Rada Mihalcea, Dan I. Moldovan
Abstract: Current text indexing and retrieval techniques have their roots in the field of Information Retrieval where the task is to extract documents that best match a query. With an ever increasing...
eXtended WordNet: Progress Report (2001)
Rada Mihalcea, Dan I. Moldovan
eXtended WordNet (XWN), a morphologically and semantically enhanced version of the WordNet dictionary, is currently build at SMU 1. There are several phases in the XWN project. This paper focuses on...
The role of lexico-semantic feedback in open-domain textual question-answering (2001)
A Harabagiu, Dan Moldovan, Marius Pasca, Rada Mihalcea, Mihai Surdeanu, R Azvan Bunescu, ...
This paper presents an open-domain textual Question-Answering system that uses several feedback loops to enhance its performance. These feedback loops combine in a new way statistical results with...
EZ.WordNet: Principles for Automatic Generation of a Coarse Grained WordNet (2001)
Rada Mihalcea, Dan I. Moldovan
In this paper, we propose several principles that enable the automatic transformation of WordNet into a coarser grained dictionary, without aecting its existing semantic relations. We derive a new...
The role of lexico-semantic feedback in open-domain textual question-answering (2001)
A Harabagiu, Dan Moldovan, Rada Mihalcea, Mihai Surdeanu, Răzvan Bunescu, Roxana Gîrju, ...
This paper presents an open-domain textual Question-Answering system that uses several feedback loops to enhance its performance. These feedback loops combine in a new way statistical results with...
The role of lexico-semantic feedback in open-domain textual question-answering (2001)
A Harabagiu, Dan Moldovan, Rada Mihalcea, Mihai Surdeanu, Răzvan Bunescu, Roxana Gîrju, ...
This paper presents an open-domain textual Question-Answering system that uses several feedback loops to enhance its performance. These feedback loops combine in a new way statistical results with...
Document Indexing Using Named Entities (2001)
Rada Mihalcea, Dan I. Moldovan
Abstract: Current text indexing and retrieval techniques have their roots in the field of Information Retrieval where the task is to extract documents that best match a query. With an ever increasing...
Improving the Search on the Internet by Using WordNet and Lexical Operators (2000)
Dan I. Moldovan, Rada Mihalcea
Not for distribution or attribution. For review purposes only. A vast amount of information is available on the Internet, and naturally, many information gathering tools have been developed. Search...
Improving the Search on the Internet by Using WordNet and Lexical Operators (2000)
Dan I. Moldovan, Rada Mihalcea
Not for distribution or attribution. For review purposes only. A vast amount of information is available on the Internet, and naturally, many information gathering tools have been developed. Search...
Semantic indexing using WordNet senses (2000)
We describe in this paper a boolean Information Retrieval system that adds word semantics to the classic word based indexing. Two of the main tasks of our system, namely the indexing and retrieval...
Falcon: Boosting knowledge for answer engines (2000)
A Harabagiu, Dan Moldovan, Rada Mihalcea, Mihai Surdeanu, Vasile Rus
This paper presents the features of Falcon, an answer engine that integrates dierent forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance. The answer...
Falcon: Boosting knowledge for answer engines (2000)
A Harabagiu, Dan Moldovan, Marius Paaca, Rada Mihalcea, Mihai Surdeanu, Zvan Bunescu, ...
This paper presents the features of FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance. The answer...
The structure and performance of an open-domain question answering system (2000)
Dan Moldovan, A Harabagiu, Marius Pasca, Rada Mihalcea, Roxana Girju, Richard Goodrum, ...
This paper presents the architecture, operation and results obtained with the LASSO Question Answering system developed in the Natural
Semantic indexing using WordNet senses (2000)
We describe in this paper a boolean Information Retrieval system that adds word semantics to the classic word based indexing. Two of the main tasks of our system, namely the indexing and retrieval...
Improving the search on the Internet by using WordNet and lexical operators (2000)
Dan Moldovan And, Dan I. Moldovan, Rada Mihalcea
This paper presents a natural language interface system to an Internet search engine that provides the following improvements: (1) accepts natural language (English) questions, (2) expands the query,...
An Iterative Approach to Word Sense Disambiguation (2000)
In this paper, we present an iterative algorithm for Word Sense Disambiguation. It combines two sources of information: WordNet and a semantic tagged corpus, for the purpose of identifying the...
Semantic indexing using WordNet senses (2000)
We describe in this paper a boolean Information l~.etrieval system that adds word semantics to the classic word based indexing. Two of the main tasks of our system, namely the indexing and retrieval...
Word sense disambiguation and its application to Internet search /--by Rada Mihalcea. (1999)
Thesis (M.S. in Computer Sience)--S.M.U.
A method for word sense disambiguation of unrestricted text (1999)
Rada Mihalcea, Dan I. Moldovan
Selecting the most appropriate sense for an am-biguous word in a sentence is a central prob-lem in Natural Language Processing. In this paper, we present a method that attempts to disambiguate all...
An automatic method for generating sense tagged corpora (1999)
Rada Mihalcea, Dan I. Moldovan
The unavailability of very large corpora with semantically disambiguated words is a major limitation in text processing research. For example, statistical methods for word sense disambiguation of...
Lasso: A Tool for Sur ng the Answer Net (1999)
Dan Moldovan Sanda, Dan Moldovan, A Harabagiu, Rada Mihalcea, Richard Goodrum, Vasile Rus
This paper presents the architecture, operation and results obtained with the Lasso system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of...
LASSO: A Tool for Surfing the Answer Net (1999)
Dan Moldovan, Sanda Harabagiu, Marius Pasca, A Harabagiu, Rada Mihalcea, Roxana Gîrju, ...
This paper presents the architecture, operation and results obtained with the Lasso system developed in the Natural Language Processing Laboratory at SMU. The system relies on a combination of...
Automatic Acquisition of Sense Tagged Corpora (1999)
Rada Mihalcea And, Rada Mihalcea, Dan I. Moldovan
An important problem in Natural Language Processing is identifying the correct sense of a word in a particular context. Thus far, statistical methods have been considered the best techniques in word...
Improving the search on the Internet by using WordNet and lexical operators (1999)
Dan I. Moldovan, Rada Mihalcea
This paper presents a natural language interface system to an Internet search engine that provides the following improvements: (1) accepts natural language (English) questions, (2) expands the query,...
An Automatic Method for Generating Sense Tagged Corpora (1999)
Rada Mihalcea, Dan I. Moldovan
The unavailability of very large corpora with semantically disambiguated words is a major limitation in text processing research. For example, statistical methods for word sense disambiguation of...
A Method for Word Sense Disambiguation of Unrestricted Text (1999)
Rada Mihalcea, Dan I. Moldovan
Selecting the most appropriate sense for an ambiguous word in a sentence is a central problem in Natural Language Processing. In this paper, we present a method that attempts to disambiguate all the...
Automatic Acquisition of Sense Tagged Corpora (1999)
Rada Mihalcea, Dan I. Moldovan
An important problem in Natural Language Processing is identifying the correct sense of a word in a particular context. Thus far, statistical methods have been considered the best techniques in word...
A WordNet-Based Interface to Internet Search Engines (1998)
Dan I. Moldovan, Rada Mihalcea
A vast amount of information is available on the Internet, and naturally, many information gathering tools have been developed. Several search engines with different characteristics, such as...
SEMCOR Semantically tagged corpus (1998)
Semcor is a textual corpus in which words are sintactically and semantically tagged. The texts included in Semcor were extracted from the Brown corpus and then linked to senses in the WordNet...
Word Sense Disambiguation based on Semantic Density (1998)
Rada Mihalcea, Dan I. Moldovan
This paper presents a Word Sense Disambiguation method based on the idea of semantic density between words. The disambiguation is done in the context of WordNet. The Internet is used as a raw corpora...
Word Sense Disambiguation based on Semantic Density (1998)
Rada Mihalcea, Dan I. Moldovan
This paper presents a Word Sense Disambiguation method based on the idea of semantic density between words. The disambiguation is done in the context of WordNet. The Internet is used as a raw corpora...