Message Understanding Conference-6

Grishman, Ralph; Sundheim, Beth

doi:10.3115/992628.992709

Cited by 1,012 publications

(564 citation statements)

References 0 publications

Supporting

Mentioning

545

Contrasting

Unclassified

Order By: Relevance

“…Rather, given a specific, particular, language (Portuguese), one of our goals was to measure, instead, how well language-dependent and language-independent methods fare. 6 The reasons to organize HAREM were thus manifold, ranging from practical opportunity to theoretical relevance: As to the former, there was a relatively large number of interested parties, which is a requirement for a successful event. In addition, in contradistinction to morphological analysis [5] where it was hard to establish a common set of agreed categories, because many choices of the participating systems were only motivated by the different behaviours of the parsers using them, NER in itself boasted of a number of almost direct applications, although they differed significantly in their requirements.…”

Section: Context and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

A Golden Resource for Named Entity Recognition in Portuguese

Santos¹,

Cardoso

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a collection of texts manually annotated with named entities in context, which was used for HAREM, the first evaluation contest for named entity recognizers for Portuguese. We discuss the options taken and the originality of our approach compared with previous evaluation initiatives in the area. We document the choice of categories, their quantitative weight in the overall collection and how we deal with vagueness and underspecification.

show abstract

Section: Context and Motivationmentioning

confidence: 99%

“…Although this is a fairly standard model, already used for Portuguese in Morfolimpíadas [4,5], there are some interesting ways in which this evaluation contest differs from MUC [6] and other predecessors in the NE domain:…”

Section: Introductionmentioning

confidence: 99%

A Golden Resource for Named Entity Recognition in Portuguese

Santos¹,

Cardoso

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The development of automatic coreference resolution systems began in earnest in 1996 in response to the MUC-6 competition organised by NRAD with the support of DARPA [7]. Since then, numerous coreference resolution systems have been developed, typically using machine learning, and exploiting supervised [8]; [9]; [10] and unsupervised (clustering) methods [11].…”

Section: Introductionmentioning

confidence: 99%

Coreference Resolution: To What Extent Does It Help NLP Applications?

Mitkov

Evans

Orăsan

et al. 2012

Text, Speech and Dialogue

View full text Add to dashboard Cite

This paper describes a study of the impact of coreference resolution on NLP applications. Further to our previous study [1], in which we investigated whether anaphora resolution could be beneficial to NLP applications, we now seek to establish whether a different, but related task -that of coreference resolution, could improve the performance of three NLP applications: text summarisation, recognising textual entailment and text classification. The study discusses experiments in which the aforementioned applications were implemented in two versions, one in which the BART coreference resolution system was integrated and one in which it was not, and then tested in processing input text. The paper discusses the results obtained.

show abstract

“…The term 'named entity recognition (extraction)' was first mentioned in 1996 at the Sixth Message Understanding Conference (MUC-6) [4], however the field started much earlier. The vast majority of proposed approaches for NER fall in two categories: handmade rule-based systems and supervised learning-based systems.…”

Section: Named Entity Extractionmentioning

confidence: 99%

A Hybrid Approach for Robust Multilingual Toponym Extraction and Disambiguation

Habib

Keulen

2013

Language Processing and Intelligent Information Systems

View full text Add to dashboard Cite

Abstract. Toponym extraction and disambiguation are key topics recently addressed by fields of Information Extraction and Geographical Information Retrieval. Toponym extraction and disambiguation are highly dependent processes. Not only toponym extraction effectiveness affects disambiguation, but also disambiguation results may help improving extraction accuracy. In this paper we propose a hybrid toponym extraction approach based on Hidden Markov Models (HMM) and Support Vector Machines (SVM). Hidden Markov Model is used for extraction with high recall and low precision. Then SVM is used to find false positives based on informativeness features and coherence features derived from the disambiguation results. Experimental results conducted with a set of descriptions of holiday homes with the aim to extract and disambiguate toponyms showed that the proposed approach outperform the state of the art methods of extraction and also proved to be robust. Robustness is proved on three aspects: language independence, high and low HMM threshold settings, and limited training data.

show abstract

Message Understanding Conference-6

Cited by 1,012 publications

References 0 publications

A Golden Resource for Named Entity Recognition in Portuguese

A Golden Resource for Named Entity Recognition in Portuguese

Coreference Resolution: To What Extent Does It Help NLP Applications?

A Hybrid Approach for Robust Multilingual Toponym Extraction and Disambiguation

Contact Info

Product

Resources

About