A metalearning approach to processing the scope of negation

Morante, Roser; Daelemans, Walter

doi:10.3115/1596374.1596381

Cited by 86 publications

(144 citation statements)

References 15 publications

(7 reference statements)

Supporting

Mentioning

140

Contrasting

Order By: Relevance

“…Agarwal and Yu [39] developed the NegScope algorithm that utilizes conditional random fields to detect negations, but it had a lower performance in comparison to NegEx. Fujikawa et al [40] developed the NegFinder algorithm for determining the scope of negation cues by adding syntactic information to the algorithm of Morante et al [36,38] that utilizes k-nearest neighbor classification as discussed above. This algorithm should not be mistaken for the NegFinder algorithm by Mutalik et al [25].…”

Section: Related Workmentioning

confidence: 99%

“…Rokach et al [37] designed an algorithm for learning regular expressions using the longest common subsequence algorithm followed by decision tree classification. Morante and Daelemans [38] proposed a machine learning algorithm utilizing k-nearest neighbor classification in addition to Support Vector Machines (SVMs) and conditional random fields to determine the scope of negation. Uzuner et al [24] proposed the StAC statistical assertion classification algorithm and showed that it outperforms the rule-based ENegEx algorithm.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

Elazhary¹

2017

IJISA

View full text Add to dashboard Cite

Abstract-Mining negations from electronic narrative medical documents is one of the prominent data mining applications. Since medical documents are freely written, it is impossible to consider all possible sentence structures in advance and so frequent update of mining algorithms is inevitable. Unfortunately most of the proposed algorithms in the literature are too complex to be easily updated. Besides, most of them cannot be easily ported to other natural languages. The simple NegEx algorithm utilizes only two regular expressions and sets of terms to mine negations from narrative medical documents and so does not suffer from these shortcomings. Meanwhile, it has shown impressive mining results and so it is the most widely adopted algorithm. This paper proposes the Negation Mining (NegMiner) tool to address some of the shortcomings of the NegEx algorithm. The NegMiner exploits some basic syntactic and semantic information to deal with contiguous and multiple negations. It is a user-friendly tool that facilitates the task of knowledge base update and the task of document analysis through the use of PDF files. This also makes it able to deal with the existence of a medical finding several times in a single sentence. Experimental results have shown the superiority of the mining results of the NegMiner in comparison to the simulated NegEx algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

Elazhary¹

2017

IJISA

View full text Add to dashboard Cite

show abstract

“…It is important to note that the main source of error here is the NegatedPredicate-to-BioScopeScopeSpan trans- Table 3: PCS measures from previous BioScope span detection approaches and our end-to-end system. Col. 1-3: end-to-end systems (Morante and Daelemans, 2009), (Ballesteros et al, 2012), and (Velldal et al, 2012);…”

Section: Our Negatedpredicate Predictormentioning

confidence: 99%

Learning Structures of Negations from Flat Annotations

Prabhakaran

Boguraev²

2015

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

View full text Add to dashboard Cite

We propose a novel method to learn negation expressions in a specialized (medical) domain. In our corpus, negations are annotated as 'flat' text spans. This allows for some infelicities in the mark-up of the ground truth, making it less than perfectly aligned with the underlying syntactic structure. Nonetheless, the negations thus captured are correct in intent, and thus potentially valuable. We succeed in training a model for detecting the negated predicates corresponding to the annotated negations, by re-mapping the corpus to anchor its 'flat' annotation spans into the predicate argument structure. Our key idea-re-mapping the negation instance spans to more uniform syntactic nodes-makes it possible to re-frame the learning task as a simpler one, and to leverage an imperfect resource in a way which enables us to learn a high performance model. We achieve high accuracy for negation detection overall, 87%. Our re-mapping scheme can be constructively applied to existing flatly annotated resources for other tasks where syntactic context is vital.

show abstract

“…In particular, we adopt the practice of solving scope resolution as a sequence labeling task (Morante and Daelemans, 2009;Lapponi et al, 2012;White, 2012) based on syntactic features Lapponi et al, 2012;Packard et al, 2014). In contrast to many of the previous systems that have used constituency-based representations Packard et al, 2014), we base our syntactic features on dependency representations, similar to the approach of Lapponi et al (2012).…”

Section: Introductionmentioning

confidence: 99%

“…While many research-based systems have been developed, with the aim of exploring features and algorithms to advance the state-of-the-art in terms of performance (Morante and Daelemans, 2009;Lapponi et al, 2012;Packard et al, 2014;Fancellu et al, 2016), many of them are difficult to employ in practice, due to layered architectures and many dependencies, and furthermore, most are simply not made publicly available in the first place.…”

Section: Introductionmentioning

confidence: 99%

An open-source tool for negation detection: a maximum-margin approach

Enger¹,

Velldal²,

Øvrelid³

2017

Proceedings of the Workshop Computational Semantics Beyond Events and Roles

View full text Add to dashboard Cite

This paper presents an open-source toolkit for negation detection. It identifies negation cues and their corresponding scope in either raw or parsed text using maximummargin classification. The system design draws on best practice from the existing literature on negation detection, aiming for a simple and portable system that still achieves competitive performance. Pretrained models and experimental results are provided for English.

show abstract

A metalearning approach to processing the scope of negation

Cited by 86 publications

References 15 publications

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

Learning Structures of Negations from Flat Annotations

An open-source tool for negation detection: a maximum-margin approach

Contact Info

Product

Resources

About