Learning multiple distributed prototypes of semantic categories for named entity recognition

Henriksson, Aron

doi:10.1504/ijdmb.2015.072766

Cited by 7 publications

(4 citation statements)

References 26 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the data is mainly in the form of free text, natural language processing (NLP) is applied in order to extract requirements information. Identification of information in free-text is typically achieved through named entity recognition (NER), which enables classification of sequences of words [29] and identifies the beginning and end of any type of predefined requirements-related information, e.g., mentions of a functionality. Sentiment analysis is an NLP task applied to enable classification of a type of emotion or attitude, typically as positive, negative, or neutral [30].…”

Section: Data-driven Requirements Elicitationmentioning

confidence: 99%

Holistic data-driven requirements elicitation in the big data era

Henriksson

Zdravković

2021

Softw Syst Model

Self Cite

View full text Add to dashboard Cite

Digital transformation stimulates continuous generation of large amounts of digital data, both in organizations and in society at large. As a consequence, there have been growing efforts in the Requirements Engineering community to consider digital data as sources for requirements acquisition, in addition to human stakeholders. The volume, velocity and variety of the data make requirements discovery increasingly dynamic, but also unstructured and complex, which current elicitation methods are unable to consider and manage in a systematic and efficient manner. We propose a framework, in the form of a conceptual metamodel and a method, for continuous and automated acquisition, analysis and aggregation of heterogeneous digital sources that aims to support data-driven requirements elicitation and management. The usability of the framework is partially validated by an in-depth case study from the business sector of video game development.

show abstract

Section: Data-driven Requirements Elicitationmentioning

confidence: 99%

Holistic data-driven requirements elicitation in the big data era

Henriksson

Zdravković

2021

Softw Syst Model

Self Cite

View full text Add to dashboard Cite

show abstract

“…Identification of information in free text is a task referred to as Named Entity Recognition (NER). NER concerns classification of sequences of words [23], where, here, the goal is to identify the beginning and end of any type of predefined requirements-related information, e.g. mentions of features.…”

Section: Data-driven Requirements Elicitationmentioning

confidence: 99%

A Data-Driven Framework for Automated Requirements Elicitation from Heterogeneous Digital Sources

Henriksson

Zdravković

2020

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

Increased digitalization and the pervasiveness of Big Data, along with vastly improved data processing capabilities, have led to the consideration of digital data as additional sources of system requirements, complementing conventional stakeholder-driven approaches. The volume, velocity and variety of these digital sources present numerous challenges which existing system development methods are unable to manage in a systematic and efficient manner. We propose a holistic and data-driven framework for continuous and automated acquisition, analysis and aggregation of heterogeneous digital sources for the purposes of requirements elicitation and management. The proposed framework includes a conceptualization in the form of a meta-model and a high-level process for its use; the framework is illustrated in a real case of an enterprise software.

show abstract

“…Information harvested in an unsupervised fashion from unlabelled corpora has for a long time (Miller et al, 2004;Freitag, 2004) been used as classifier features for improving the performance of named entity recognition and other types of chunk classification tasks. For instance, information from Brown clustering has been used for biomedical entity recognition (de Bruijn et al, 2011), predictive class bigram model clustering for general named entity recognition in several languages (Täckström et al, 2012), Random Indexing for named entity recognition in clinical text (Henriksson, 2015), and different kinds of word embeddings have been used for recognising opinion targets (Liu et al, 2015).…”

Section: Incorporation Of Unsupervised Approachesmentioning

confidence: 99%

PAL, a tool for Pre-annotation and Active Learning

Skeppstedt¹,

Paradis²,

Kerren³

2016

JLCL

View full text Add to dashboard Cite

Many natural language processing systems rely on machine learning models that are trained on large amounts of manually annotated text data. The lack of sufficient amounts of annotated data is, however, a common obstacle for such systems, since manual annotation of text is often expensive and time-consuming.The aim of "PAL, a tool for Pre-annotation and Active Learning" is to provide a ready-made package that can be used to simplify annotation and to reduce the amount of annotated data required to train a machine learning classifier. The package provides support for two techniques that have been shown to be successful in previous studies, namely active learning and pre-annotation.The output of the pre-annotation is provided in the annotation format of the annotation tool BRAT, but PAL is a stand-alone package that can be adapted to other formats.

show abstract

Learning multiple distributed prototypes of semantic categories for named entity recognition

Cited by 7 publications

References 26 publications

Holistic data-driven requirements elicitation in the big data era

Holistic data-driven requirements elicitation in the big data era

A Data-Driven Framework for Automated Requirements Elicitation from Heterogeneous Digital Sources

PAL, a tool for Pre-annotation and Active Learning

Contact Info

Product

Resources

About