Automatically Acquiring Structured Case Representations: The SMART Way

Asiimwe, Stella Maris; Craw, Susan; Wiratunga, Nirmalie; Taylor, Bruce

doi:10.1007/978-1-84800-086-5_4

Cited by 4 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The usual bag-of-words model has also been improved, for instance using graphs to represent text [35], taking into account the position of words, which makes it possible to identify the negation of terms. Some approaches, such as the one presented by Asiimwe et al [36], proposed even richer case representations, requiring the need of information extraction (IE). IE has been shown to improve significantly results in CBR, as shown in Recio García et al [37], where a significant increase in recall in observed for the retrieval task.…”

Section: Related Workmentioning

confidence: 99%

Automatic case acquisition from texts for process-oriented case-based reasoning

Dufour-Lussier

Ber

Lieber

et al. 2014

Information Systems

View full text Add to dashboard Cite

This paper introduces a method for the automatic acquisition of a rich case representation from free text for process-oriented case-based reasoning. Case engineering is among the most complicated and costly tasks in implementing a case-based reasoning system. This is especially so for process-oriented case-based reasoning, where more expressive case representations are generally used and, in our opinion, actually required for satisfactory case adaptation. In this context, the ability to acquire cases automatically from procedural texts is a major step forward in order to reason on processes. We therefore detail a methodology that makes case acquisition from processes described as free text possible, with special attention given to assembly instruction texts. This methodology extends the techniques we used to extract actions from cooking recipes. We argue that techniques taken from natural language processing are required for this task, and that they give satisfactory results. An evaluation based on our implemented prototype extracting workflows from recipe texts is provided.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic case acquisition from texts for process-oriented case-based reasoning

Dufour-Lussier

Ber

Lieber

et al. 2014

Information Systems

View full text Add to dashboard Cite

show abstract

“…FCA has already been used in CBR, for instance in [9] and in [2]. In [9], the formal context is a representation of the case base (the objects are the cases and their properties are binary properties of cases).…”

Section: Discussion and Related Workmentioning

confidence: 99%

“…By contrast, in our work, FCA is used for adaptation: the formal context is all about the vocabulary for describing cases (the ingredients and the actions performed on ingredients). The objective of [2] is to obtain structured cases from texts, using FCA. The formal context objects are the texts and its properties are relevant terms of these texts.…”

Section: Discussion and Related Workmentioning

confidence: 99%

“…verb, noun, adjective) of each word, which was sufficient to train an error-driven, contextsensitive, transformation-based tagger [6] with an accuracy a > .90, well below the state of the art for regular texts, but sufficient for a prototype implementa-tion. 2 The other preliminary steps (tokenization, clause segmentation, chunking) were implemented using hand-crafted regular expressions. 3 At this stage we know which words are verbs (and thus actions) and we are able to identify their syntactic arguments, which should be sufficient to get on with the task of building a formal tree representation of a recipe.…”

Section: The Toolchainmentioning

confidence: 99%

See 1 more Smart Citation

Text Adaptation Using Formal Concept Analysis

Dufour-Lussier

Lieber

Nauer

et al. 2010

Case-Based Reasoning. Research and Development

View full text Add to dashboard Cite

This paper addresses the issue of adapting cases represented by plain text with the help of formal concept analysis and natural language processing technologies. The actual cases represent recipes in which we classify ingredients according to culinary techniques applied to them. The complex nature of linguistic anaphoras in recipe texts make usual text mining techniques inefficient so a stronger approach, using syntactic and dynamic semantic analysis to build a formal representation of a recipe, had to be used. This representation is useful for various applications but, in this paper, we show how one can extract ingredient-action relations from it in order to use formal concept analysis and select an appropriate replacement sequence of culinary actions to use in adapting the recipe text.Key words: formal concept analysis, natural language processing, text mining, textual case-based reasoning ⋆ The authors would like to thank the reviewers for their helpful comments, as well as Zeeshan Ahmed for his previous work on a related topic and Jenia Berzak, Le Dieu Thu, and Ripan Hermawan for letting us use their corpus of part-of-speech-tagged recipe texts. 1

show abstract

“…A number of these methods employ shallow statistical inferences that do not typically result in knowledge-rich representations. Techniques in natural language processing have been explored but their huge reliance on grammar makes them less attractive, especially in domains where problem-solving methodologies have not recorded using strict grammatical structure [3]. Within the Semantic Web community, the use of metadata annotations, such as tagging [4] has proved immensely popular as a technique for enriching information resources, but its employment of domain experts makes it less cost-effective.…”

Section: Introductionmentioning

confidence: 99%

An Approach for Enriching Information for Supporting Collaborative e-Work

Anya

Nagar

Tawfik

2008

Computational Science – ICCS 2008

View full text Add to dashboard Cite

Abstract. As a result of the high level of knowledge required in collaborative eWork as well as its changing work contexts, e-Work support systems need to provide not only information in the form of documents and articles, but also expert-level explanations in the form of supporting literature and references to theories and related cases, to justify retrieved information and offer cognitive support to e-Work. In this paper, we present a novel approach for enriching information for supporting collaborative e-Work, which combines latent semantic analysis, domain task modelling and conceptual learning. We illustrate the potential of our approach using our e-Workbench system. e-Workbench is a prototype system for adaptive collaborative e-Work.

show abstract

Automatically Acquiring Structured Case Representations: The SMART Way

Cited by 4 publications

References 12 publications

Automatic case acquisition from texts for process-oriented case-based reasoning

Automatic case acquisition from texts for process-oriented case-based reasoning

Text Adaptation Using Formal Concept Analysis

An Approach for Enriching Information for Supporting Collaborative e-Work

Contact Info

Product

Resources

About