Getting the Meaning Right: A Complementary Distributional Layer for the Web Semantics

Nováček, Vít; Handschuh, Siegfried; Decker, Stefan

doi:10.1007/978-3-642-25073-6_32

Cited by 17 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The representation of the relationships between entities in texts is very close to the approach of [Baroni and Lenci, 2010], however, we have extended the tensor-based representation to tackle a broader notion of text and data semantics, as described in detail in [Nováček et al, 2011]. The indexing and querying of the relationships between entities mentioned in the texts is based on fuzzy index structures, similarly to [Zadrozny and Nowacka, 2009].…”

Section: Related Workmentioning

confidence: 99%

“…The content is then exposed via a multiple-perspective search and browse interface. SKIMMR brings the following major improvements over CORAAL: (1) more advanced backend (built using our distributional data semantics framework introduced in [Nováček et al, 2011]); (2) simplified modes of interaction with the data leading to increased usability and better user experience; (3) richer, more robust fuzzy querying; (4) general streamlining of the underlying technologies and front-ends motivated by the simple, yet powerful metaphor of machine-aided skim reading.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SKIMMR: Facilitating knowledge discovery in life sciences by machine-aided skim reading

Nováček

Burns

2014

Preprint

View full text Add to dashboard Cite

Background: Unlike full reading, 'skim-reading' involves the process of looking quickly over information in an attempt to cover more material whilst still being able to retain a superficial view of the underlying content. Within this work, we specifically emulate this natural human activity by providing a dynamic graph-based view of entities automatically extracted from text. For the extraction, we use shallow parsing, co-occurrence analysis and semantic similarity computation techniques. Our main motivation is to assist biomedical researchers and clinicians in coping with increasingly large amounts of potentially relevant articles that are being published ongoingly in life sciences. Methods: To construct the high-level network overview of articles, we extract weighted binary statements from the text. We consider two types of these statements, co-occurrence and similarity, both organised in the same distributional representation (i.e., in a vectorspace model). For the co-occurrence weights, we use point-wise mutual information that indicates the degree of non-random association between two co-occurring entities. For computing the similarity statement weights, we use cosine distance based on the relevant co-occurrence vectors. These statements are used to build fuzzy indices of terms, statements and provenance article identifiers, which support fuzzy querying and subsequent result ranking. These indexing and querying processes are then used to construct a graphbased interface for searching and browsing entity networks extracted from articles, as well as articles relevant to the networks being browsed. Last but not least, we describe a methodology for automated experimental evaluation of the presented approach. The method uses formal comparison of the graphs generated by our tool to relevant gold standards based on manually curated PubMed, TREC challenge and MeSH data. Results: We provide a web-based prototype (called 'SKIMMR') that generates a network of inter-related entities from a set of documents which a user may explore through our interface. When a particular area of the entity network looks interesting to a user, the tool displays the documents that are the most relevant to those entities of interest currently shown in the network. We present this as a methodology for browsing a collection of research articles. PrePrints SKIMMR: Machine-Aided Skim Reading 2 report on the results of experimental evaluation using the two domains and one additional dataset based on the TREC challenge. The results show that the presented method for machine-aided skim reading outperforms tools like PubMed regarding focused browsing and informativeness of the browsing context. Conclusions: Both conceptually and practically, the SKIMMR methodology instantiates the notion of 'skim reading' within software. In preliminary trials, sample users find new, interesting and non-trivial facts with the tool. A comprehensive experimental evaluation of the SKIMMR prototype using simulations of various types of browsing behaviour show...

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

SKIMMR: Facilitating knowledge discovery in life sciences by machine-aided skim reading

Nováček

Burns

2014

Preprint

View full text Add to dashboard Cite

show abstract

“…This means that lexical and distributional models of semantics provide complementary approach to data semantics on the web that comes into play when the creation of rich semantic models or their use is not feasible or too costly (e.g. [39]). …”

Section: Lexical and Distributional Semanticsmentioning

confidence: 99%

Data Semantics on the Web

Stuckenschmidt

2012

J Data Semant

View full text Add to dashboard Cite

Data Semantics is a wide area that continuously faces new challenges arising from the invention of new information formats and novel applications. An area that is particularly challenging with respect to identifying, representing and using data semantics is the Web. This paper attempts to characterize the nature and challenges of Data Semantics on the Web as an interesting research area to be covered by the Journal on Data Semantics.

show abstract

“…Distributional semantic models provide a complementary layer of meaning for structured data, which can be used to support semantic approximation for querying and reasoning over heterogeneous data (Novacek et al 2011;Freitas et al 2013;Freitas and Curry 2014).…”

Section: Large-scale Reasoningmentioning

confidence: 99%