Report on INEX 2009

Beckers, Thomas; Bellot, Patrice; Demartini, Gianluca; Denoyer, Ludovic; Vries, Christopher M. De; Doucet, Antoine; Fachry, Khairun Nisa; Fuhr, Norbert; Gallinari, Patrick; Geva, Shlomo; Huang, Wei Che; Iofciu, Tereza; Kamps, Jaap; Kazai, Gabriella; Koolen, Marijn; Kutty, Sangeetha; Landoni, Monica; Lehtonen, Miro; Nayak, Richi; Nordlie, Ragnar; Pharo, Nils; SanJuan, Eric; Schenkel, Ralf; Tannier, Xavier; Theobald, Martin; Thom, James A.; Trotman, Andrew; Vries, Arjen P. de

doi:10.1145/1842890.1842897

Cited by 8 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Social Book Search (SBS) (Koolen et al 2012) was another new track but a direct descendant of the INEX 2011 Books and Social Search Track, and the earlier Book Search Tracks (since 2007). Although the traditional out-of-copyright, full-text books still were continued as a task by special demand of those interested, the focus clearly shifted to the social book data, coming from Amazon and LibraryThing and originally constructed to support the INEX Interactive Track (running 2004-2010, including real-world complex book search requests, user profiles and personal book catalogues.…”

Section: Clef 2012mentioning

confidence: 99%

“…Second, a new track on Contextual Suggestion was started, running at the Text REtrieval Conference (TREC) 2012 (Dean- Hall et al 2012), rather than at CLEF, to attract a wider attendance. This track was a direct result of the SIGIR 2011 workshop on Supporting Complex Search Tasks: Entertain Me (Belkin et al 2011), which in turn was a spin-off of discussion at INEX 2010 (Beckers et al 2010).…”

Section: Clef 2012mentioning

confidence: 99%

See 1 more Smart Citation

From XML Retrieval to Semantic Search and Beyond

Kamps

Koolen

Geva³

et al. 2019

The Information Retrieval Series

View full text Add to dashboard Cite

INEX ran as an independent evaluation forum for 10 years before it teamed up with CLEF in 2012. Even before 2012 there was considerable collaboration between INEX and CLEF, and these collaborations increased in intensity when CLEF moved beyond its traditional cross-lingual focus in 2009/2010 shifting to include all experimental IR. This led to the merger of CLEF and INEX, and effectively to the inclusion of INEX as a large track or lab into CLEF in 2012. This chapter details the efforts of the INEX lab in CLEF (2012CLEF ( -2014, as well as the ongoing activities as separate labs, under the labels Social Book Search ), and Microblog Contextualization (2016-2018.

show abstract

Section: Clef 2012mentioning

confidence: 99%

Section: Clef 2012mentioning

confidence: 99%

From XML Retrieval to Semantic Search and Beyond

Kamps

Koolen

Geva³

et al. 2019

The Information Retrieval Series

View full text Add to dashboard Cite

show abstract

“…More recent algorithms focus on automatic TOC extraction where the goal is to parse this hierarchical structure of sections and subsections from the TOC pages embedded in the document. Most of the research developed in this area has been linked to the INEX [8] and ICDAR competitions [9], [10], [11] which target old and long OCR-ised books instead of small papers as for the previous methods. Outside these competitions, we find the methods proposed by Elhaj et al [12], [13], based also in TOC page parsing.…”

Section: Introductionmentioning

confidence: 99%

“…The second type gives for granted a TOC page [9], [10], which may not appear in the document. We do not assume either the presence of a TOC page that can be parsed.…”

Section: Introductionmentioning

confidence: 99%

Table-Of-Contents generation on contemporary documents

Bentabet¹,

Juge²,

Ferradans³

2019

Preprint

View full text Add to dashboard Cite

The generation of precise and detailed Table-Of-Contents (TOC) from a document is a problem of major importance for document understanding and information extraction. Despite its importance, it is still a challenging task, especially for non-standardized documents with rich layout information such as commercial documents. In this paper, we present a new neuralbased pipeline for TOC generation applicable to any searchable document. Unlike previous methods, we do not use semantic labeling nor assume the presence of parsable TOC pages in the document. Moreover, we analyze the influence of using external knowledge encoded as a template. We empirically show that this approach is only useful in a very low resource environment. Finally, we propose a new domain-specific data set that sheds some light on the difficulties of TOC generation in real-world documents. The proposed method shows better performance than the state-of-the-art on a public data set and on the newly released data set.

show abstract

“…The INitiative for the Evaluation of XML Retrieval (INEX) [3,22] prepared in 2009 the INEX Wikipedia Collection [50], an XML-ified and semanticallyenriched version of the English Wikipedia. The 2009 INEX Wikipedia collection has been considerably exploited to investigate several aspects of XML retrieval, including mixing contentoriented and structure-oriented queries as well as focusing on efficiency [4,23,51]. This domain only focuses on the descendants query primitive.…”

Section: Introductionmentioning

confidence: 99%