Focused retrieval with proximity scoring

Beigbeder, Michel

doi:10.1145/1774088.1774462

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To cope with the variation of such structure, we define two types of document parts: sections, i.e., non-textual units with a title, and passages, textual units without titles. The intra-document relations considered are: (1) the order of passages [4,7,15,28],…”

Section: Document Graph Representationmentioning

confidence: 99%

“…We study here how to perform passage contextualization with methods akin to neural IR, as their expressive power have created a gap in performances compared with classical methods [10]. Multiple approaches represent a passage's context based on the various types of relations it has with other parts of the document [1,4,7,15,23,24,28]. We investigate how such a representation, encoded as a graph, may be leveraged by graph neural networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Passage Retrieval on Structured Documents Using Graph Attention Networks

Albarede

Mulhem

Goeuriot

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Passage Retrieval systems aim at retrieving and ranking small text units according to their estimated relevance to a query. A usual practice is to consider the context a passage appears in (its containing document, neighbour passages, etc.) to improve its relevance estimation. In this work, we study the use of Graph Attention Networks (GATs), a graph node embedding method, to perform passage contextualization. More precisely, we first propose a document graph representation based on several inter-and intra-document relations. Then, we investigate two ways of leveraging the use of GATs on this representation in order to incorporate contextual information for passage retrieval. We evaluate our approach on a Passage Retrieval task for structured documents: CLEF-IP2013. Our results show that our document graph representation coupled with the expressive power of GATs allows for a better context representation leading to improved performances.

show abstract

Section: Document Graph Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Passage Retrieval on Structured Documents Using Graph Attention Networks

Albarede

Mulhem

Goeuriot

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The third and last proposal integrates the structure in the Beigbeder and Mercier's proximity model for flat documents and for two usages: the first one is the definition of logical units to be returned to the user, and the second one is the enlargement of the influence function range over whole sections when query terms appear in the title of the elements. However non logical tags are not taken into account in this work (Beigbeder 2010).…”

Section: Proximity and Structurementioning

confidence: 99%

“…Only Broschart and Schenkel (2008) and Beigbeder (2010) proposed methods to achieve focused retrieval. Moreover, only that of Beigbeder proved its effectiveness in this context.…”

Section: Proximity and Structurementioning

confidence: 99%

Using proximity and tag weights for focused retrieval in structured documents

2014

Self Cite

View full text Add to dashboard Cite

Focused information retrieval is concerned with the retrieval of small units of information. In this context, the structure of the documents as well as the proximity among query terms have been found useful for improving retrieval effectiveness. In this article, we propose an approach combining the proximity of the terms and the tags which mark these terms. Our approach is based on a Fetch and Browse method where the fetch step is performed with BM25 and the browse step with a structure enhanced proximity model. In this way, the ranking of a document depends not only upon the existence of the query terms within the document but also upon the tags which mark these terms. Thus, the document tends to be highly relevant when query terms are close together and are emphasized by tags. The evaluation of this model on a large XML structured collection provided by the INEX 2010 XML IR evaluation campaign shows that the use of term proximity and structure improves the retrieval effectiveness of BM25 in the context of focused information retrieval.

show abstract

“…The work most related to ours is that of Beigbeder who applied proximity scoring for focused retrieval [5]. Each position in the text is assigned with a proximity value depending on its distance from the query terms.…”

Section: Related Workmentioning

confidence: 99%

Position-based contextualization for passage retrieval

Carmel¹,

Shtok

Kurland

2013

Proceedings of the 22nd ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

We present a novel contextualization approach for passage retrieval. The core principle is to let any occurrence of a query term in a document affect the passage retrieval score, whether the occurrence is in the passage or not. This effect is controlled by the distance between the term occurrence and the passage. Empirical evaluation demonstrates the merits of our approach; the resultant retrieval performance substantially transcends that of previously proposed passage retrieval methods, including those that use various contextualization approaches.

show abstract

Focused retrieval with proximity scoring

Cited by 7 publications

References 11 publications

Passage Retrieval on Structured Documents Using Graph Attention Networks

Passage Retrieval on Structured Documents Using Graph Attention Networks

Using proximity and tag weights for focused retrieval in structured documents

Position-based contextualization for passage retrieval

Contact Info

Product

Resources

About