Report on INEX 2013

Bellot, Patrice; Doucet, Antoine; Geva, Shlomo; Gurajada, Sairam; Kamps, Jaap; Kazai, Gabriella; Koolen, Marijn; Mishra, Abhisek; Mothe, Josiane; Preminger, Michael; SanJuan, Eric; Schenkel, Ralf; Tannier, Xavier; Theobald, Martin; Trappett, Matthew; Trotman, Andrew; Sanderson, Mark; Scholer, Falk; Wang, Q.

doi:10.1145/2568388.2568393

Cited by 9 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…stanford.edu/projects/glove/ 5 The data consists of an English Wikipedia dump from November 2012. It was released as a test collection for the INEX 2013 tweet contextualisation track [8] semantic network bins, 2 distances and 4 dimensional bins, we have 15 features per set of word embeddings, and 60 features in total per sentence pair, when, e.g., the 4 OoB sets are used.…”

Section: Feature Setsmentioning

confidence: 99%

Short Text Similarity with Word Embeddings

Kenter

Rijke

2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

356

240

View full text Add to dashboard Cite

Determining semantic similarity between texts is important in many tasks in information retrieval such as search, query suggestion, automatic summarization and image finding. Many approaches have been suggested, based on lexical matching, handcrafted patterns, syntactic parse trees, external sources of structured semantic knowledge and distributional semantics. However, lexical features, like string matching, do not capture semantic similarity beyond a trivial level. Furthermore, handcrafted patterns and external sources of structured semantic knowledge cannot be assumed to be available in all circumstances and for all domains. Lastly, approaches depending on parse trees are restricted to syntactically well-formed texts, typically of one sentence in length. We investigate whether determining short text similarity is possible using only semantic features-where by semantic we mean, pertaining to a representation of meaning-rather than relying on similarity in lexical or syntactic representations. We use word embeddings, vector representations of terms, computed from unlabelled data, that represent terms in a semantic space in which proximity of vectors can be interpreted as semantic similarity. We propose to go from word-level to text-level semantics by combining insights from methods based on external sources of semantic knowledge with word embeddings. A novel feature of our approach is that an arbitrary number of word embedding sets can be incorporated. We derive multiple types of meta-features from the comparison of the word vectors for short text pairs, and from the vector means of their respective word embeddings. The features representing labelled short text pairs are used to train a supervised learning algorithm. We use the trained model at testing time to predict the semantic similarity of new, unlabelled pairs of short texts. We show on a publicly available evaluation set commonly used for the task of semantic similarity that our method outperforms baseline methods that work under the same conditions.

show abstract

Section: Feature Setsmentioning

confidence: 99%

Short Text Similarity with Word Embeddings

Kenter

Rijke

2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

356

240

View full text Add to dashboard Cite

show abstract

“…For TextBenDS, we use as metric only the query response time. We note the response time for each query as t(Q i ) and t(Q i ) ∀i ∈ [1,4]. All queries Q 1 to Q 4 and Q 1 to Q 4 are executed 10 times for both top-k keywords and top-k documents, which is sufficient according to the central limit theorem.…”

Section: Performance Metrics and Execution Protocolmentioning

confidence: 99%

TextBenDS: a Generic Textual Data Benchmark for Distributed Systems

et al. 2020

View full text Add to dashboard Cite

Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, computation errors are introduced when analyzing only subsets of the dataset. Therefore, in a Big Data context, it is crucial to lower the runtime of computing weighting schemes, without hindering the analysis process and the accuracy of the machine learning algorithms. To address this requirement for the task of top-k keywords and documents, it is customary to design benchmarks that compare weighting schemes within various configurations of distributed frameworks and database management systems. Thus, we propose a generic document-oriented benchmark for storing textual data and constructing weighting schemes (TextBenDS). Our benchmark offers a generic data model designed with a multidimensional approach for storing text documents. We also propose using aggregation queries with various complexities and selectivities for constructing term weighting schemes, that are utilized in extracting top-k keywords and documents. We evaluate the computing performance of the queries on several distributed environments set within the Apache Hadoop ecosystem. Our experimental results provide interesting insights. As an example, MongoDB proves to have the best overall performance, while Spark's execution time remains almost the same, regardless of the weighting schemes.

show abstract

“…The general background of the INEX workshop is best summarized in INEX reports published within INEX workshops [24][25][26][27][28][29][30] and the SIGIR Forum [1,2,22], the biannual publication of the ACM Specific Interest Group on Information Retrieval (SIGIR). The evolution of the share of a http://pageperso.univ-lr.fr/antoine.doucet/structureExtraction/training.…”

Section: Related Publicationsmentioning

confidence: 99%

Logical Structure Extraction from Digitized Books

Doucet¹

2018

Series in Machine Perception and Artificial Intelligence

View full text Add to dashboard Cite

Mass digitization projects, such as the Million Book Project, efforts of the Open Content Alliance, and the digitization work of Google, are converting whole libraries by digitizing books on an industrial scale [5]. The process involves the efficient photographing of books, page-by-page, and the conversion of the image of each page into searchable text through the use of optical character recognition (OCR) software.Current digitization and OCR technologies typically produce the full text of digitized books with only minimal structure information. Pages and paragraphs are usually identified and marked up in the OCR, but more sophisticated structures, such as chapters, sections, etc., are not recognized. In order to enable systems to provide users with richer browsing experiences, it is necessary to make such additional structures available, for example, in the form of XML markup embedded in the full text of the digitized books.The Book Structure Extraction competition aims to address this need by promoting research into automatic structure recognition and extraction techniques that could complement or enhance current OCR methods and Document Analysis and Text Recognition Downloaded from www.worldscientific.com by UNIVERSITY OF HELSINKI on 11/26/20. Re-use and distribution is strictly not permitted, except for Open Access articles.

show abstract

Report on INEX 2013

Cited by 9 publications

References 5 publications

Short Text Similarity with Word Embeddings

Short Text Similarity with Word Embeddings

TextBenDS: a Generic Textual Data Benchmark for Distributed Systems

Logical Structure Extraction from Digitized Books

Contact Info

Product

Resources

About