Overview of 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; Wang, Qiuyue

doi:10.1007/978-3-642-40802-1_27

Cited by 17 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that Wikipedia typically refers to only a single source per statement, this initial experiment will have to be complemented by a user study. As in our previous user studies [6,24,25], we plan to use result pooling and crowd-source relevance assessments.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Linking Today's Wikipedia and News from the Past

Mishra

2014

Proceedings of the 7th Workshop on Ph.D Students

Self Cite

View full text Add to dashboard Cite

In this paper we propose a novel task of automatically linking Wikipedia excerpts describing events to past news articles. Constantly evolving Wikipedia articles tend to summarize past events by abstracting fine-grained details that mattered when the event happened. On the other hand, contemporary news articles provide details of events, as they had happened. With connections between these two orthogonal information sources in place, a user could jump between them to acquire a holistic view on past events. We cast the linking problems into two retrieval tasks and propose a single framework for addressing them. In addition, we delineate challenges involved in both these tasks and propose a framework to address these challenges.To build a better understanding of the problem, we initially consider the simpler task of linking Wikipedia events that are systematically curated into years, decades and centuries, to relevant news articles from the past. These events come with a short textual description and a date indicating when the event happened. We present a two-stage cascade approach that leverages the temporal information associated to a given event for improving the linking effectiveness. We additionally design several baselines and show that our approach outperforms all the baselines. Through the results of studying the simplified task we come a step closer to solving the larger problem proposed in this paper. As future work, we plan to build an automatic linking system that answers to the challenges identified in this paper.

show abstract

Section: Discussionmentioning

confidence: 99%

“…As a final baseline method, we combine the above approaches and rank documents according to P (q | d t ) = P (qtext | dtext ) · P (qtime | t) · P (qtime | dtime ) (6) with factors as defined in Equations (1), (3), and (5).…”

Section: Time-aware Language Modelsmentioning

confidence: 99%

Linking Today's Wikipedia and News from the Past

Mishra

2014

Proceedings of the 7th Workshop on Ph.D Students

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each of these corpora has 100 original texts and for each document 20 permutations (2000 in total). We compared our accuracy results with those reported in the literature, namely entity grid models (Content + Egrid, Content + HMM-prodn, Content + HMM-d-seq, Egrid + HMM-prodn, Egrid + HMM-d-seq, 2 terrier.org is a search engine platform developed by the University of Glasgow Egrid + Content + HMM-prodn, Egrid + Content + HMM-dseq, Egrid + Content + HMM-prodn + HMM-d-seq) 3 , discourse relation based approaches (Type+Arg+Sal,Arg+Sal, Type+Sal, Type+Arg, Baseline+Type+Arg+Sal) 4 , probabilistic content model (Probabilistic content) 5 and topic based model (Topic-relaxed) 5 . In Table 1, O, R, R1 and R2 refer to the initial sentence order and the permutations described above and O > /< /= R• shows the proportion of times where initial order was scored higher/lower/equally than/to permuted text for the best set of parameter values w t t = 0.25, w ct = 0.5, w tc = 0.75, and w cc = 1.…”

Section: Discussionmentioning

confidence: 99%

“…ese examples illustrate that appropriate SO is crucial for readability. Automatic text generation, particularly multi-document extractive summarization, systems also face SO problem [3,4]. We distinguish two DOI: h p://dx.doi.org/10.1145/3077136.3080720 of sentences and (2) to measure the order quality, i.e.…”

Section: Introductionmentioning

confidence: 99%

A Metric for Sentence Ordering Assessment Based on Topic-Comment Structure

Ermakova

Mothe

Firsov

2017

Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

Sentence ordering (SO) is a key component of verbal ability. It is also crucial for automatic text generation. While numerous researchers developed various methods to automatically evaluate the informativeness of the produced contents, the evaluation of readability is usually performed manually. In contrast to that, we present a selfsu cient metric for SO assessment based on text topic-comment structure. We show that this metric has high accuracy.

show abstract

“…INEX (2012-2014) was a stand-alone initiative pioneering structured and XML retrieval from 2002 6 ; it joined forces with CLEF in 2012 to further promote the evaluation of focused retrieval by providing large test collections of structured documents [28,29,54,137,236,253,267];…”

Section: Tracks and Labsmentioning

confidence: 99%

CLEF 15th Birthday

Ferro

2014

SIGIR Forum

View full text Add to dashboard Cite

2014 marks the 15 th birthday for CLEF, an evaluation campaign activity which has applied the Cranfield evaluation paradigm to the testing of multilingual and multimodal information access systems in Europe. This paper provides a summary of the motivations which led to the establishment of CLEF, and a description of how it has evolved over the years, the major achievements, and what we see as the next challenges.1 http://www.clef-initiative.eu/ 2 http://trec.nist.gov/ 3

show abstract

Overview of INEX 2013

Abstract: OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible.

Cited by 17 publications

References 8 publications

Linking Today's Wikipedia and News from the Past

Linking Today's Wikipedia and News from the Past

A Metric for Sentence Ordering Assessment Based on Topic-Comment Structure

CLEF 15th Birthday

Contact Info

Product

Resources

About