Keyword Extraction Using Word Co-occurrence

Wartena, Christian; Brussee, Rogier; Slakhorst, Wout

doi:10.1109/dexa.2010.32

Cited by 49 publications

(27 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using intra-document term distributions, the authors report performances that approximate those of tf/idf -based methods. Wartena et al [22] propose to infer keyword candidates from the semantic relationships between terms in academic abstracts and BBC news stories. Tomokiyo et al [21] present a language modelling approach to keyword extraction from longer coherent news articles.…”

Section: Related Workmentioning

confidence: 99%

Exploiting User Comments for Audio-Visual Content Indexing and Retrieval

Eickhoff

Vries

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. State-of-the-art content sharing platforms often require users to assign tags to pieces of media in order to make them easily retrievable. Since this task is sometimes perceived as tedious or boring, annotations can be sparse. Commenting on the other hand is a frequently used means of expressing user opinion towards shared media items. This work makes use of time series analyses in order to infer potential tags and indexing terms for audio-visual content from user comments. In this way, we mitigate the vocabulary gap between queries and document descriptors. Additionally, we show how large-scale encyclopaedias such as Wikipedia can aid the task of tag prediction by serving as surrogates for high-coverage natural language vocabulary lists. Our evaluation is conducted on a corpus of several million real-world user comments from the popular video sharing platform YouTube, and demonstrates significant improvements in retrieval performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Exploiting User Comments for Audio-Visual Content Indexing and Retrieval

Eickhoff

Vries

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…There are various options to compute the similarity between two distributions. In [13] we have shown that the following correlation coefficient gives the best results:…”

Section: Co-occurrence Based Keyword Extractionmentioning

confidence: 93%

“…We have motivated and presented this method in detail in [13]. The basic idea is that we represent each term t by a distribution of terms that is typical for the documents in which t occurs.…”

Section: Keyword Extractionmentioning

confidence: 99%

Selecting keywords for content based recommendation

Wartena

Slakhorst

Wibbels

2010

Proceedings of the 19th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

The continued growth of online content makes personalized recommendation an increasingly important tool for media consumption. While collaborative filtering techniques have shown to be very successful in stable collections, content based approaches are necessary for recommending new items. Content based recommendation uses the similarity between new items and consumed items to predict whether a new item is interesting for the user. The similarity is computed by comparing the content or the meta-data of the items. In this paper we consider recommendation of TVbroadcasts for which meta-data and synopses are available. We thereby concentrate on the new item problem. We investigate the value of different types of meta-data provided by the broadcaster or extracted from synopsis. We show that extracted keywords are better suited for recommendation than manually assigned keywords. Furthermore we show that the number of keywords used is of great importance. Using a rather small number of keywords to present an item yields the best results for recommendation.

show abstract

“…Most labels used as queries in this task are given in plural form and are reduced to singular form for matching with the base forms. More details on the model can be found in [38,39]. Assuming that q is a term like other terms, we also call this distribution the co-occurrence distribution of q.…”

Section: Algorithm and Resultsmentioning

confidence: 99%

Automatic tagging and geotagging in video collections and communities

Larson

Soleymani

Serdyukov

et al. 2011

Proceedings of the 1st ACM International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Automatically generated tags and geotags hold great promise to improve access to video collections and online communities. We overview three tasks offered in the MediaEval 2010 benchmarking initiative, for each, describing its use scenario, definition and the data set released. For each task, a reference algorithm is presented that was used within MediaEval 2010 and comments are included on lessons learned. The Tagging Task, Professional involves automatically matching episodes in a collection of Dutch television with subject labels drawn from the keyword thesaurus used by the archive staff. The Tagging Task, Wild Wild Web involves automatically predicting the tags that are assigned by users to their online videos. Finally, the Placing Task requires automatically assigning geo-coordinates to videos. The specification of each task admits the use of the full range of available information including user-generated metadata, speech recognition transcripts, audio, and visual features.

show abstract

Keyword Extraction Using Word Co-occurrence

Cited by 49 publications

References 17 publications

Exploiting User Comments for Audio-Visual Content Indexing and Retrieval

Exploiting User Comments for Audio-Visual Content Indexing and Retrieval

Selecting keywords for content based recommendation

Automatic tagging and geotagging in video collections and communities

Contact Info

Product

Resources

About