1. |
- Demidova, Elena, et al.
(författare)
-
Analysing Entities, Topics and Events in Community Memories.
- 2013
-
Ingår i: Proc. of the first International Workshop on Archiving Community Memories.
-
Konferensbidrag (refereegranskat)abstract
- his paper briefly describes the components of the ARCOMEM architecture concerned with the extraction, enrichment, consolidation and dynamics analysis of entities, topics and events, deploying text mining, NLP, and semantic data integration technologies. In particular, we focus on four main areas relevant to support the ARCOMEM requirements and use cases: (a) entity and event extraction from text; (b) entity and event enrichment and consolidation; (c) topicdetection and dynamics; and (d) temporal aspects and dynamics detection in Web language and online social networks.
|
|
2. |
|
|
3. |
|
|
4. |
- Holzmann, Helge, et al.
(författare)
-
BlogNEER: Applying Named Entity Evolution Recognition on the Blogosphere
- 2013
-
Ingår i: CEUR Workshop Proceedings. - 1613-0073. ; 1091, s. 28-39
-
Konferensbidrag (refereegranskat)abstract
- The introduction of Social Media allowed more people to publish texts by removing barriers that are technical but also social such as the editorial controls that exist in traditional media. The resulting language tends to be more like spoken language because people adapt their use to the medium. Since spoken language is more dynamic, more new and short lived terms are introduced also in written format on the Web. In teTahmasebi2012 we presented an unsupervised method for Named Entity Evolution Recognition (NEER) to find name changes in newspaper collections. In this paper we present BlogNEER, an extension to apply NEER on blog data. The language used in blogs is often closer to spoken language than to language used in traditional media. BlogNEER introduces a novel semantic filtering method that makes use of Semantic Web resources (i.e., DBpedia) to gain more information about terms. We present the approach of BlogNEER and initial results that show the potentials of the approach.
|
|
5. |
- Holzmann, Helge, et al.
(författare)
-
Named entity evolution recognition on the Blogosphere
- 2015
-
Ingår i: International Journal on Digital Libraries. - : Springer Science and Business Media LLC. - 1432-5012 .- 1432-1300. ; 15:2-4, s. 209-235
-
Tidskriftsartikel (refereegranskat)abstract
- Advancements in technology and culture lead to changes in our language. These changes create a gap between the language known by users and the language stored in digital archives. It affects user’s possibility to firstly find content and secondly interpret that content. In a previous work, we introduced our approach for named entity evolution recognition (NEER) in newspaper collections. Lately, increasing efforts in Web preservation have led to increased availability of Web archives covering longer time spans. However, language on the Web is more dynamic than in traditional media and many of the basic assumptions from the newspaper domain do not hold for Web data. In this paper we discuss the limitations of existing methodology for NEER. We approach these by adapting an existing NEER method to work on noisy data like the Web and the Blogosphere in particular. We develop novel filters that reduce the noise and make use of Semantic Web resources to obtain more information about terms. Our evaluation shows the potentials of the proposed approach.
|
|
6. |
|
|
7. |
|
|
8. |
- Tahmasebi, Nina, 1982, et al.
(författare)
-
Finding Individual Word Sense Changes and their Delay in Appearance
- 2017
-
Ingår i: Proceedings of Recent Advances in Natural Language Processing 2017. Varna, Bulgaria 2–8 September, 2017 / edited by Galia Angelova, Kalina Bontcheva, Ruslan Mitkov, Ivelina Nikolova, Irina Temnikova. - : Incoma Ltd. Shoumen, Bulgaria. - 1313-8502 .- 2603-2813. - 9789544520489
-
Konferensbidrag (refereegranskat)abstract
- We present a method for detecting word sense changes by utilizing automatically induced word senses. Our method works on the level of individual senses and allows a word to have e.g. one stable sense and then add a novel sense that later experiences change. Senses are grouped based on polysemy to find linguistic concepts and we can find broadening and narrowing as well as novel (polysemous and homonymic) senses. We evaluate on a testset, present recall and estimates of the time between expected and found change.
|
|
9. |
- Tahmasebi, Nina, 1982, et al.
(författare)
-
On the Uses of Word Sense Change for Research in the Digital Humanities
- 2017
-
Ingår i: Research and Advanced Technology for Digital Libraries - 21st International Conference on Theory and Practice of Digital Libraries, TPDL 2017, Thessaloniki, Greece, September 18-21, 2017. Proceedings / edited by Jaap Kamps, Giannis Tsakonas, Yannis Manolopoulos, Lazaros Iliadis, Ioannis Karydis. - Cham : Springer Verlag. - 1611-3349. - 9783319670072
-
Konferensbidrag (refereegranskat)abstract
- With advances in technology and culture, our language changes. We invent new words, add or change meanings of existing words and change names of existing things. Unfortunately, our language does not carry a memory; words, expressions and meanings used in the past are forgotten over time. When searching and interpreting content from archives, language changes pose a great challenge. In this paper, we present results of automatic word sense change detection and show the utility for archive users as well as digital humanities’ research. Our method is able to capture changes that relate to the usage and culture of a word that cannot easily be found using dictionaries or other resources.
|
|
10. |
- Tahmasebi, Nina, 1982, et al.
(författare)
-
The Role of Language Evolution in Digital Archives
- 2013
-
Ingår i: CEUR Workshop Proceedings. - 1613-0073. ; 1091, s. 16-27
-
Konferensbidrag (refereegranskat)abstract
- With advancements in technology and culture, our languagechanges. We invent new words, add or change meanings of existing words and change names of existing things. Left untackled, these changes in language create a gap between the language known by users and the language stored in our digital archives. In particular, they affect our possibility to firstly find and content and secondly interpret that content. In this paper we discuss the limitations brought on by language evolution and existing methodology for automatically finding evolution. We discuss measured needed in the near future to ensure semantically accessible digital archives for long-term preservation.
|
|