1 |
O.: Usefulness of sentiment analysis
|
|
|
|
In: http://www.diva-portal.org/smash/get/diva2%3A589140/FULLTEXT01.pdf (2012)
|
|
BASE
|
|
Show details
|
|
2 |
Information Access Evaluation meets Multilinguality, Multimodality, and Visual
|
|
|
|
In: http://sigir.org/forum/2012D/p029.pdf (2012)
|
|
BASE
|
|
Show details
|
|
3 |
Information Access Evaluation meets Multilinguality, Multimodality, and Visual
|
|
|
|
In: http://wwwhome.cs.utwente.nl/~hiemstra/papers/sigirforum12.pdf (2012)
|
|
BASE
|
|
Show details
|
|
4 |
Overview of iCLEF 2009: Exploring Search Behaviour in a Multilingual Folksonomy environment
|
|
|
|
In: http://clef.isti.cnr.it/2009/working_notes/iclef_overview_2009.pdf (2009)
|
|
BASE
|
|
Show details
|
|
5 |
Overview of iCLEF 2008: search log analysis for Multilingual Image Retrieval
|
|
|
|
In: http://ceur-ws.org/Vol-1174/CLEF2008wn-iCLEF-GonzaloEt2008.pdf (2008)
|
|
BASE
|
|
Show details
|
|
6 |
SICS: Valence Annotation based on Seeds in Word Space
|
|
|
|
In: http://www.sics.se/~jussi/Artiklar/2007_Semeval_Praha/cr/first_SICS.pdf (2007)
|
|
Abstract:
The SICS team used a resource-thrifty ap-proach for valence annotation based on a word-space model and a set of seed words. The model was trained on newsprint, and va-lence was computed using proximity to one of two manually defined points in a high-dimensional word space — one represent-ing positive valence, the other representing negative valence. By projecting each head-line into this space, choosing as valence the similarity score to the point that was closer to the headline, the experiment provided re-sults with high recall of negative or positive headlines. These results show that working without a high-coverage lexicon is a viable approach to content analysis of textual data. 1 Working without a lexicon Our approach takes as its starting point the obser-vation that lexical resources always are noisy, out of date, and most often suffer simultaneously from being both too specific and too general. For our ex-periments, our only lexical resource consists of a list of eight positive words and eight negative words, as shown below in Table 1. We use a medium-sized corpus of general newsprint to build a general word space, and use our minimal lexical resource to orient ourselves in it. 2 Word space A word space is a high-dimensional vector space built from distributional statistics, in which each word in the vocabulary is represented as a context vector ~v of occurrence frequencies, such as: ~vi = [fj, · · · , fn] where f is the (normally transformed) frequency of occurrence of word i in context j. The point of this representation is that semantic similarity between words can be computed using vector similarity mea-sures. The semantics of the word space are deter-mined by the data from which the occurrence infor-mation has been collected. The data in the SemEval Affective Text task con-sists of news headlines, which means that a relevant word space should be produced from topically sim-ilar texts, such as newswire documents. For this reason, we trained our model on a corpus of US newsprint which is available for experimentation for participants in the Cross Language Evaluation Fo-rum (CLEF).1 The corpus consists of some 100,000
|
|
URL: http://www.sics.se/~jussi/Artiklar/2007_Semeval_Praha/cr/first_SICS.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.1564
|
|
BASE
|
|
Hide details
|
|
7 |
Authors, genre, and linguistic convention
|
|
|
|
In: http://eprints.sics.se/913/1/authorsAndGenrePAN07.pdf (2007)
|
|
BASE
|
|
Show details
|
|
8 |
SICS: valence annotation based on seeds in word space
|
|
|
|
In: http://www.sics.se/~jussi/Artiklar/2007_Semeval_Praha/cr/second_SICS-letter.pdf (2007)
|
|
BASE
|
|
Show details
|
|
9 |
SICS: Valence annotation based on seeds in word space
|
|
|
|
In: http://acl.ldc.upenn.edu/w/w07/W07-2064.pdf (2007)
|
|
BASE
|
|
Show details
|
|
10 |
Authors, genre, and linguistic convention
|
|
|
|
In: http://www.sics.se/%7Ejussi/Artiklar/2007_SIGIR_Amsterdam/2007_SIGIR.pan.pdf (2007)
|
|
BASE
|
|
Show details
|
|
11 |
Multilingual interactive experiments with Flickr
|
|
|
|
In: http://www.sics.se/jussi/Artiklar/2006_NewText_Trento/Proceedings/working_notes/11_cloughEtAl.pdf (2006)
|
|
BASE
|
|
Show details
|
|
12 |
Effects of foreign language and task scenario on relevance assessment
|
|
|
|
In: http://www.sics.se/%7Ejussi/Artiklar/2005_JDoc_Xling/phjk.pdf (2005)
|
|
BASE
|
|
Show details
|
|
13 |
Mumbling – User-Driven Cooperative Interaction
|
|
|
|
In: http://www.sics.se/%7Ejussi/Artiklar/1994_TR_m/mumble.pdf (2005)
|
|
BASE
|
|
Show details
|
|
14 |
On sense and reference
|
|
|
|
In: http://www.sics.se/%7Ejussi/Artiklar/2002_NTCIR_Tokyo/NTCIR.pdf (2003)
|
|
BASE
|
|
Show details
|
|
15 |
English-Japanese Cross-lingual Query Expansion Using Random Indexing of Aligned Bilingual Text Data
|
|
|
|
In: http://www.sics.se/~preben/papers/ntcir2002/Sahlgren-Hansen-Karlgren-ntcir-2002.pdf (2002)
|
|
BASE
|
|
Show details
|
|
16 |
Statistics and Graphotactical Rules in Finding OCR-errors
|
|
|
|
In: http://stp.ling.uu.se/exarb/arch/2000-001.pdf (2000)
|
|
BASE
|
|
Show details
|
|
17 |
Statistics and Graphotactical Rules in Finding OCR-errors
|
|
|
|
In: http://stp.ling.uu.se/educa/thesis/arch/2000-001.ps (2000)
|
|
BASE
|
|
Show details
|
|
18 |
The Basics of Information Retrieval: Statistics and Linguistics
|
|
|
|
In: http://www.sics.se/~jussi/Undervisning/texter/ir-textbook.4.ps (2000)
|
|
BASE
|
|
Show details
|
|
19 |
Non-Topical Factors in Information Access
|
|
|
|
In: http://www.sics.se/~jussi/Artiklar/1999_Webnet_Honolulu/webnet.ps (1999)
|
|
BASE
|
|
Show details
|
|
20 |
Worlds Without Words
|
|
|
|
In: http://www.sics.se/~jussi/Papers/1994_ERCIM_Kista/ercim94.ps (1999)
|
|
BASE
|
|
Show details
|
|
|
|