TCS
2010
13 years 7 months ago
2010
A text is a word together with an additional linear order on it. We study quantitative models for texts, i.e. text series which assign to texts elements of a semiring. We introduc...
EMNLP
2009
13 years 10 months ago
2009
Measuring the similarity between two texts is a fundamental problem in many NLP and IR applications. Among the existing approaches, the cosine measure of the term vectors represen...
EMNLP
2010
13 years 10 months ago
2010
Almost all Chinese language processing tasks involve word segmentation of the language input as their first steps, thus robust and reliable segmentation techniques are always requ...
MT
2007
13 years 11 months ago
2007
This paper describes the framework of the StatCan Daily Translation Extraction System (SDTES), a computer system that maps and compares webbased translation texts of Statistics Can...
JQL
2007
14 years 5 days ago
2007
How can it be said that texts are "near" or "distant" from one another? Are different texts by a single author more similar than texts by different authors? To...
IPM
2008
14 years 9 days ago
2008
Authorship analysis of electronic texts assists digital forensics and anti-terror investigation. Author identification can be seen as a single-label multi-class text categorizatio...
NAACL
1994
14 years 1 months ago
1994
The functionality of systems that extract information from texts can be specified quite simply: the input is a stream of texts and the output is some representation of the informa...
COLING
1994
14 years 1 months ago
1994
To align bilingual texts becomes a crucial issue recently. Rather than using length-based or translation-based criterion, a part-of-speech-based criterion is proposed. We postulat...
ECIR
2003
Springer
14 years 1 months ago
2003
Springer
This paper explores the use of texts that are related to an image collection, also known as collateral texts, for building thesauri in specialist domains to aid in image retrieval....
AAAI
2008
14 years 2 months ago
2008
Classification of texts potentially containing a complex and specific terminology requires the use of learning methods that do not rely on extensive feature engineering. In this w...