Results 251 to 260 of about 40,470,474 (303)
Some of the next articles are maybe not open access.
Societal Versus Encoded Stereotypes in Text Encoders
2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI), 2023Text encoders have recently been convicted of en-coding unjustified social stereotypes, which lead models to make biased and prejudiced predictions when trained on downstream tasks such as sentiment analysis or question answering. The presence of bias in NLP models is dangerous since it promotes the divide between different social groups.
Yacine Gaci +3 more
openaire +2 more sources
Computers and the Humanities, 1995
This article identifies problems and proposes solutions for encoding verse texts in SGML. It is organized around a series of distinctions and oppositions which the TEI Work Group on Verse regard as significant. These include examination of the formal properties which distinguish verse from prose, followed by discussions of (1) text-searching vs ...
David Chisholm, David Robey
openaire +2 more sources
This article identifies problems and proposes solutions for encoding verse texts in SGML. It is organized around a series of distinctions and oppositions which the TEI Work Group on Verse regard as significant. These include examination of the formal properties which distinguish verse from prose, followed by discussions of (1) text-searching vs ...
David Chisholm, David Robey
openaire +2 more sources
Encoding Video Narration as Text
Real-Time Imaging, 2000Summary: The paper describes a solution to the problem of transmitting ``talking head'' video in real-time across low-bandwidth transmission media. Our solution is based on a video reconstruction system, which can generate realistic audio-visual narrations from arbitrary pieces of text.
Stephen Welsh, Damian Conway
openaire +3 more sources
Computers and the Humanities, 1995
There is a great deal of variation in the encoding of spoken texts in electronic form, both with respect to the types of features represented and the way particular features are rendered. This paper surveys problems in the electronic representation of speech and presents the solutions proposed by the Text Encoding Initiative.
openaire +2 more sources
There is a great deal of variation in the encoding of spoken texts in electronic form, both with respect to the types of features represented and the way particular features are rendered. This paper surveys problems in the electronic representation of speech and presents the solutions proposed by the Text Encoding Initiative.
openaire +2 more sources
Predictive encoding in text compression
Information Processing & Management, 1989Abstract In predictive text compression the characters are encoded one by one on the basis of a few preceding characters. The usage of contextual knowledge makes the compression more effective than the plain coding of characters independently of their neighbors.
Timo Raita, Jukka Teuhola
openaire +1 more source