Sciweavers

390 search results - page 56 / 78
» Are Ontologies Involved in Natural Language Processing
Sort
View
135
Voted
EMNLP
2010
15 years 1 months ago
Negative Training Data Can be Harmful to Text Classification
This paper studies the effects of training data on binary text classification and postulates that negative training data is not needed and may even be harmful for the task. Tradit...
Xiaoli Li, Bing Liu, See-Kiong Ng
137
Voted
EMNLP
2009
15 years 1 months ago
Review Sentiment Scoring via a Parse-and-Paraphrase Paradigm
This paper presents a parse-and-paraphrase paradigm to assess the degrees of sentiment for product reviews. Sentiment identification has been well studied; however, most previous ...
Jingjing Liu, Stephanie Seneff
154
Voted
EMNLP
2009
15 years 1 months ago
Feasibility of Human-in-the-loop Minimum Error Rate Training
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
Omar Zaidan, Chris Callison-Burch
147
Voted
ICDE
2008
IEEE
200views Database» more  ICDE 2008»
15 years 10 months ago
Enforcing security in semantics driven policy based networks
— Security is emerging as an important requirement for a number of distributed applications such as online banking, social networking etc. due to the private nature of the data b...
Palanivel Balaji Kodeswaran, Sethuram Balaji Kodes...
144
Voted
AAAI
2007
15 years 6 months ago
Learning by Reading: A Prototype System, Performance Baseline and Lessons Learned
A traditional goal of Artificial Intelligence research has been a system that can read unrestricted natural language texts on a given topic, build a model of that topic and reason...
Ken Barker, Bhalchandra Agashe, Shaw Yi Chaw, Jame...