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...
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 ...
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...
— 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...
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...