On the negativity of negation
By Christopher Potts. 2010
97 citations recorded by the source corpus.
Natural language negation is persistently negative in the pragmatic sense, and emphatic and attenuating negative polarity items modulate this effect in systematic ways. I use large corpora of informal texts with meta-data approximating features of the context to characterize this pragmatic negativity, and I attempt to explain it in terms of the ways in which negative sentences engage the questions under discussion. The discussion highlights some of the ways in which quantitative corpus methods can be used to achieve novel results in linguistic pragmatics.
Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Literature and Literary Theory
View Paper: https://www.semanticscholar.org/paper/23072946b57bb808eee20e14799f1ffa43d84c01
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Richard Socher
- Mohit Bansal
- Christopher D. Manning
- Percy Liang
- Caiming Xiong
- Luke S. Zettlemoyer
- Samuel R. Bowman
- Jianfeng Gao
In Experimental and Cognitive Psychology
- Richard Socher
- Moritz Sudhof
- Daniel J. Wilson
- A. Shapiro
- Andrew Y. Ng
- Christopher D. Manning
- Christopher Potts
In Literature and Literary Theory
- Richard Socher
- Moritz Sudhof
- Daniel J. Wilson
- A. Shapiro
- Andrew Y. Ng
- Christopher D. Manning
- Christopher Potts
Citations in the corpus
- Measuring news sentiment (2020, methodology): “2See Socher, Pennington, Huang, Ng, and Manning (2011), Potts (2010), and Sudhof, Goméz Emilsson, Maas, and Potts (2014).”
- Semantic Compositionality through Recursive Matrix-Vector Spaces (2012, background): “For instance not great is still pretty good and not terrible ; see Potts (2010) for details.”
- Recursive deep learning for natural language processing and computer vision (2014, background): “I also show results on the experience project (EP) dataset (Potts, 2010) that captures a broader spectrum of human sentiments and emotions.”
- Multi-Dimensional Sentiment Analysis with Learned Representations (2012, background): “There are many intuitive correlations between the authors’ word choices and readers’ reaction responses (Potts, 2010).”
- Sentiment Analysis: An Overview from Linguistics (2016, unknown): “36 million reviews in a corpus from the Internet Movie Database (Potts 2011).”
- Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions (2011, background): “Furthermore, we show results on the recently introduced experience project (EP) dataset (Potts, 2010) that captures a broader spectrum of human sentiments and emotions.”