We analyzed 700 million words, phrases, and topic instances collected from the Facebook
messages of 75,000 volunteers, who also took standard personality tests, and found striking …

Measuring the similarity between words, sentences, paragraphs and documents is an
important component in various tasks such as information retrieval, document clustering …

Abstract Language data available through social media provide opportunities to study
people at an unprecedented scale. However, little guidance is available to psychologists …

The Handbook of Natural Language Processing, Second Edition presents practical tools
and techniques for implementing natural language processing in computer systems. Along …

The concept of collocations is certainly one of the most controversial notions in linguis-3 tics,
even though it is based on a compelling, widely-shared intuition that certain words 4 have a …

2.1 List of special situations for the comparison of different coefficients of association
strength. The symbol ǫ in Equations B and E indicates a first-order approximation for ǫ→ …

• San Francisco, ad hoc, by and large, Where Eagles Dare, kick the bucket, part of speech, in
step, the Oakland Raiders, trip the light fantastic, telephone box, call (someone) up, take a …

In this paper, we propose an unsupervised method for discovering inference rules from text,
such as" X is author of Y≈ X wrote Y"," X solved Y≈ X found a solution to Y", and" X caused …

One of the main challenges in question-answering is the potential mismatch between the
expressions in questions and the expressions in texts. While humans appear to use …

Statistical supervised learning techniques have been successful for many natural language
processing tasks, but they require labeled datasets, which can be expensive to obtain. On …