Learn More
Non-expert annotation services like Amazon’s Mechanical Turk (AMT) are cheap and fast ways to evaluate systems and provide categorical annotations for training data. Unfortunately, some annotators choose bad labels in order to maximize their pay. Manual identification is tedious, so we experiment with an item-response model. It learns in an unsupervised(More)
A metaphor is a figure of speech that refers to one concept in terms of another, as in “He is such a sweet person”. Metaphors are ubiquitous and they present NLP with a range of challenges for WSD, IE, etc. Identifying metaphors is thus an important step in language understanding. However, since almost any word can serve as a metaphor, they are impossible(More)
We present two Twitter datasets annotated with coarse-grained word senses (supersenses), as well as a series of experiments with three learning scenarios for supersense tagging: weakly supervised learning, as well as unsupervised and supervised domain adaptation. We show that (a) off-the-shelf tools perform poorly on Twitter, (b) models augmented with(More)
Hate speech in the form of racist and sexist remarks are a common occurrence on social media. For that reason, many social media services address the problem of identifying hate speech, but the definition of hate speech varies markedly and is largely a manual effort (BBC, 2015; Lomas, 2015). We provide a list of criteria founded in critical race theory, and(More)
We experiment with using different sources of distant supervision to guide unsupervised and semi-supervised adaptation of part-of-speech (POS) and named entity taggers (NER) to Twitter. We show that a particularly good source of not-so-distant supervision is linked websites. Specifically, with this source of supervision we are able to improve over the(More)
Choosing the right parameters for a word sense disambiguation task is critical to the success of the experiments. We explore this idea for prepositions, an often overlooked word class. We examine the parameters that must be considered in preposition disambiguation, namely context, features, and granularity. Doing so delivers an increased performance that(More)
We present a simple method for learning part-of-speech taggers for languages like Akawaio, Aukan, or Cakchiquel – languages for which nothing but a translation of parts of the Bible exists. By aggregating over the tags from a few annotated languages and spreading them via wordalignment on the verses, we learn POS taggers for 100 languages, using the(More)
We develop a supersense taxonomy for adjectives, based on that of GermaNet, and apply it to English adjectives in WordNet using human annotation and supervised classification. Results show that accuracy for automatic adjective type classification is high, but synsets are considerably more difficult to classify, even for trained human annotators. We release(More)
We present a preliminary study on unsupervised preposition sense disambiguation (PSD), comparing different models and training techniques (EM, MAP-EM with L0 norm, Bayesian inference using Gibbs sampling). To our knowledge, this is the first attempt at unsupervised preposition sense disambiguation. Our best accuracy reaches 56%, a significant improvement(More)