Learn More
We present two Twitter datasets annotated with coarse-grained word senses (super-senses), as well as a series of experiments with three learning scenarios for super-sense 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)
Relation Extraction (RE) is the task of extracting semantic relationships between entities in text. Recent studies on relation extraction are mostly supervised. The clear drawback of supervised methods is the need of training data: labeled data is expensive to obtain, and there is often a mismatch between the training data and the data the system will be(More)
We present a novel, count-based approach to obtaining inter-lingual word representations based on inverted indexing of Wikipedia. We present experiments applying these representations to 17 datasets in document classification, POS tagging, dependency parsing, and word alignment. Our approach has the advantage that it is simple, computationally efficient 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)
In NLP, we need to document that our proposed methods perform significantly better with respect to standard metrics than previous approaches, typically by reporting p-values obtained by rank-or randomization-based tests. We show that significance results following current research standards are unreliable and, in addition , very sensitive to sample size,(More)
Crowdsourcing lets us collect multiple annotations for an item from several annota-tors. Typically, these are annotations for non-sequential classification tasks. While there has been some work on crowdsourc-ing named entity annotations, researchers have largely assumed that syntactic tasks such as part-of-speech (POS) tagging cannot be crowdsourced. This(More)
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence mod-eling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise. We address these issues and evaluate bi-LSTMs with word, character, and unicode byte embeddings for POS tagging.(More)
In this shared task paper for SemEval-2014 Task 8, we show that most semantic structures can be approximated by trees through a series of almost bijective graph transformations. We transform input graphs, apply off-the-shelf methods from syntactic parsing on the resulting trees, and retrieve output graphs. Using tree approximations, we obtain good results(More)
We present a simple, yet effective approach to adapt part-of-speech (POS) taggers to new domains. Our approach only requires a dictionary and large amounts of unlabeled target data. The idea is to use the dictionary to mine the unlabeled target data for unambigu-ous word sequences, thus effectively collecting labeled target data. We add the mined instances(More)
Natural language processing (NLP) annotation projects employ guidelines to maximize inter-annotator agreement (IAA), and models are estimated assuming that there is one single ground truth. However, not all disagreement is noise, and in fact some of it may contain valuable linguistic information. We integrate such information in the training of a(More)