A common challenge for biomedical natural language processing (BioNLP) is data sparsity. Distributed word representation approaches have been developed recently that represent word by learning from a large unlabeled data, such approaches have shown to overcome the data sparsity and improve NLP tasks. In this tutorial, we will introduce various word representation approaches, including the tradi...

In the paper we present a tool for lemmatization of multi-word common noun phrases and named entities for Polish called PoLem1. The tool is based on a set of manually crafted rules and heuristics utilizing a set of dictionaries (including morphological, named entities and inflection patterns). The accuracy of lemmatization obtained by the tool reached 97.99% on a dataset with multi-word common ...

Learning word sense classes has been shown to be useful in fine-grained word sense disambiguation [Kohomban and Lee, 2005]. However, the common choice for sense classes, WordNet lexicographer files, are not designed for machine learning based word sense disambiguation. In this work, we explore the use of clustering techniques in an effort to construct sense classes that are more suitable for wo...

We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a flexible match using automatically generated paraphrases. We find that the use of paraphrases over strict word matches represents an average F-measure ...

We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a flexible match using automatically generated paraphrases. We find that the use of paraphrases over strict word matches represents an average F-measure ...

We investigate the structures present in the Enron email dataset using singular value decomposition and semidiscrete decomposition. Using word frequency profiles we show that messages fall into two distinct groups, whose extrema are characterized by short messages and rare words versus long messages and common words. It is surprising that length of message and word use pattern should be related...

Word embeddings have been found to provide meaningful representations for words in an efficient way; therefore, they have become common in Natural Language Processing systems. In this paper, we evaluated different word embedding models trained on a large Portuguese corpus, including both Brazilian and European variants. We trained 31 word embedding models using FastText, GloVe, Wang2Vec and Wor...

Word-final /t/-deletion refers to a common phenomenon in spoken English where words such as /wEst/ “west” are pronounced as [wEs] “wes” in certain contexts. Phonological variation like this is common in naturally occurring speech. Current computational models of unsupervised word segmentation usually assume idealized input that is devoid of these kinds of variation. We extend a non-parametric m...

Indirect word learning lacks many of the overt social-pragmatic cues to reference available in direct word learning, yet the two result in equally robust mappings when comprehension is assessed immediately after learning. The 3 studies reported here investigated how 3-year-olds (N=96) respond to more challenging tests of the relative strengths of indirect and direct word learning. In Study 1, c...