Supervised sequence-labeling systems in natural language processing often suffer from data sparsity because they use word types as features in their prediction tasks. Consequently, they have difficulty estimating parameters for types which appear in the test set, but seldom (or never) appear in the training set. We demonstrate that distributional representations of word types, trained on unannotated text, can be used to improve performance on rare words. We incorporate aspects of these representations into the feature space of our sequence-labeling systems. In an experiment on a standard chunking dataset, our best technique improves a chunker from 0.76 F1 to 0.86 F1 on chunks beginning with rare words. On the same dataset, it improves our part-of-speech tagger from 74 % to 80 % accuracy on rare words. Furthermore, our system improves significantly over a baseline system when applied to text from a different domain, and it reduces the sample complexity of sequence labeling. 1

Neural probabilistic language models (NPLMs) have been shown to be competitive with and occasionally superior to the widely-used n-gram language models. The main drawback of NPLMs is their extremely long training and testing times. Morin and Bengio have proposed a hierarchical language model built around a binary tree of words, which was two orders of magnitude faster than the nonhierarchical model it was based on. However, it performed considerably worse than its non-hierarchical counterpart in spite of using a word tree created using expert knowledge. We introduce a fast hierarchical language model along with a simple feature-based algorithm for automatic construction of word trees from the data. We then show that the resulting models can outperform non-hierarchical neural models as well as the best n-gram models. 1

In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show that deep belief networks have certain properties which are very interesting for transliteration and possibly also for translation and that a combination with conventional techniques leads to an improvement over both components on an Arabic-English transliteration task. 1

Unsupervised vector-based approaches to semantics can model rich lexical meanings, but they largely fail to capture sentiment information that is central to many word meanings and important for a wide range of NLP tasks. We present a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term–document information as well as rich sentiment content. The proposed model can leverage both continuous and multi-dimensional sentiment information as well as non-sentiment annotations. We instantiate the model to utilize the document-level sentiment polarity annotations present in many online documents (e.g. star ratings). We evaluate the model using small, widely used sentiment and subjectivity corpora and find it out-performs several previously introduced methods for sentiment classification. We also introduce a large dataset of movie reviews to serve as a more robust benchmark for work in this area. recognition, part of speech tagging, and document retrieval (Turney and Pantel, 2010; Collobert and Weston, 2008; Turian et al., 2010). In this paper, we present a model to capture both semantic and sentiment similarities among words. The semantic component of our model learns word vectors via an unsupervised probabilistic model of documents. However, in keeping with linguistic and cognitive research arguing that expressive content and descriptive semantic content are distinct (Kaplan, 1999; Jay, 2000; Potts, 2007), we find that this basic model misses crucial sentiment information. For example, while it learns that wonderful and amazing are semantically close, it doesn’t capture the fact that these are both very strong positive sentiment words, at the opposite end of the spectrum from terrible and awful. Thus, we extend the model with a supervised sentiment component that is capable of embracing many social and attitudinal aspects of meaning (Wilson

Abstract not found

Recently, there has been substantial interest in using large amounts of unlabeled data to learn word representations which can then be used as features in supervised classifiers for NLP tasks. However, most current approaches are slow to train, do not model the context of the word, and lack theoretical grounding. In this paper, we present a new learning method, Low Rank Multi-View Learning (LR-MVL) which uses a fast spectral method to estimate low dimensional context-specific word representations from unlabeled data. These representation features can then be used with any supervised learner. LR-MVL is extremely fast, gives guaranteed convergence to a global optimum, is theoretically elegant, and achieves state-ofthe-art performance on named entity recognition (NER) and chunking problems. 1 Introduction and Related Work Over the past decade there has been increased interest in using unlabeled data to supplement the labeled data in semi-supervised learning settings to overcome the inherent data sparsity and get improved generalization accuracies in high dimensional domains like NLP. Approaches like [1, 2]

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

We present results obtained with several advanced language modeling techniques, including class based model, cache model, maximum entropy model, structured language model, random forest language model and several types of neural network based language models. We show results obtained after combining all these models by using linear interpolation. We conclude that for both small and moderately sized tasks, we obtain new state of the art results with combination of models, that is significantly better than performance of any individual model. Obtained perplexity reductions against Good-Turing trigram baseline are over 50 % and against modified Kneser-Ney smoothed 5-gram over 40%. Index Terms: language modeling, neural networks, model combination, speech recognition

Most supervised language processing systems show a significant drop-off in performance when they are tested on text that comes from a domain significantly different from the domain of the training data. Sequence labeling systems like partof-speech taggers are typically trained on newswire text, and in tests their error rate on, for example, biomedical data can triple, or worse. We investigate techniques for building open-domain sequence labeling systems that approach the ideal of a system whose accuracy is high and constant across domains. In particular, we investigate unsupervised techniques for representation learning that provide new features which are stable across domains, in that they are predictive in both the training and out-of-domain test data. In experiments, our novel techniques reduce error by as much as 29 % relative to the previous state of the art on out-of-domain text. 1

We propose a generative model based on Temporal Restricted Boltzmann Machines for transition based dependency parsing. The parse tree is built incrementally using a shiftreduce parse and an RBM is used to model each decision step. The RBM at the current time step induces latent features with the help of temporal connections to the relevant previous steps which provide context information. Our parser achieves labeled and unlabeled attachment scores of 88.72 % and 91.65 % respectively, which compare well with similar previous models and the state-of-the-art. 1