While the web provides a fantastic linguistic resource, collecting and processing data at web-scale is beyond the reach of most academic laboratories. Previous research has relied on search engines to collect online information, but this is hopelessly inefficient for building large-scale linguistic resources, such as lists of named-entity types or clusters of distributionally-similar words. An alternative to processing web-scale text directly is to use the information provided in an N-gram corpus. An N-gram corpus is an efficient compression of large amounts of text. An N-gram corpus states how often each sequence of words (up to length N) occurs. We propose tools for working with enhanced web-scale N-gram corpora that include richer levels of source annotation, such as part-of-speech tags. We describe a new set of search tools that make use of these tags, and collectively lower the barrier for lexical learning and ambiguity resolution at web-scale. The tools will allow novel sources of information to be applied to long-standing natural language challenges. 1.

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.

In sentiment analysis of product reviews, one important problem is to produce a summary of opinions based on product features/attributes (also called aspects). However, for the same feature, people can express it with many different words or phrases. To produce a useful summary, these words and phrases, which are domain synonyms, need to be grouped under the same feature group. Although several methods have been proposed to extract product features from reviews, limited work has been done on clustering or grouping of synonym features. This paper focuses on this task. Classic methods for solving this problem are based on unsupervised learning using some forms of distributional similarity. However, we found that these methods do not do well. We then model it as a semi-supervised learning problem. Lexical characteristics of the problem are exploited to automatically identify some labeled examples. Empirical evaluation shows that the proposed method outperforms existing state-of-the-art methods by a large margin.

It has been established that incorporating word cluster features derived from large unlabeled corpora can significantly improve prediction of linguistic structure. While previous work has focused primarily on English, we extend these results to other languages along two dimensions. First, we show that these results hold true for a number of languages across families. Second, and more interestingly, we provide an algorithm for inducing cross-lingual clusters and we show that features derived from these clusters significantly improve the accuracy of cross-lingual structure prediction. Specifically, we show that by augmenting direct-transfer systems with cross-lingual cluster features, the relative error of delexicalized dependency parsers, trained on English treebanks and transferred to foreign languages, can be reduced by up to 13%. When applying the same method to direct transfer of named-entity recognizers, we observe relative improvements of up to 26%.

This report describes a variety of work that uses web-scale N-gram data. This

recognition

Finding the right representation for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This paper investigates language model representations, in which language models trained on unlabeled corpora are used to generate real-valued feature vectors for words. We investigate ngram models and probabilistic graphical models, including a novel lattice-structured Markov Random Field. Experiments indicate that language model representations outperform traditional representations, and that graphical model representations outperform ngram models, especially on sparse and polysemous words. 1

Word classes automatically induced from distributional evidence have proved useful many NLP tasks including Named Entity Recognition, parsing and sentence retrieval. The Brown hard clustering algorithm is commonly used in this scenario. Here we propose to use Latent Dirichlet Allocation in order to induce soft, probabilistic word classes. We compare our approach against Brown in terms of efficiency. We also compare the usefulness of the induced Brown and LDA word classes for the semi-supervised learning of three NLP tasks: fine-grained Named Entity Recognition, Morphological Analysis and semantic Relation Classification. We show that using LDA for word class induction scales better with the number of classes than the Brown algorithm and the resulting classes outperform Brown on the three tasks. 1

We propose a general cross-domain bootstrapping algorithm for domain adaptation in the task of named entity recognition. We first generalize the lexical features of the source domain model with word clusters generated from a joint corpus. We then select target domain instances based on multiple criteria during the bootstrapping process. Without using annotated data from the target domain and without explicitly encoding any target-domainspecific knowledge, we were able to improve the source model’s F-measure by 7 points on the target domain.