Automatic sentiment classification has been extensively studied and applied in recent years. However, sentiment is expressed differently in different domains, and annotating corpora for every possible domain of interest is impractical. We investigate domain adaptation for sentiment classifiers, focusing on online reviews for different types of products. First, we extend to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline. Second, we identify a measure of domain similarity that correlates well with the potential for adaptation of a classifier from one domain to another. This measure could for instance be used to select a small set of domains to annotate whose trained classifiers would transfer well to many other domains.

/pdf/biographies-bollywood-boom-boxes-and-blenders-domain-2fr5jtcxb2.pdf

Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification

Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For many NLP tasks, however, we are confronted with new domains in which labeled data is scarce or non-existent. In such cases, we seek to adapt existing models from a resource-rich source domain to a resource-poor target domain. We introduce structural correspondence learning to automatically induce correspondences among features from different domains. We test our technique on part of speech tagging and show performance gains for varying amounts of source and target training data, as well as improvements in target domain parsing accuracy using our improved tagger.

/pdf/domain-adaptation-with-structural-correspondence-learning-3mvozpxuqi.pdf

Domain Adaptation with Structural Correspondence Learning

Principal component analysis is one of the most important and powerful methods in chemometrics as well as in a wealth of other areas. This paper provides a description of how to understand, use, and interpret principal component analysis. The paper focuses on the use of principal component analysis in typical chemometric areas but the results are generally applicable.

/pdf/principal-component-analysis-1sba76ou47.pdf

Principal component analysis

Traditionally, Information Extraction (IE) has focused on satisfying precise, narrow, pre-specified requests from small homogeneous corpora (e.g., extract the location and time of seminars from a set of announcements). Shifting to a new domain requires the user to name the target relations and to manually create new extraction rules or hand-tag new training examples. This manual labor scales linearly with the number of target relations.

This paper introduces Open IE (OIE), a new extraction paradigm where the system makes a single data-driven pass over its corpus and extracts a large set of relational tuples without requiring any human input. The paper also introduces TEXTRUNNER, a fully implemented, highly scalable OIE system where the tuples are assigned a probability and indexed to support efficient extraction and exploration via user queries.

We report on experiments over a 9,000,000 Web page corpus that compare TEXTRUNNER with KNOWITALL, a state-of-the-art Web IE system. TEXTRUNNER achieves an error reduction of 33% on a comparable set of extractions. Furthermore, in the amount of time it takes KNOWITALL to perform extraction for a handful of pre-specified relations, TEXTRUNNER extracts a far broader set of facts reflecting orders of magnitude more relations, discovered on the fly. We report statistics on TEXTRUNNER's 11,000,000 highest probability tuples, and show that they contain over 1,000,000 concrete facts and over 6,500,000 more abstract assertions.

/pdf/open-information-extraction-from-the-web-4hdvlsd9yu.pdf

Open information extraction from the web

The state-of-the-art methods used for relation classification are primarily based on statistical machine learning, and their performance strongly depends on the quality of the extracted features. The extracted features are often derived from the output of pre-existing natural language processing (NLP) systems, which leads to the propagation of the errors in the existing tools and hinders the performance of these systems. In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features. Our method takes all of the word tokens as input without complicated pre-processing. First, the word tokens are transformed to vectors by looking up word embeddings 1 . Then, lexical level features are extracted according to the given nouns. Meanwhile, sentence level features are learned using a convolutional approach. These two level features are concatenated to form the final extracted feature vector. Finally, the features are fed into a softmax classifier to predict the relationship between two marked nouns. The experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods.

/pdf/relation-classification-via-convolutional-deep-neural-1v77s8v4mm.pdf

Relation Classification via Convolutional Deep Neural Network

We present a fast algorithm for non-linear dimension reduction. The algorithm builds a local linear model of the data by merging PCA with clustering based on a new distortion measure. Experiments with speech and image data indicate that the local linear algorithm produces encodings with lower distortion than those built by five layer auto-associative networks. The local linear algorithm is also more than an order of magnitude faster to train.

/pdf/fast-non-linear-dimension-reduction-w6pda7m323.pdf

Fast Non-Linear Dimension Reduction

Truecasing is the process of restoring case information to badly-cased or noncased text. This paper explores truecasing issues and proposes a statistical, language modeling based truecaser which achieves an accuracy of ∼98% on news articles. Task based evaluation shows a 26% F-measure improvement in named entity recognition when using truecasing. In the context of automatic content extraction, mention detection on automatic speech recognition text is also improved by a factor of 8. Truecasing also enhances machine translation output legibility and yields a BLEU score improvement of 80.2%. This paper argues for the use of truecasing as a valuable component in text processing applications.

tRuEcasIng

The invention detects signs of emerging illness, such as flu, skin cancer, backache, etc., among the general population and individuals. The detection of symptoms of illness is performed through the utilization of embedded devices equipped with various sensors, such as cameras, glasses, wrist watches, TVs, fire warning systems, and having the ability to analyze the detected information and to transmit that information via wireless and regular communication channels to a central server for a more detailed analysis and possible action. The information about locally detected symptoms is gathered at central location and processed to ascertain whether there is a new epidemic of a flu, therefore enabling early shipment of a flu vaccine which prevents the spread of the disease.

Medical non-intrusive prevention based on network of embedded systems

T he pragmatic goal of natural language (NL) and multimodal interfaces (speech recognition, keyboard entry, pointing, among others) is to enable ease-of-use for users/customers in performing more sophisticated human-computer interactions (HCI). NL research attempts to define extensive discourse models that in turn provide improved models of context-enabling HCI and personalization. Customers have the initiative to Technologies that successfully recognize and react to spoken or typed words are key to true personalization. Front-and back-end systems must respond in accord, and one solution may be found somewhere in the middle(ware).

Natural language dialogue for personalized interaction

With the emergence of electronic-commerce systems, successful information access on electroniccommerce web sites becomes essential Menu-driven navigation and keyword search currently provided by most commercial sites have considerable limitations because they tend to overwhelm and frustrate users with lengthy, rigid, and ineffective interactions To provide an efficient solution for information access, we have built the NATURAL language ASSISTANT (NLA), a web-based natural language dialog system to help users find relevant products on electronic-commerce sites The system brings together technologies in natural language processing and human-computer interaction to create a faster and more intuitive way of interacting with web sites By combining statistical parsing techniques with traditional AI rule-based technology, we have created a dialog system that accommodates both customer needs and business requirements The system is currently embedded in an application for recommending laptops and was deployed as a pilot on IBM's web site

/pdf/natural-language-assistant-a-dialog-system-for-online-29uywvipbd.pdf

Nanda Kambhatla

Papers

Fast Non-Linear Dimension Reduction

tRuEcasIng

Medical non-intrusive prevention based on network of embedded systems

Natural language dialogue for personalized interaction

Natural Language Assistant: A Dialog System for Online Product Recommendation