Bhuwan Dhingra

Gated-Attention Readers for Text Comprehension

In this paper we study the problem of answering cloze-style questions over documents. Our model, the Gated-Attention (GA) Reader, integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader. This enables the reader to build query-specific representations of tokens in the document for accurate answer selection. The GA Reader obtains state-of-the-art results on three benchmarks for this task--the CNN \& Daily Mail news stories and the Who Did What dataset. The effectiveness of multiplicative interaction is demonstrated by an ablation study, and by comparing to alternative compositional operators for implementing the gated-attention. The code is available at this https URL

Tweet2Vec: Character-Based Distributed Representations for Social Media

Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significantly better when the input contains many out-of-vocabulary words or unusual character sequences. Our tweet2vec encoder is publicly available.

Stock market prediction using Hidden Markov Models

Stock market prediction is a classic problem which has been analyzed extensively using tools and techniques of Machine Learning. Interesting properties which make this modeling non-trivial is the time dependence, volatility and other similar complex dependencies of this problem. To incorporate these, Hidden Markov Models (HMMs) have recently been applied to forecast and predict the stock market. We present the Maximum a Posteriori HMM approach for forecasting stock values for the next day given historical data. In our approach, we consider the fractional change in Stock value and the intra-day high and low values of the stock to train the continuous HMM. This HMM is then used to make a Maximum a Posteriori decision over all the possible stock values for the next day. We test our approach on several stocks, and compare the performance to some of the existing methods using HMMs and Artificial Neural Networks using Mean Absolute Percentage Error (MAPE).

Using Graphs of Classifiers to Impose Declarative Constraints on Semi-supervised Learning

We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In addition to representing individual SSL heuristics, we show that multiple heuristics can be automatically combined using Bayesian optimization methods. We experiment with two classes of tasks, link-based text classification and relation extraction. We show modest improvements on well-studied link-based classification benchmarks, and state-of-the-art results on relation-extraction tasks for two realistic domains.

Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction.

We propose a general approach to modeling semi-supervised learning constraints on unlabeled data. Both traditional supervised classification tasks and many natural semisupervised learning heuristics can be approximated by specifying the desired outcome of walks through a graph of classifiers. We demonstrate the modeling capability of this approach in the task of relation extraction, and experimental results show that the modeled constraints achieve better performance as expected.