Text classification is a foundational task in many NLP applications. Traditional text classifiers often rely on many human-designed features, such as dictionaries, knowledge bases and special tree kernels. In contrast to traditional methods, we introduce a recurrent convolutional neural network for text classification without human-designed features. In our model, we apply a recurrent structure to capture contextual information as far as possible when learning word representations, which may introduce considerably less noise compared to traditional window-based neural networks. We also employ a max-pooling layer that automatically judges which words play key roles in text classification to capture the key components in texts. We conduct experiments on four commonly used datasets. The experimental results show that the proposed method outperforms the state-of-the-art methods on several datasets, particularly on document-level datasets.

Unsupervised discovery of synonymous phrases is useful in a variety of tasks ranging from text mining and search engines to semantic analysis and machine translation. This paper presents an unsupervised corpus-based conditional model: Near-Synonym System (NeSS) for finding phrasal synonyms and near synonyms that requires only a large monolingual corpus. The method is based on maximizing information-theoretic combinations of shared contexts and is parallelizable for large-scale processing. An evaluation framework with crowd-sourced judgments is proposed and results are compared with alternate methods, demonstrating considerably superior results to the literature and to thesaurus look up for multi-word phrases. Moreover, the results show that the statistical scoring functions and overall scalability of the system are more important than language specific NLP tools. The method is language-independent and practically useable due to accuracy and real-time performance via parallel decomposition.

In Kernel-based Learning the targeted phenomenon is summarized by a set of explanatory examples derived from the training set. When the model size grows with the complexity of the task, such approaches are so computationally demanding that the adoption of comprehensive models is not always viable.In this paper, a general framework aimed at minimizing this problem is proposed: multiple classifiers are stratified and dynamically invoked according to increasing levels of complexity corresponding to incrementally more expressive representation spaces.Computationally expensive inferences are thus adopted only when the classification at lower levels is too uncertain over an individual instance. The application of complex functions is thus avoided where possible, with a significant reduction of the overall costs. The proposed strategy has been integrated within two well-known algorithms: Support Vector Machines and Passive-Aggressive Online classifier.A significant cost reduction (up to 90%), with a negligible performance drop, is observed against two Natural Language Processing tasks, i.e. Question Classification and Sentiment Analysis in Twitter.

Manually labeling documents for training a text classifier is expensive and time-consuming. Moreover, a classifier trained on labeled documents may suffer from overfitting and adaptability problems. Dataless text classification (DLTC) has been proposed as a solution to these problems, since it does not require labeled documents. Previous research in DLTC has used explicit semantic analysis of Wikipedia content to measure semantic distance between documents, which is in turn used to classify test documents based on nearest neighbours. The semantic-based DLTC method has a major drawback in that it relies on a large-scale, finely-compiled semantic knowledge base, which is difficult to obtain in many scenarios. In this paper we propose a novel kind of model, descriptive LDA (DescLDA), which performs DLTC with only category description words and unlabeled documents. In DescLDA, the LDA model is assembled with a describing device to infer Dirichlet priors from prior descriptive documents created with category description words. The Dirichlet priors are then used by LDA to induce category-aware latent topics from unlabeled documents. Experimental results with the 20Newsgroups and RCV1 datasets show that: (1) our DLTC method is more effective than the semantic-based DLTC baseline method; and (2) the accuracy of our DLTC method is very close to state-of-the-art supervised text classification methods. As neither external knowledge resources nor labeled documents are required, our DLTC method is applicable to a wider range of scenarios.

Word Sense Disambiguation is a difficult problem to solve in the unsupervised setting. This is because in this setting inference becomes more dependent on the interplay between different senses in the context due to unavailability of learning resources. Using two basic ideas, sense dependency and selective dependency, we model the WSD problem as a Maximum A Posteriori (MAP) Inference Query on a Markov Random Field (MRF) built using WordNet and Link Parser or Stanford Parser. To the best of our knowledge this combination of dependency and MRF is novel, and our graph-based unsupervised WSD system beats state-of-the-art system on SensEval-2, SensEval-3 and SemEval-2007 English all-words datasets while being over 35 times faster.

Topic modeling techniques have the benefits of modeling words and documents uniformly under a probabilistic framework. However, they also suffer from the limitations of sensitivity to initialization and unigram topic distribution, which can be remedied by deep learning techniques. To explore the combination of topic modeling and deep learning techniques, we first explain the standard topic modelfrom the perspective of a neural network. Based on this, we propose a novel neural topic model (NTM) where the representation of words and documents are efficiently and naturally combined into a uniform framework. Extending from NTM, we can easily add a label layer and propose the supervised neural topic model (sNTM) to tackle supervised tasks. Experiments show that our models are competitive in both topic discovery and classification/regression tasks.

Peer-to-peer lending is a new highly liquid market for debt, which is rapidly growing in popularity. Here we consider modelling market rates, developing a non-linear Gaussian Process regression method which incorporates both structured data and unstructured text from the loan application. We show that the peer-to-peer market is predictable, and identify a small set of key factors with high predictive power. Our approach outperforms baseline methods for predicting market rates, and generates substantial profit in a trading simulation.

Knowledge graph completion aims to perform link prediction between entities. In this paper, we consider the approach of knowledge graph embeddings. Recently, models such as TransE and TransH build entity and relation embeddings by regarding a relation as translation from head entity to tail entity. We note that these models simply put both entities and relations within the same semantic space. In fact, an entity may have multiple aspects and various relations may focus on different aspects of entities, which makes a common space insufficient for modeling. In this paper, we propose TransR to build entity and relation embeddings in separate entity space and relation spaces. Afterwards, we learn embeddings by first projecting entities from entity space to corresponding relation space and then building translations between projected entities. In experiments, we evaluate our models on three tasks including link prediction, triple classification and relational fact extraction. Experimental results show significant and consistent improvements compared to state-of-the-art baselines including TransE and TransH.

This paper proposes approaches to automatically createa large number of new bilingual dictionaries for low resource languages, especially resource-poor and endangered languages, from a single input bilingual dictionary. Our algorithms produce translations of wordsin a source language to plentiful target languages using available Wordnets and a machine translator (MT). Since our approaches rely on just one input dictionary, available Wordnets and an MT, they are applicable toany bilingual dictionary as long as one of the two languagesis English or has a Wordnet linked to the Princeton Wordnet. Starting with 5 available bilingual dictionaries,we create 48 new bilingual dictionaries. Of these, 30 pairs of languages are not supported by the popular MTs: Google and Bing.

We consider the following problem: There is a set of items (e.g., movies) and a group of agents (e.g., passengers on a plane); each agent has some intrinsic utility for each of the items. Our goal is to pick a set of K items that maximize the total derived utility of all the agents (i.e., in our example we are to pick K movies that we put on the plane's entertainment system). However, the actual utility that an agent derives from a given item is only a fraction of its intrinsic one, and this fraction depends on how the agent ranks the item among the chosen, available, ones. We provide a formal specification of the model and provide concrete examples and settings where it is applicable. We show that the problem is hard in general, but we show a number of tractability results for its natural special cases.