Accordingly, a prime step in text mining applications is to extract interesting patterns and features, from this supply of unstructured data. Feature extraction can be considered as the core of social media mining tasks such as sentiment analysis, event detection, and news recommendation [2]. In the literature, sentiment analysis tends to be used to refer to the task of classifying the polarity of a given piece of text at the document, sentence, feature, or aspect level [23]. There are various applications on a variety of domains which utilize sentiment analysis, in this regard one can mention applying the sentiment analysis for political reviews to estimate the general viewpoint of the parties [43], predicting stock market prices based on sentiment analysis by utilizing the different financial news data [5], and making use of the sentiment analysis to recognize the current medical and psychological status for a community [23]. Machine learning algorithms and statistical learning techniques have been rising in a variety of scientific fields [9, 10]. A number of machine learning techniques have been proposed to perform the task of sentiment analysis. As one of the powerful sub-domains of machine learning in recent years, deep learning models are emerging as a persuasive computational tool, they have affected many research areas and can be traced in many applications. With respect to the deep learning, textual deep representation models attempt to discover and present intricate syntactic and semantic representations of texts, automatically from data without any handmade feature engineering.

Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output vocabulary, e.g. in neural encoder decoders, as the action spaces. Both have their own limitations. This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space from the data. Comprehensive experiments are conducted examining both continuous and discrete action types and two different optimization methods based on stochastic variational inference. Results show that the proposed latent actions achieve superior empirical performance improvement over previous word-level policy gradient methods on both DealOrNoDeal and MultiWoz dialogs. Our detailed analysis also provides insights about various latent variable approaches for policy learning and can serve as a foundation for developing better latent actions in future research.

Humans are unique in their ability to learn from, understand the world through and communicate with language… Or are they? Perhaps not for long, if Dr. Layla El Asri, a Research Manager at Microsoft Research Montreal, has a say in it. She wants you to be able to talk to your machine just like you'd talk to another person. The hard part is getting your machine to understand and talk back to you like it's that other person. Today, Dr. El Asri talks about the particular challenges she and other scientists face in building sophisticated dialogue systems that lay the foundation for talking machines. She also explains how reinforcement learning, in the form of a text game generator called TextWorld, is helping us get there, and relates a fascinating story from more than fifty years ago that reveals some of the safeguards necessary to ensure that when we design machines specifically to pass the Turing test, we design them in an ethical and responsible way. Layla El Asri: In a video game, most of the time you only have a few actions that you can take. You just need to learn when you should go right, when you should go left, when you should go up, when you should go down. But when it comes to dialogue, you need to learn how to make a sentence that is grammatically correct, and then you need to learn how to make a sentence that makes sense in the global context of the dialogue, or a sentence that brings new information in the dialogue that is going to make the person you are talking to satisfied with the sentence. Your action space is just huge because it's not just up/down, right/left, it's all the sentences you could imagine! Host: You're listening to the Microsoft Research Podcast, a show that brings you closer to the cutting-edge of technology research and the scientists behind it. Host: Humans are unique in their ability to learn from, understand the world through and communicate with language… Or are they? Perhaps not for long, if Dr. Layla El Asri, a Research Manager at Microsoft Research Montreal, has a say in it. She wants you to be able to talk to your machine just like you'd talk to another person.

Scientific documents rely on both mathematics and text to communicate ideas. Inspired by the topical correspondence between mathematical equations and word contexts observed in scientific texts, we propose a novel topic model that jointly generates mathematical equations and their surrounding text (TopicEq). Using an extension of the correlated topic model, the context is generated from a mixture of latent topics, and the equation is generated by an RNN that depends on the latent topic activations. To experiment with this model, we create a corpus of 400K equation-context pairs extracted from a range of scientific articles from arXiv, and fit the model using a variational autoencoder approach. Experimental results show that this joint model significantly outperforms existing topic models and equation models for scientific texts. Moreover, we qualitatively show that the model effectively captures the relationship between topics and mathematics, enabling novel applications such as topic-aware equation generation, equation topic inference, and topic-aware alignment of mathematical symbols and words.

Machine learning clustering techniques are not the only way to extract topics from a text data set. Text mining literature has proposed a number of statistical models, known as probabilistic topic models, to detect topics from an unlabeled set of documents. One of the most popular models is the latent Dirichlet allocation (LDA) algorithm developed by Blei, Ng, and Jordan [i]. LDA is a generative unsupervised probabilistic algorithm that isolates the top K topics in a data set as described by the most relevant N keywords. In other words, the documents in the data set are represented as random mixtures of latent topics, where each topic is characterized by a Dirichlet distribution over a fixed vocabulary.

Sentiment analysis is a task that may suffer from a lack of data in certain cases, as the datasets are often generated and annotated by humans. In cases where data is inadequate for training discriminative models, generate models may aid training via data augmentation. Generative Adversarial Networks (GANs) are one such model that has advanced the state of the art in several tasks, including as image and text generation. In this paper, I train GAN models on low resource datasets, then use them for the purpose of data augmentation towards improving sentiment classifier generalization. Given the constraints of limited data, I explore various techniques to train the GAN models. I also present an analysis of the quality of generated GAN data as more training data for the GAN is made available. In this analysis, the generated data is evaluated as a test set (against a model trained on real data points) as well as a training set to train classification models. Finally, I also conduct a visual analysis by projecting the generated and the real data into a two-dimensional space using the t-Distributed Stochastic Neighbor Embedding (t-SNE) method.

NLP is a technology through which computers can "understand" and reproduce human language. Although the language processing applications are in the early stage of development that isn't very mature yet, they are definitely one of the most interesting tools that might soon change the online space for good. NLP applications are mostly used in chat-bots and other tools providing virtual customer support. Of course, any interaction with customers is meticulously tracked, analysed and optimised to perform better and better. This itself makes the NLP technology a perfect tool for the sentiment analysis.

Detecting and aggregating sentiments toward people, organizations, and events expressed in unstructured social media have become critical text mining operations. Early systems detected sentiments over whole passages, whereas more recently, target-specific sentiments have been of greater interest. In this paper, we present MTTDSC, a multi-task target-dependent sentiment classification system that is informed by feature representation learnt for the related auxiliary task of passage-level sentiment classification. The auxiliary task uses a gated recurrent unit (GRU) and pools GRU states, followed by an auxiliary fully-connected layer that outputs passage-level predictions. In the main task, these GRUs contribute auxiliary per-token representations over and above word embeddings. The main task has its own, separate GRUs. The auxiliary and main GRUs send their states to a different fully connected layer, trained for the main task. Extensive experiments using two auxiliary datasets and three benchmark datasets (of which one is new, introduced by us) for the main task demonstrate that MTTDSC outperforms state-of-the-art baselines. Using word-level sensitivity analysis, we present anecdotal evidence that prior systems can make incorrect target-specific predictions because they miss sentiments expressed by words independent of target.

Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip require a much more complex multi-turn dialogue. Current limitations of conversational systems have made it difficult to support applications that require personalization, customization and context dependent interactions. We tackle this challenging problem by using domain-independent AI planning to automatically create dialogue plans, customized to guide a dialogue towards achieving a given goal. The input includes a library of atomic dialogue actions, an initial state of the dialogue, and a goal. Dialogue plans are plugged into a dialogue system capable to orchestrate their execution. Use cases demonstrate the viability of the approach. Our work on dialogue planning has been integrated into a product, and it is in the process of being deployed into another.

An obstacle to the development of many natural language processing products is the vast amount of training examples necessary to get satisfactory results. The generation of these examples is often a tedious and time-consuming task. This paper this paper proposes a method to transform the sentiment of sentences in order to limit the work necessary to generate more training data. This means that one sentence can be transformed to an opposite sentiment sentence and should reduce by half the work required in the generation of text. The proposed pipeline consists of a sentiment classifier with an attention mechanism to highlight the short phrases that determine the sentiment of a sentence. Then, these phrases are changed to phrases of the opposite sentiment using a baseline model and an autoencoder approach. Experiments are run on both the separate parts of the pipeline as well as on the end-to-end model. The sentiment classifier is tested on its accuracy and is found to perform adequately. The autoencoder is tested on how well it is able to change the sentiment of an encoded phrase and it was found that such a task is possible. We use human evaluation to judge the performance of the full (end-to-end) pipeline and that reveals that a model using word vectors outperforms the encoder model. Numerical evaluation shows that a success rate of 54.7% is achieved on the sentiment change.