Deep learning has significantly improved state-of-the-art performance for natural language processing tasks like machine translation, summarization, question answering, and text classification. Each of these tasks is typically studied with a specific metric, and performance is often measured on a set of standard benchmark datasets. This has led to the development of architectures designed specifically for those tasks and metrics, but it does not necessarily promote the emergence of general NLP models, those which can perform well across a wide variety of NLP tasks. In order to explore the possibility of such models as well as the tradeoffs that arise in optimizing for them, we introduce the Natural Language Decathlon (decaNLP). The goal of the Decathlon is to explore models that generalize to all ten tasks and investigate how such models differ from those trained for single tasks.

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known categories are jointly optimised. Second, an unsupervised method is used for further tuning the weights. Sharing weights injects prior knowledge to unknown categories. The unsupervised tuning (i.e. the risk minimisation) improves the F-Measure when recognising nearly zero-shot data on the DSTC3 corpus. This unsupervised method can be applied subject to two assumptions: the rank of the class marginal is assumed to be known and the class-conditional scores of the classifier are assumed to follow a Gaussian distribution.

Sentiment analysis is the computational study of opinionated text and is becoming increasing important to online commercial applications. However, the majority of current approaches determine sentiment by attempting to detect the overall polarity of a sentence, paragraph, or text window, but without any knowledge about the entities mentioned (e.g. restaurant) and their aspects (e.g. price). Aspect-level sentiment analysis of customer feedback data when done accurately can be leveraged to understand strong and weak performance points of businesses and services, and can also support the formulation of critical action steps to improve performance. In this paper we focus on aspect-level sentiment classification, studying the role of opinion context extraction for a given aspect and the extent to which traditional and neural sentiment classifiers benefit when trained using the opinion context text. We propose four methods to aspect context extraction using lexical, syntactic and sentiment co-occurrence knowledge. Further, we evaluate the usefulness of the opinion contexts for aspect-sentiment analysis. Our experiments on benchmark data sets from SemEval and a real-world dataset from the insurance domain suggests that extracting the right opinion context is effective in improving classification performance.Specifically combining syntactical features with sentiment co-occurrence knowledge leads to the best aspect-sentiment classification performance.

K-fold cross validation (CV) is a popular method for estimating the true performance of machine learning models, allowing model selection and parameter tuning. However, the very process of CV requires random partitioning of the data and so our performance estimates are in fact stochastic, with variability that can be substantial for natural language processing tasks. We demonstrate that these unstable estimates cannot be relied upon for effective parameter tuning. The resulting tuned parameters are highly sensitive to how our data is partitioned, meaning that we often select sub-optimal parameter choices and have serious reproducibility issues. Instead, we propose to use the less variable J-K-fold CV, in which J independent K-fold cross validations are used to assess performance. Our main contributions are extending J-K-fold CV from performance estimation to parameter tuning and investigating how to choose J and K. We argue that variability is more important than bias for effective tuning and so advocate lower choices of K than are typically seen in the NLP literature, instead use the saved computation to increase J. To demonstrate the generality of our recommendations we investigate a wide range of case-studies: sentiment classification (both general and target-specific), part-of-speech tagging and document classification.

Cultural activity is an inherent aspect of urban life and the success of a modern city is largely determined by its capacity to offer generous cultural entertainment to its citizens. To this end, the optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as it can reduce financial costs in terms of planning and improve quality of life in the city, more generally. In this paper, we make use of a large longitudinal dataset of user location check-ins from the online social network WeChat to develop a data-driven framework for cultural planning in the city of Beijing. We exploit rich spatio-temporal representations on user activity at cultural venues and use a novel extended version of the traditional latent Dirichlet allocation model that incorporates temporal information to identify latent patterns of urban cultural interactions. Using the characteristic typologies of mobile user cultural activities emitted by the model, we determine the levels of demand for different types of cultural resources across urban areas. We then compare those with the corresponding levels of supply as driven by the presence and spatial reach of cultural venues in local areas to obtain high resolution maps that indicate urban regions with lack of cultural resources, and thus give suggestions for further urban cultural planning and investment optimisation.

We propose a new method of estimation in topic models, that is not a variation on the existing simplex finding algorithms, and that estimates the number of topics K from the observed data. We derive new finite sample minimax lower bounds for the estimation of A, as well as new upper bounds for our proposed estimator. We describe the scenarios where our estimator is minimax adaptive. Our finite sample analysis is valid for any number of documents (n), individual document length (N_i), dictionary size (p) and number of topics (K), and both p and K are allowed to increase with n, a situation not handled well by previous analyses. We complement our theoretical results with a detailed simulation study. We illustrate that the new algorithm is faster and more accurate than the current ones, although we start out with a computational and theoretical disadvantage of not knowing the correct number of topics K, while we provide the competing methods with the correct value in our simulations.

In order to feed this data into our RNN, all input documents must have the same length. We will limit the maximum review length to max_words by truncating longer reviews and padding shorter reviews with a null value (0). We can accomplish this using the pad_sequences() function in Keras. For now, set max_words to 500. We start building our model architecture in the code cell below.

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language cues, training a model with a small set of labeled datasets is still a challenge. For instance, in expanding sentiment analysis to new languages and cultures, it may not always be possible to obtain comprehensive labeled datasets. In this paper, we investigate the application of semi-supervised and transfer learning methods to improve performances on low resource sentiment classification tasks. We experiment with extracting dense feature representations, pre-training and manifold regularization in enhancing the performance of sentiment classification systems. Our goal is a coherent implementation of these methods and we evaluate the gains achieved by these methods in matched setting involving training and testing on a single corpus setting as well as two cross corpora settings. In both the cases, our experiments demonstrate that the proposed methods can significantly enhance the model performance against a purely supervised approach, particularly in cases involving a handful of training data.

Topic modeling is a type of statistical modeling for discovering the abstract "topics" that occur in a collection of documents. Latent Dirichlet Allocation (LDA) is an example of topic model and is used to classify text in a document to a particular topic. It builds a topic per document model and words per topic model, modeled as Dirichlet distributions. Here we are going to apply LDA to a set of documents and split them into topics. The data set we'll use is a list of over one million news headlines published over a period of 15 years and can be downloaded from Kaggle.

Starting with the idea that sentiment analysis models should be able to predict not only positive or negative but also other psychological states of a person, we implement a sentiment analysis model to investigate the relationship between the model and emotional state. We first examine psychological measurements of 64 participants and ask them to write a book report about a story. After that, we train our sentiment analysis model using crawled movie review data. We finally evaluate participants' writings, using the pretrained model as a concept of transfer learning. The result shows that sentiment analysis model performs good at predicting a score, but the score does not have any correlation with human's self-checked sentiment.