Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM algorithm. Since each step in the EM algorithm is differentiable, the proposed method can backpropagate the loss through the EM algorithm to train the neural networks. The expected test likelihood is maximized by a stochastic gradient descent method using a set of multiple text corpora with an episodic training framework. In our experiments, we demonstrate that the proposed method achieves better perplexity than existing methods using three real-world text document sets.
Transformer, based on the encoder-decoder framework, has achieved state-of-the-art performance on several natural language generation tasks. The encoder maps the words in the input sentence into a sequence of hidden states, which are then fed into the decoder to generate the output sentence. These hidden states usually correspond to the input words and focus on capturing local information. However, the global (sentence level) information is seldom explored, leaving room for the improvement of generation quality. In this paper, we propose a novel global representation enhanced Transformer (GRET) to explicitly model global representation in the Transformer network. Specifically, in the proposed model, an external state is generated for the global representation from the encoder. The global representation is then fused into the decoder during the decoding process to improve generation quality. We conduct experiments in two text generation tasks: machine translation and text summarization. Experimental results on four WMT machine translation tasks and LCSTS text summarization task demonstrate the effectiveness of the proposed approach on natural language generation.
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially synthesize new labeled data for supervised classification tasks. We mainly focus on cases with scarce labeled data. Our method, referred to as language-model-based data augmentation (LAMBADA), involves fine-tuning a state-of-the-art language generator to a specific task through an initial training phase on the existing (usually small) labeled data. Using the fine-tuned model and given a class label, new sentences for the class are generated. Our process then filters these new sentences by using a classifier trained on the original data. In a series of experiments, we show that LAMBADA improves classifiers' performance on a variety of datasets. Moreover, LAMBADA significantly improves upon the state-of-the-art techniques for data augmentation, specifically those applicable to text classification tasks with little data.
With the rise of opioid abuse in the US, there has been a growth of overlapping hotspots for overdose-related and HIV-related deaths in Springfield, Boston, Fall River, New Bedford, and parts of Cape Cod. With a large part of population, including rural communities, active on social media, it is crucial that we leverage the predictive power of social media as a preventive measure. We explore the predictive power of micro-blogging social media website Twitter with respect to HIV new diagnosis rates per county. While trending work in Twitter NLP has focused on primarily text-based features, we show that multi-dimensional feature construction can significantly improve the predictive power of topic features alone with respect STI's (sexually transmitted infections). By multi-dimensional features, we mean leveraging not only the topical features (text) of a corpus, but also location-based information (counties) about the tweets in feature-construction. We develop novel text-location-based smoothing features to predict new diagnoses of HIV.
Automatically imitating input text is a common task in natural language generation, often used to create humorous results. Classic algorithms for learning to imitate text, e.g. simple Markov chains, usually have a trade-off between originality and syntactic correctness. We present two ways of automatically parodying philosophical statements from examples overcoming this issue, and show how these can work in interactive systems as well. The first algorithm uses interpolated Markov models with extensions to improve the quality of the generated texts. For the second algorithm, we propose dynamically extracting templates and filling these with new content. To illustrate these algorithms, we implemented TorfsBot, a Twitterbot imitating the witty, semi-philosophical tweets of professor Rik Torfs, the previous KU Leuven rector. We found that users preferred generative models that focused on local coherent sentences, rather than those mimicking the global structure of a philosophical statement. The proposed algorithms are thus valuable new tools for automatic parody as well as template learning systems.
This paper describes a corpus of about 3000 English literary texts with about 250 million words extracted from the Gutenberg project that span a range of genres from both fiction and non-fiction written by more than 130 authors (e.g., Darwin, Dickens, Shakespeare). Quantitative Narrative Analysis (QNA) is used to explore a cleaned subcorpus, the Gutenberg English Poetry Corpus (GEPC) which comprises over 100 poetic texts with around 2 million words from about 50 authors (e.g., Keats, Joyce, Wordsworth). Some exemplary QNA studies show author similarities based on latent semantic analysis, significant topics for each author or various text-analytic metrics for George Eliot's poem 'How Lisa Loved the King' and James Joyce's 'Chamber Music', concerning e.g. lexical diversity or sentiment analysis. The GEPC is particularly suited for research in Digital Humanities, Natural Language Processing or Neurocognitive Poetics, e.g. as training and test corpus, or for stimulus development and control.
Computational synthesis planning approaches have achieved recent success in organic chemistry, where tabulated synthesis procedures are readily available for supervised learning. The syntheses of inorganic materials, however, exist primarily as natural language narratives contained within scientific journal articles. This synthesis information must first be extracted from the text in order to enable analogous synthesis planning methods for inorganic materials. In this work, we present a system for automatically extracting structured representations of synthesis procedures from the texts of materials science journal articles that describe explicit, experimental syntheses of inorganic compounds. We define the structured representation as a set of linked events made up of extracted scientific entities and evaluate two unsupervised approaches for extracting these structures on expert-annotated articles: a strong heuristic baseline and a generative model of procedural text. We also evaluate a variety of supervised models for extracting scientific entities. Our results provide insight into the nature of the data and directions for further work in this exciting new area of research.
A word embedding is a low-dimensional, dense and real- valued vector representation of a word. Word embeddings have been used in many NLP tasks. They are usually gener- ated from a large text corpus. The embedding of a word cap- tures both its syntactic and semantic aspects. Tweets are short, noisy and have unique lexical and semantic features that are different from other types of text. Therefore, it is necessary to have word embeddings learned specifically from tweets. In this paper, we present ten word embedding data sets. In addition to the data sets learned from just tweet data, we also built embedding sets from the general data and the combination of tweets with the general data. The general data consist of news articles, Wikipedia data and other web data. These ten embedding models were learned from about 400 million tweets and 7 billion words from the general text. In this paper, we also present two experiments demonstrating how to use the data sets in some NLP tasks, such as tweet sentiment analysis and tweet topic classification tasks.
Extracting the "correct" location information from text data, i.e., determining the place of event, has long been a goal for automated text processing. To approximate human-like coding schema, we introduce a supervised machine learning algorithm that classifies each location word to be either correct or incorrect. We use news articles collected from around the world (Integrated Crisis Early Warning System [ICEWS] data and Open Event Data Alliance [OEDA] data) to test our algorithm that consists of two stages. In the feature selection stage, we extract contextual information from texts, namely, the N-gram patterns for location words, the frequency of mention, and the context of the sentences containing location words. In the classification stage, we use three classifiers to estimate the model parameters in the training set and then to predict whether a location word in the test set news articles is the place of the event. The validation results show that our algorithm improves the accuracy rate of the current geolocation methods of dictionary approach by as much as 25%.
In this paper, we introduce the task of targeted aspect-based sentiment analysis. The goal is to extract fine-grained information with respect to entities mentioned in user comments. This work extends both aspect-based sentiment analysis that assumes a single entity per document and targeted sentiment analysis that assumes a single sentiment towards a target entity. In particular, we identify the sentiment towards each aspect of one or more entities. As a testbed for this task, we introduce the SentiHood dataset, extracted from a question answering (QA) platform where urban neighbourhoods are discussed by users. In this context units of text often mention several aspects of one or more neighbourhoods. This is the first time that a generic social media platform in this case a QA platform, is used for fine-grained opinion mining. Text coming from QA platforms is far less constrained compared to text from review specific platforms which current datasets are based on. We develop several strong baselines, relying on logistic regression and state-of-the-art recurrent neural networks.