Goto

Collaborating Authors

Learning to Learn from Weak Supervision by Full Supervision

arXiv.org Machine Learning

In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to control the magnitude of the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of supervised data. Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model.


Towards Controlled Transformation of Sentiment in Sentences

arXiv.org Artificial Intelligence

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.


5 Things You Need to Know about Sentiment Analysis and Classification

@machinelearnbot

In the last years, Sentiment Analysis has become a hot-trend topic of scientific and market research in the field of Natural Language Processing (NLP) and Machine Learning. Below, you can find 5 useful things you need to know about Sentiment Analysis that are connected to Social Media, Datasets, Machine Learning, Visualizations, and Evaluation Methods applied by researchers and market experts. Sentiment Analysis examines the problem of studying texts, like posts and reviews, uploaded by users on microblogging platforms, forums, and electronic businesses, regarding the opinions they have about a product, service, event, person or idea. The most common use of Sentiment Analysis is this of classifying a text to a class. Depending on the dataset and the reason, Sentiment Classification can be binary (positive or negative) or multi-class (3 or more classes) problem.


Learning Sentiment-Specific Word Embedding via Global Sentiment Representation

AAAI Conferences

Context-based word embedding learning approaches can model rich semantic and syntactic information. However, it is problematic for sentiment analysis because the words with similar contexts but opposite sentiment polarities, such as good and bad, are mapped into close word vectors in the embedding space. Recently, some sentiment embedding learning methods have been proposed, but most of them are designed to work well on sentence-level texts. Directly applying those models to document-level texts often leads to unsatisfied results. To address this issue, we present a sentiment-specific word embedding learning architecture that utilizes local context informationas well as global sentiment representation. The architecture is applicable for both sentence-level and document-level texts. We take global sentiment representation as a simple average of word embeddings in the text, and use a corruption strategy as a sentiment-dependent regularization. Extensive experiments conducted on several benchmark datasets demonstrate that the proposed architecture outperforms the state-of-the-art methods for sentiment classification.


Sentiment Analysis: Types, Tools, and Use Cases

#artificialintelligence

What do you do before purchasing something that costs more than a pack of gum? Whether you want to treat yourself to new sneakers, a laptop, or an overseas tour, processing an order without checking out similar products or offers and reading reviews doesn't make much sense anymore. Thanks to comment sections on eCommerce sites, social nets, review platforms, or dedicated forums, you can learn a ton about a product or service and evaluate whether it's a good value for money. Other customers, including your potential clients, will do all the above. People's desire to engage with businesses and the overall brand perception depends heavily on public opinion.