Multi-task Learning for Target-dependent Sentiment Classification

arXiv.org Machine Learning

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.


A Beginner's Guide on Sentiment Analysis with RNN – Towards Data Science

@machinelearnbot

In order to feed this data into our RNN, all input documents must have the same length. We start building our model architecture in the code cell below. We have imported some layers from Keras that you might need but feel free to use any other layers / transformations you like. To summarize, our model is a simple RNN model with 1 embedding, 1 LSTM and 1 dense layers. We first need to compile our model by specifying the loss function and optimizer we want to use while training, as well as any evaluation metrics we'd like to measure.


Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment

arXiv.org Artificial Intelligence

The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE) task. The proposed method, which is inspired by a statistical hypothesis test, consists of two phases: the first phase is to introduce the predictability of textual entailment labels as a null hypothesis which is extremely unacceptable if a target corpus has no hidden bias, and the second phase is to test the null hypothesis using a Naive Bayes model. The experimental result of the Stanford Natural Language Inference (SNLI) corpus does not reject the null hypothesis. Therefore, it indicates that the SNLI corpus has a hidden bias which allows prediction of textual entailment labels from hypothesis sentences even if no context information is given by a premise sentence. This paper also presents the performance impact of NN models for RTE caused by this hidden bias.


The Use of NLP to Extract Unstructured Medical Data From Text - insideBIGDATA

#artificialintelligence

When working in healthcare, a lot of the relevant information for making accurate predictions and recommendations is only available in free-text clinical notes. Much of this data is trapped in free-text documents in unstructured form. This data is needed in order to make healthcare decisions. Hence, it is important to be able to extract data in the best possible way such that the information obtained can be analyzed and used. State-of-the-art NLP algorithms can extract clinical data from text using deep learning techniques such as healthcare-specific word embeddings, named entity recognition models, and entity resolution models.


Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification

arXiv.org Machine Learning

Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT). However, due to the especially expensive and labor-intensive labeling, existing public corpora in AT-level are all relatively small. Meanwhile, most of the previous methods rely on complicated structures with given scarce data, which largely limits the efficacy of the neural models. In this paper, we exploit a new direction named coarse-to-fine task transfer, which aims to leverage knowledge learned from a rich-resource source domain of the coarse-grained AC task, which is more easily accessible, to improve the learning in a low-resource target domain of the fine-grained AT task. To resolve both the aspect granularity inconsistency and feature mismatch between domains, we propose a Multi-Granularity Alignment Network (MGAN). In MGAN, a novel Coarse2Fine attention guided by an auxiliary task can help the AC task modeling at the same fine-grained level with the AT task. To alleviate the feature false alignment, a contrastive feature alignment method is adopted to align aspect-specific feature representations semantically. In addition, a large-scale multi-domain dataset for the AC task is provided. Empirically, extensive experiments demonstrate the effectiveness of the MGAN.