A mobile terminal including a body; a touchscreen provided to a front and extending to side of the body and configured to display content; and a controller configured to detect one side of the body comes into contact with one side of an external terminal, display a first area on the touchscreen corresponding to a contact area of the body and the external terminal and a second area including the content, receive an input of moving the content displayed in the second area to the first area, display the content in the first area, and share the content in the first area with the external terminal.

Mobile terminal and method for controlling the same

Remaining useful life (RUL) prediction of lithium-ion batteries can assess the battery reliability to determine the advent of failure and mitigate battery risk. The existing RUL prediction techniques for lithium-ion batteries are inefficient for learning the long-term dependencies among the capacity degradations. This paper investigates deep-learning-enabled battery RUL prediction. The long short-term memory (LSTM) recurrent neural network (RNN) is employed to learn the long-term dependencies among the degraded capacities of lithium-ion batteries. The LSTM RNN is adaptively optimized using the resilient mean square back-propagation method, and a dropout technique is used to address the overfitting problem. The developed LSTM RNN is able to capture the underlying long-term dependencies among the degraded capacities and construct an explicitly capacity-oriented RUL predictor, whose long-term learning performance is contrasted to the support vector machine model, the particle filter model, and the simple RNN model. Monte Carlo simulation is combined to generate a probabilistic RUL prediction. Experimental data from multiple lithium-ion cells at two different temperatures is deployed for model construction, verification, and comparison. The developed method is able to predict the battery's RUL independent of offline training data, and when some offline data is available, the RUL can be predicted earlier than in the traditional methods.

Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface markers of African American English (AAE) and ratings of toxicity in several widely-used hate speech datasets. Then, we show that models trained on these corpora acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others. Finally, we propose *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.

/pdf/the-risk-of-racial-bias-in-hate-speech-detection-2kbqdhuica.pdf

The Risk of Racial Bias in Hate Speech Detection.

Speech emotion recognition with deep convolutional neural networks

The use of deep pre-trained transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding label, two approaches are common: Cross-encoders performing full self-attention over the pair and Bi-encoders encoding the pair separately. The former often performs better, but is too slow for practical use. In this work, we develop a new transformer architecture, the Poly-encoder, that learns global rather than token level self-attention features. We perform a detailed comparison of all three approaches, including what pre-training and fine-tuning strategies work best. We show our models achieve state-of-the-art results on four tasks; that Poly-encoders are faster than Cross-encoders and more accurate than Bi-encoders; and that the best results are obtained by pre-training on large datasets similar to the downstream tasks.

/pdf/poly-encoders-architectures-and-pre-training-strategies-for-149guslv6c.pdf

Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers. In this paper, we propose a novel deep dual recurrent encoder model that utilizes text data and audio signals simultaneously to obtain a better understanding of speech data. As emotional dialogue is composed of sound and spoken content, our model encodes the information from audio and text sequences using dual recurrent neural networks (RNNs) and then combines the information from these sources to predict the emotion class. This architecture analyzes speech data from the signal level to the language level, and it thus utilizes the information within the data more comprehensively than models that focus on audio features. Extensive experiments are conducted to investigate the efficacy and properties of the proposed model. Our proposed model outperforms previous state-of-the-art methods in assigning data to one of four emotion categories (i.e., angry, happy, sad and neutral) when the model is applied to the IEMOCAP dataset, as reflected by accuracies ranging from 68.8% to 71.8%.

Multimodal Speech Emotion Recognition Using Audio and Text

In this paper, we are interested in exploiting textual and acoustic data of an utterance for the speech emotion classification task. The baseline approach models the information from audio and text independently using two deep neural networks (DNNs). The outputs from both the DNNs are then fused for classification. As opposed to using knowledge from both the modalities separately, we propose a framework to exploit acoustic information in tandem with lexical data. The proposed framework uses two bi-directional long short-term memory (BLSTM) for obtaining hidden representations of the utterance. Furthermore, we propose an attention mechanism, referred to as the multi-hop, which is trained to automatically infer the correlation between the modalities. The multi-hop attention first computes the relevant segments of the textual data corresponding to the audio signal. The relevant textual data is then applied to attend parts of the audio signal. To evaluate the performance of the proposed system, experiments are performed in the IEMOCAP dataset. Experimental results show that the proposed technique outperforms the state-of-the-art system by 6.5% relative improvement in terms of weighted accuracy.

Speech Emotion Recognition Using Multi-hop Attention Mechanism

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning models. Recently, Hate and Abusive Speech on Twitter, a dataset much greater in size and reliability, has been released. However, this dataset has not been comprehensively studied to its potential. In this paper, we conduct the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and discuss the possibility of using additional features and context data for improvements. Experimental results show that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model scoring 0.805 F1.

/pdf/comparative-studies-of-detecting-abusive-language-on-twitter-3tgt3x0u78.pdf

Comparative Studies of Detecting Abusive Language on Twitter.

In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing. First, we explore the effect of additional information by adopting a pretrained language model to compute the vector representation of the input text and by applying transfer learning from a large-scale corpus. Second, we enhance the compare-aggregate model by proposing a novel latent clustering method to compute additional information within the target corpus and by changing the objective function from listwise to pointwise. To evaluate the performance of the proposed approaches, experiments are performed with the WikiQA and TREC-QA datasets. The empirical results demonstrate the superiority of our proposed approach, which achieve state-of-the-art performance for both datasets.

Seunghyun Yoon

Papers

Multimodal Speech Emotion Recognition Using Audio and Text

Speech Emotion Recognition Using Multi-hop Attention Mechanism

Multimodal Speech Emotion Recognition Using Audio and Text

Comparative Studies of Detecting Abusive Language on Twitter.

A Compare-Aggregate Model with Latent Clustering for Answer Selection