Sarcasm requires some shared knowledge between speaker and audience; it is a profoundly contextual phenomenon. Most computational approaches to sarcasm detection, however, treat it as a purely linguistic matter, using information such as lexical cues and their corresponding sentiment as predictive features. We show that by including extra-linguistic information from the context of an utterance ...

Abstract: The roles played by learning and memorization represent an important topic in deep learning research. Recent work on this subject has shown that the optimization behavior of DNNs trained on shuffled labels is qualitatively different from DNNs trained with real labels. Here, we propose a novel permutation approach that can differentiate memorization from learning in deep neural network...

Adversarial training is an effective way to defend deep neural networks (DNN) against adversarial examples. However, there are atypical samples that rare and hard learn, or even hurt DNNs' generalization performance on test data. In this paper, we propose a novel algorithm reweight the based self-supervised techniques mitigate negative effects of samples. Specifically, memory bank built record ...

This research addresses the use of mobile devices with both embedded and external sensors to provide contextualized help, advice, and remediation to learners engaged in real-world learn-by-doing tasks. This work is situated within the context of learning a complex procedure, in particular emergency responders learning to conduct urban search and rescue operations. Research issues include the de...

This work presents a supervised prepositional phrase (PP) attachment disambiguation system that uses contextualized distributional information as the distance metric for a nearest-neighbor classifier. Contextualized word vectors constructed from the GigaWord Corpus provide a method for implicit Word Sense Disambiguation (WSD), whose reliability helps this system outperform baselines and achieve...

There has a large scale annotated newswire data for Chinese word segmentation. However, some research proves that the performance of the segmenter has significant decrease when applying the model trained on the newswire to other domain, such as patent and literature. The same character appeared in different words may be in different position and with different meaning. In this paper, we introdu...

This study aims to investigate the effectiveness of a storytelling approach in Chinese adult e-learners’ vocabulary learning. Two classes of 60 students participated in the experiment, with 30 in the experimental group and 30 in the control group. The storytelling approach and the rote memorization approach were employed by the two groups respectively in one teaching session of 30 minutes. Two ...