Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of natural language processing (NLP). In this paper, we review significant deep learning related models and methods that have been employed for numerous NLP tasks and provide a walk-through of their evolution. We also summarize, compare and contrast the various models and put forward a detailed understanding of the past, present and future of deep learning in NLP.

No abstract

Affective computing is an emerging interdisciplinary research field bringing together researchers and practitioners from various fields, ranging from artificial intelligence, natural language processing, to cognitive and social sciences. With the proliferation of videos posted online (e.g., on YouTube, Facebook, Twitter) for product reviews, movie reviews, political views, and more, affective computing research has increasingly evolved from conventional unimodal analysis to more complex forms of multimodal analysis. This is the primary motivation behind our first of its kind, comprehensive literature review of the diverse field of affective computing. Furthermore, existing literature surveys lack a detailed discussion of state of the art in multimodal affect analysis frameworks, which this review aims to address. Multimodality is defined by the presence of more than one modality or channel, e.g., visual, audio, text, gestures, and eye gage. In this paper, we focus mainly on the use of audio, visual and text information for multimodal affect analysis, since around 90% of the relevant literature appears to cover these three modalities. Following an overview of different techniques for unimodal affect analysis, we outline existing methods for fusing information from different modalities. As part of this review, we carry out an extensive study of different categories of state-of-the-art fusion techniques, followed by a critical analysis of potential performance improvements with multimodal analysis compared to unimodal analysis. A comprehensive overview of these two complementary fields aims to form the building blocks for readers, to better understand this challenging and exciting research field

No abstract

Multimodal sentiment analysis is an increasingly popular research area, which extends the conventional language-based definition of sentiment analysis to a multimodal setup where other relevant modalities accompany language. In this paper, we pose the problem of multimodal sentiment analysis as modeling intra-modality and inter-modality dynamics. We introduce a novel model, termed Tensor Fusion Network, which learns both such dynamics end-to-end. The proposed approach is tailored for the volatile nature of spoken language in online videos as well as accompanying gestures and voice. In the experiments, our model outperforms state-ofthe-art approaches for both multimodal and unimodal sentiment analysis.

Multimodal sentiment analysis is a developing area of research, which involves the identification of sentiments in videos. Current research considers utterances as independent entities, i.e., ignores the interdependencies and relations among the utterances of a video. In this paper, we propose a LSTM-based model that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process. Our method shows 5-10% performance improvement over the state of the art and high robustness to generalizability.

Long noncoding RNAs (lncRNA) have been implicated in human cancer but their mechanisms of action are mainly undocumented. In this study, we investigated lncRNA alterations that contribute to gastric cancer through an analysis of The Cancer Genome Atlas RNA sequencing data and other publicly available microarray data. Here we report the gastric cancer-associated lncRNA HOXA11-AS as a key regulator of gastric cancer development and progression. Patients with high HOXA11-AS expression had a shorter survival and poorer prognosis. In vitro and in vivo assays of HOXA11-AS alterations revealed a complex integrated phenotype affecting cell growth, migration, invasion, and apoptosis. Strikingly, high-throughput sequencing analysis after HOXA11-AS silencing highlighted alterations in cell proliferation and cell-cell adhesion pathways. Mechanistically, EZH2 along with the histone demethylase LSD1 or DNMT1 were recruited by HOXA11-AS, which functioned as a scaffold. HOXA11-AS also functioned as a molecular sponge for miR-1297, antagonizing its ability to repress EZH2 protein translation. In addition, we found that E2F1 was involved in HOXA11-AS activation in gastric cancer cells. Taken together, our findings support a model in which the EZH2/HOXA11-AS/LSD1 complex and HOXA11-AS/miR-1297/EZH2 cross-talk serve as critical effectors in gastric cancer tumorigenesis and progression, suggesting new therapeutic directions in gastric cancer. Cancer Res; 76(21); 6299-310. ©2016 AACR.

No abstract