Yanghui Rao

TL;DR: An Attentional Encoder Network (AEN) is proposed for targeted sentiment classification that eschews complex recurrent neural networks and employs attention based encoders for the modeling between context and target, which can excavate the rich introspective and interactive semantic information from the word embeddings without considering the distance between words.

TL;DR: An efficient algorithm and three pruning strategies are proposed to automatically build a word-level emotional dictionary for social emotion detection and a method based on topic modeling is proposed to construct a topic-level dictionary, where each topic is correlated with social emotions.

TL;DR: This article proposes two sentiment topic models to associate latent topics with evoked emotions of readers and shows that the generated social emotion lexicon samples show that the models can discover meaningful latent topics exhibiting emotion focus.

TL;DR: A topic-level maximum entropy (TME) model is proposed for social emotion classification over short text that generates topic- level features by modeling latent topics, multiple emotion labels, and valence scored by numerous readers jointly.

TL;DR: An Attentional Encoder Network (AEN) is proposed which eschews recurrence and employs attention based encoders for the modeling between context and target and raises the label unreliability issue and introduces label smoothing regularization.