• Publications
  • Influence
EmotionLines: An Emotion Corpus of Multi-Party Conversations
TLDR
We introduce EmotionLines, the first dataset with emotions labeling on all utterances in each dialogue only based on their textual content. Expand
  • 69
  • 16
  • PDF
SocialNLP 2018 EmotionX Challenge Overview: Recognizing Emotions in Dialogues
TLDR
This paper describes an overview of the Dialogue Emotion Recognition Challenge, EmotionX, at the Sixth SocialNLP Workshop, which recognizes the emotion of each utterance in dialogues. Expand
  • 16
  • 2
  • PDF
Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling
TLDR
In this paper, we proposed an inter-sentence diverse beam search which can generate interesting sentences and avoid redundancy given a sequence of similar photos. Expand
  • 11
  • 1
  • PDF
Knowledge-Enriched Visual Storytelling
TLDR
We introduce KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories. Expand
  • 4
  • 1
  • PDF
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
TLDR
We propose the entropy-enhanced dynamic memory network (DMN) to effectively model video modality, which can improve the model's ability to comprehend and memorize sequential information. Expand
  • 10
  • PDF
Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System
TLDR
In this paper, we proposed a multi-step joint-modality attention network (JMAN) based on recurrent neural network (RNN) to reason on videos. Expand
  • 5
  • PDF
Characterizing the Value of Information in Medical Notes
TLDR
We use two prediction tasks, readmission prediction and in-hospital mortality prediction, to characterize the value of information in medical notes. Expand
  • 1
  • PDF
Dixit: Interactive Visual Storytelling via Term Manipulation
TLDR
We introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. Expand