• Publications
  • Influence
A Diversity-Promoting Objective Function for Neural Conversation Models
TLDR
Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses regardless of the input. Expand
  • 912
  • 237
  • PDF
A Persona-Based Neural Conversation Model
TLDR
We present persona-based models for handling the issue of speaker consistency in neural response generation. Expand
  • 604
  • 127
  • PDF
Deep Reinforcement Learning for Dialogue Generation
TLDR
We introduce a neural conversational model based on the long-term success of dialogues to model future reward in dialogue generation. Expand
  • 742
  • 122
  • PDF
Adversarial Learning for Neural Dialogue Generation
TLDR
We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. Expand
  • 592
  • 81
  • PDF
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
TLDR
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Expand
  • 276
  • 74
  • PDF
A Hierarchical Neural Autoencoder for Paragraphs and Documents
TLDR
We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. Expand
  • 466
  • 40
  • PDF
Visualizing and Understanding Neural Models in NLP
TLDR
We explore multiple strategies for visualizing compositionality in neural models for NLP, inspired by similar work in computer vision. Expand
  • 388
  • 34
  • PDF
A Simple, Fast Diverse Decoding Algorithm for Neural Generation
TLDR
This paper includes material from the unpublished script "Mutual Information and Diverse Decoding Improve Neural Machine Translation" (Li and Jurafsky, 2016). Expand
  • 135
  • 28
  • PDF
Understanding Neural Networks through Representation Erasure
TLDR
A general methodology to analyze and interpret decisions from a neural model by observing the effects on the model of erasing various parts of the representation, such as input word-vector dimensions, intermediate hidden units, or input words. Expand
  • 230
  • 27
  • PDF
Towards a General Rule for Identifying Deceptive Opinion Spam
TLDR
We explore generalized approaches for identifying online deceptive opinion spam based on a new gold standard dataset, which is comprised of data from three different domains ( Hotel, Restaurant, Doctor), each of which contains three types of reviews, i.e. customer generated truthful reviews, Turker generated deceptive reviews and employee (domain-expert)generated deceptive reviews. Expand
  • 192
  • 24
  • PDF