• Publications
  • Influence
Style Transfer in Text: Exploration and Evaluation
TLDR
In this paper, we propose to learn style transfer with non-parallel data and propose a general evaluation metric for style transfer in natural language processing. Expand
  • 227
  • 61
  • PDF
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
TLDR
We explore a general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction. Expand
  • 200
  • 33
  • PDF
Stack-Pointer Networks for Dependency Parsing
TLDR
We introduce a novel architecture for dependency parsing: \emph{stack-pointer networks} (\textbf{\textsc{StackPtr}}). Expand
  • 89
  • 22
  • PDF
Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings
TLDR
We consider the task of named entity recognition for Chinese social media. Expand
  • 120
  • 21
  • PDF
Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
TLDR
We combine the state-of-the-art Chinese word segmentation system (Chen et al., 2015) with the best Chinese social media NER model (Peng and Dredze, 2015). Expand
  • 101
  • 9
  • PDF
Plan-And-Write: Towards Better Automatic Storytelling
TLDR
We propose a plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. Expand
  • 81
  • 9
  • PDF
The Woman Worked as a Babysitter: On Biases in Language Generation
TLDR
We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. Expand
  • 29
  • 5
  • PDF
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
TLDR
In this paper, we explore using contextualized word embeddings to compute more accurate relatedness scores for automatic evaluation of open-domain dialogue systems. Expand
  • 14
  • 5
  • PDF
Multi-task Domain Adaptation for Sequence Tagging
TLDR
We propose a neural network framework that supports domain adaptation for multiple tasks simultaneously, and learns shared representations that better generalize for domain adaptation. Expand
  • 57
  • 4
  • PDF
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
TLDR
We investigate cross-lingual transfer and posit that an order-agnostic model will perform better when transferring to distant foreign languages. Expand
  • 41
  • 4
  • PDF