• Publications
  • Influence
Language to Logical Form with Neural Attention
TLDR
We present a general method based on an attention-enhanced encoder-decoder model for semantic parsing using recurrent neural networks with long short-term memory units. Expand
  • 423
  • 56
  • PDF
Unified Language Model Pre-training for Natural Language Understanding and Generation
TLDR
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. Expand
  • 308
  • 52
  • PDF
Long Short-Term Memory-Networks for Machine Reading
TLDR
We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning with memory and attention. Expand
  • 558
  • 50
  • PDF
Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification
TLDR
We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification. Expand
  • 403
  • 49
  • PDF
Coarse-to-Fine Decoding for Neural Semantic Parsing
TLDR
We propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Expand
  • 183
  • 24
  • PDF
Data-to-Text Generation with Content Selection and Planning
TLDR
We present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training, improving the state-of-the-art on the RotoWire dataset. Expand
  • 89
  • 24
  • PDF
Learning to Generate Product Reviews from Attributes
TLDR
This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating. Expand
  • 81
  • 20
  • PDF
Question Answering over Freebase with Multi-Column Convolutional Neural Networks
TLDR
We introduce multi-column convolutional neural networks to understand questions from three different aspects (namely, answer path, answer context, and answer type) and learn their distributed representations. Expand
  • 289
  • 19
  • PDF
Ranking with Recursive Neural Networks and Its Application to Multi-Document Summarization
TLDR
We develop a Ranking framework upon Recursive Neural Networks (R2N2) to rank sentences for multi-document summarization. Expand
  • 166
  • 14
  • PDF
Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction
TLDR
In this paper, we develop a novel approach to aspect term extraction based on unsupervised learning of distributed representations of words and dependency paths. Expand
  • 98
  • 14
  • PDF