• Publications
  • Influence
Abstractive Document Summarization with a Graph-Based Attentional Neural Model
TLDR
A novel graph-based attention mechanism in the sequence-to-sequence framework to address the saliency factor of summarization, which has been overlooked by prior works and is competitive with state-of-the-art extractive methods. Expand
From Neural Sentence Summarization to Headline Generation: A Coarse-to-Fine Approach
TLDR
A coarse-to-fine approach is proposed, which first identifies the important sentences of a document using document summarization techniques, and then exploits a multi-sentence summarization model with hierarchical attention to leverage the important sentence for headline generation. Expand
A Neural Approach to Pun Generation
TLDR
This paper proposes neural network models for homographic pun generation, and they can generate puns without requiring any pun data for training and are able to generate homographicpuns of good readability and quality. Expand
Learning to Recommend Quotes for Writing
TLDR
This paper collects abundant quotes from the Internet, and mine real contexts containing these quotes from large amount of electronic books, to build up a learning framework for quote recommendation, and applies a supervised learning to rank model to integrate multiple features. Expand
Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study
TLDR
This paper proposes an approach to extend the neural abstractive model trained on large scale SDS data to the MDS task, which makes use of a small number of multi-document summaries for fine tuning. Expand
A Neural Network Approach to Quote Recommendation in Writings
TLDR
This paper proposes a neural network approach based on LSTMs to the quote recommendation task, which directly learns the distributed meaning representations for the contexts and the quotes, and measures the relevance based on the meaning representations. Expand
QuoteRec: Toward Quote Recommendation for Writing
TLDR
A quote recommender system called QuoteRec is presented and two models to learn the vector representations of quotes and contexts are investigated, and the neural network model achieves state-of-the-art results on the quote recommendation task. Expand
Weakly Supervised Co-Training of Query Rewriting andSemantic Matching for e-Commerce
TLDR
This study investigates the instinctive connection between query rewriting and semantic matching tasks, and proposes a co-training framework to address the data sparseness problem when training deep neural networks. Expand
Learning to Order Natural Language Texts
TLDR
A set of features is introduced to characterize the order and coherence of natural language texts, and the learning to rank technique is used to determine the order of any two sentences and the total order of all sentences. Expand
Towards a Neural Network Approach to Abstractive Multi-Document Summarization
TLDR
This paper proposes an approach to extend the neural abstractive model trained on large scale SDS data to the MDS task, which makes use of a small number of multi-document summaries for fine tuning. Expand
...
1
2
...