Structure-Infused Copy Mechanisms for Abstractive Summarization
arXiv:1806.05658
Abstract
Seq2seq learning has produced promising results on summarization. However, in many cases, system summaries still struggle to keep the meaning of the original intact. They may miss out important words or relations that play critical roles in the syntactic structure of source sentences. In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from the source sentence to summary sentence. The approach naturally combines source dependency structure with the copy mechanism of an abstractive sentence summarizer. Experimental results demonstrate the effectiveness of incorporating source-side syntactic information in the system, and our proposed approach compares favorably to state-of-the-art methods.
13 pages
References in corpus (7)
- On the difficulty of training Recurrent Neural Networks
- A Deep Reinforced Model for Abstractive Summarization
- Selective Encoding for Abstractive Sentence Summarization
- Faithful to the Original: Fact Aware Neural Abstractive Summarization
- A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
- Efficient Summarization with Read-Again and Copy Mechanism
- Distraction-Based Neural Networks for Document Summarization
Cited by in corpus (22)
- Abstract Meaning Representation for Multi-Document Summarization
- Neural Abstractive Text Summarization with Sequence-to-Sequence Models
- Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
- Noisy Self-Knowledge Distillation for Text Summarization
- Scoring Sentence Singletons and Pairs for Abstractive Summarization
- Point-less: More Abstractive Summarization with Pointer-Generator Networks
- Reinforced Extractive Summarization with Question-Focused Rewards
- Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
- Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
- Controlling the Amount of Verbatim Copying in Abstractive Summarization
- Analyzing Sentence Fusion in Abstractive Summarization
- Contrastive Attention Mechanism for Abstractive Sentence Summarization
- Guiding Extractive Summarization with Question-Answering Rewards
- Lexicon-constrained Copying Network for Chinese Abstractive Summarization
- Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations
- A Novel ILP Framework for Summarizing Content with High Lexical Variety
- Selective Attention Encoders by Syntactic Graph Convolutional Networks for Document Summarization
- A Large-Scale Multi-Length Headline Corpus for Analyzing Length-Constrained Headline Generation Model Evaluation
- Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
- SgSum: Transforming Multi-document Summarization into Sub-graph Selection
- Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes
- Joint Parsing and Generation for Abstractive Summarization