Controllable Abstractive Summarization
arXiv:1711.05217
Abstract
Current models for document summarization disregard user preferences such as the desired length, style, the entities that the user might be interested in, or how much of the document the user has already read. We present a neural summarization model with a simple but effective mechanism to enable users to specify these high level attributes in order to control the shape of the final summaries to better suit their needs. With user input, our system can produce high quality summaries that follow user preferences. Without user input, we set the control variables automatically. On the full text CNN-Dailymail dataset, we outperform state of the art abstractive systems (both in terms of F1-ROUGE1 40.38 vs. 39.53 and human evaluation).
ACL2018 Workshop on Neural Machine Translation and Generation (NMT@ACL)
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- On the difficulty of training Recurrent Neural Networks
- Convolutional Sequence to Sequence Learning
- A Deep Reinforced Model for Abstractive Summarization
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- Adversarial Generation of Natural Language
- Controlling Output Length in Neural Encoder-Decoders
Cited by in corpus (15)
- Reducing Transformer Depth on Demand with Structured Dropout
- Neural Text Generation with Unlikelihood Training
- Pre-training via Paraphrasing
- ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
- Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
- Controlling the Output Length of Neural Machine Translation
- CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization
- Addressing Some Limitations of Transformers with Feedback Memory
- A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
- Improving Readability for Automatic Speech Recognition Transcription
- Retrieve and Refine: Improved Sequence Generation Models For Dialogue
- DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
- Nutribullets Hybrid: Multi-document Health Summarization
- Controlling Length in Image Captioning
- Neural MultiVoice Models for Expressing Novel Personalities in Dialog