Controlling Output Length in Neural Encoder-Decoders
arXiv:1609.09552
Abstract
Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods. Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.
11 pages. To appear in EMNLP 2016
References in corpus (8)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Sequence Level Training with Recurrent Neural Networks
- Effective Approaches to Attention-based Neural Machine Translation
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- A Persona-Based Neural Conversation Model
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- Generating News Headlines with Recurrent Neural Networks
- Pointing the Unknown Words
Cited by in corpus (22)
- Abstract Meaning Representation for Multi-Document Summarization
- Actor-Critic based Training Framework for Abstractive Summarization
- Explaining Question Answering Models through Text Generation
- Controlling the Output Length of Neural Machine Translation
- Deep Recurrent Generative Decoder for Abstractive Text Summarization
- Controllable Abstractive Summarization
- Length-controllable Abstractive Summarization by Guiding with Summary Prototype
- CoCon: A Self-Supervised Approach for Controlled Text Generation
- Deep Extrapolation for Attribute-Enhanced Generation
- Steering Output Style and Topic in Neural Response Generation
- Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
- Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
- Positional Encoding to Control Output Sequence Length
- Polite Dialogue Generation Without Parallel Data
- Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
- Controlling Length in Image Captioning
- LenAtten: An Effective Length Controlling Unit For Text Summarization
- Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning
- A Novel ILP Framework for Summarizing Content with High Lexical Variety
- TransSent: Towards Generation of Structured Sentences with Discourse Marker
- CUT: Controllable Unsupervised Text Simplification
- An Empirical Study of Extrapolation in Text Generation with Scalar Control