Controlling Output Length in Neural Encoder-Decoders

2016/09/30 by Kikuchi, Yuta, Neubig, Graham, Sasano, Ryohei +2 · 5 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/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.

Cited by

• Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
• ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions
• Reasoning-Guided Claim Normalization for Noisy Multilingual Social Media Posts
• Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
• Length Representations in Large Language Models

Related

• Positional Encoding to Control Output Sequence Length
• Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning
• Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
• Closed-Book Training to Improve Summarization Encoder Memory
• Windowing Models for Abstractive Summarization of Long Texts