DeepAI AI Chat
Log In Sign Up

On Decoding Strategies for Neural Text Generators

by   Gian Wiher, et al.
ETH Zurich

When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation tasks. For example, while mode-seeking methods like beam search perform remarkably well for machine translation, they have been observed to lead to incoherent and repetitive text in story generation. Despite such observations, the effectiveness of decoding strategies is often assessed with respect to only a single task. This work – in contrast – provides a comprehensive analysis of the interaction between language generation tasks and decoding strategies. Specifically, we measure changes in attributes of generated text as a function of both decoding strategy and task using human and automatic evaluation. Our results reveal both previously-observed and surprising findings. For example, the nature of the diversity-quality trade-off in language generation is very task-specific; the length bias often attributed to beam search is not constant across tasks.


If beam search is the answer, what was the question?

Quite surprisingly, exact maximum a posteriori (MAP) decoding of neural ...

On the probability-quality paradox in language generation

When generating natural language from neural probabilistic models, high ...

BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation

This study mainly investigates two decoding problems in neural keyphrase...

How Decoding Strategies Affect the Verifiability of Generated Text

Language models are of considerable importance. They are used for pretra...

Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG

Some Natural Language Generation (NLG) tasks require both faithfulness a...

Language Model Decoding as Likelihood-Utility Alignment

A critical component of a successful language generation pipeline is the...

Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG

Ever since neural models were adopted in data-to-text language generatio...