Learning and Analyzing Generation Order for Undirected Sequence Models

by   Yichen Jiang, et al.

Undirected neural sequence models have achieved performance competitive with the state-of-the-art directed sequence models that generate monotonically from left to right in machine translation tasks. In this work, we train a policy that learns the generation order for a pre-trained, undirected translation model via reinforcement learning. We show that the translations decoded by our learned orders achieve higher BLEU scores than the outputs decoded from left to right or decoded by the learned order from Mansimov et al. (2019) on the WMT'14 German-English translation task. On examples with a maximum source and target length of 30 from De-En, WMT'16 English-Romanian, and WMT'21 English-Chinese translation tasks, our learned order outperforms all heuristic generation orders on four out of six tasks. We next carefully analyze the learned order patterns via qualitative and quantitative analysis. We show that our policy generally follows an outer-to-inner order, predicting the left-most and right-most positions first, and then moving toward the middle while skipping less important words at the beginning. Furthermore, the policy usually predicts positions for a single syntactic constituent structure in consecutive steps. We believe our findings could provide more insights on the mechanism of undirected generation models and encourage further research in this direction. Our code is publicly available at https://github.com/jiangycTarheel/undirected-generation


page 1

page 2

page 3

page 4


Asynchronous Bidirectional Decoding for Neural Machine Translation

The dominant neural machine translation (NMT) models apply unified atten...

An Empirical Study of Generation Order for Machine Translation

In this work, we present an empirical study of generation order for mach...

Regularizing Neural Machine Translation by Target-bidirectional Agreement

Although Neural Machine Translation (NMT) has achieved remarkable progre...

A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models

Undirected neural sequence models such as BERT have received renewed int...

Sequence Modeling with Unconstrained Generation Order

The dominant approach to sequence generation is to produce a sequence in...

Insertion-based Decoding with Automatically Inferred Generation Order

Conventional neural autoregressive decoding commonly assumes a left-to-r...

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter

Neural machine translation usually adopts autoregressive models and suff...

Please sign up or login with your details

Forgot password? Click here to reset