Mode recovery in neural autoregressive sequence modeling

Ilia Kulikov, Sean Welleck, Kyunghyun Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite its wide use, recent studies have revealed unexpected and undesirable properties of neural autoregressive sequence models trained with maximum likelihood, such as an unreasonably high affinity to short sequences after training and to infinitely long sequences at decoding time. We propose to study these phenomena by investigating how the modes, or local maxima, of a distribution are maintained throughout the full learning chain of the ground-truth, empirical, learned and decoding-induced distributions, via the newly proposed mode recovery cost. We design a tractable testbed where we build three types of ground-truth distributions: (1) an LSTM based structured distribution, (2) an unstructured distribution where probability of a sequence does not depend on its content, and (3) a product of these two which we call a semi-structured distribution. Our study reveals both expected and unexpected findings. First, starting with data collection, mode recovery cost strongly relies on the ground-truth distribution and is most costly with the semi-structured distribution. Second, after learning, mode recovery cost from the ground-truth distribution may increase or decrease compared to data collection, with the largest cost degradation occurring with the semi-structured ground-truth distribution. Finally, the ability of the decoding-induced distribution to recover modes from the learned distribution is highly impacted by the choices made earlier in the learning chain. We conclude that future research must consider the entire learning chain in order to fully understand the potentials and perils and to further improve neural autoregressive sequence models.

Original languageEnglish (US)
Title of host publicationSPNLP 2021 - 5th Workshop on Structured Prediction for NLP, Proceedings of the Workshop
EditorsZornitsa Kozareva, Sujith Ravi, Andreas Vlachos, Priyanka Agrawal, Andre F. T. Martins
PublisherAssociation for Computational Linguistics (ACL)
Pages44-52
Number of pages9
ISBN (Electronic)9781954085756
StatePublished - 2021
Event5th Workshop on Structured Prediction for NLP, SPNLP 2021 - Virtual, Bangkok, Thailand
Duration: Aug 6 2021 → …

Publication series

NameSPNLP 2021 - 5th Workshop on Structured Prediction for NLP, Proceedings of the Workshop

Conference

Conference5th Workshop on Structured Prediction for NLP, SPNLP 2021
Country/TerritoryThailand
CityVirtual, Bangkok
Period8/6/21 → …

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software

Fingerprint

Dive into the research topics of 'Mode recovery in neural autoregressive sequence modeling'. Together they form a unique fingerprint.

Cite this