Learning deterministic weighted automata with queries and counterexamples

Gail Weiss, Yoav Goldberg, Eran Yahav

Research output: Contribution to journalConference articlepeer-review

35 Scopus citations

Abstract

We present an algorithm for extraction of a probabilistic deterministic finite automaton (PDFA) from a given black-box language model, such as a recurrent neural network (RNN). The algorithm is a variant of the exact-learning algorithm L*, adapted to a probabilistic setting with noise. The key insight is the use of conditional probabilities for observations, and the introduction of a local tolerance when comparing them. When applied to RNNs, our algorithm often achieves better word error rate (WER) and normalised distributed cumulative gain (NDCG) than that achieved by spectral extraction of weighted finite automata (WFA) from the same networks. PDFAs are substantially more expressive than n-grams, and are guaranteed to be stochastic and deterministic - unlike spectrally extracted WFAs.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Volume32
StatePublished - 2019
Event33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019

Bibliographical note

Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.

Funding

The authors wish to thank Rémi Eyraud for his helpful discussions and comments, and Chris Ham-merschmidt for his assistance in obtaining the results with FLEXFRINGE . The research leading to the results presented in this paper is supported by the Israeli Science Foundation (grant No.1319/16), and the European Research Council (ERC) under the European Union’s Seventh Framework Programme (FP7-2007-2013), under grant agreement no. 802774 (iEXTRACT). The authors wish to thank R?mi Eyraud for his helpful discussions and comments, and Chris Hammerschmidt for his assistance in obtaining the results with FLEXFRINGE. The research leading to the results presented in this paper is supported by the Israeli Science Foundation (grant No.1319/16), and the European Research Council (ERC) under the European Union's Seventh Framework Programme (FP7-2007-2013), under grant agreement no. 802774 (iEXTRACT).

FundersFunder number
FLEXFRINGE
Israeli Science Foundation1319/16
European Commission
Seventh Framework Programme802774, FP7-2007-2013

    Fingerprint

    Dive into the research topics of 'Learning deterministic weighted automata with queries and counterexamples'. Together they form a unique fingerprint.

    Cite this