University of Cambridge > Talks.cam > CQIF Seminar > A Quantum Search Decoder for Natural Language Processing

A Quantum Search Decoder for Natural Language Processing

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Johannes Bausch.

Probabilistic language models, e.g. those based on an LSTM , often face the problem of finding a high probability prediction from a sequence of random variables over a set of tokens. This is commonly addressed using a form of greedy decoding such as beam search, where a limited number of highest-likelihood paths (the beam width) of the decoder are kept, and at the end the maximum-likelihood path is chosen.

In this work, we construct a quantum algorithm to find the globally optimal parse (i.e. for infinite beam width) with high constant success probability. When the input to the decoder is distributed as a power-law with exponent k>0, our algorithm has runtime R^{n f(R,k)}, where f is upper-bounded by 1/2 and goes to 0 exponentially fast with increasing k, hence making our algorithm always more than quadratically faster than its classical counterpart.

We further modify our procedure to recover a finite beam width variant, which enables an even stronger empirical speedup while still retaining higher accuracy than possible classically. Finally, we apply this quantum beam search decoder to Mozilla’s implementation of Baidu’s DeepSpeech neural net, which we show to exhibit such a power law word rank frequency.

This talk is part of the CQIF Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity