If Beam Search Is the Answer, What Was the Question?

By Clara Meister, Tim Vieira, Ryan Cotterell. 2020

176 citations recorded by the source corpus.

Quite surprisingly, exact maximum a posteriori (MAP) decoding of neural language generators frequently leads to low-quality results. Rather, most state-of-the-art results on language generation tasks are attained using beam search despite its overwhelmingly high search error rate. This implies that the MAP objective alone does not express the properties we desire in text, which merits the question: if beam search is the answer, what was the question? We frame beam search as the exact solution to a different decoding objective in order to gain insights into why high probability under a model alone may not indicate adequacy. We find that beam search enforces uniform information density in text, a property motivated by cognitive science. We suggest a set of decoding objectives that explicitly enforce this property and find that exact decoding with these objectives alleviates the problems encountered when decoding poorly calibrated language generation models. Additionally, we analyze the text produced using various decoding strategies and see that, in our neural machine translation experiments, the extent to which this property is adhered to strongly correlates with BLEU.

Subfields: Artificial Intelligence, Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Sergey Levine
  2. Michael Janner
  3. Qiyang Li
  4. Ilya Kostrikov
  5. Mengjiao Yang
  6. Ryan Cotterell
  7. Pieter Abbeel
  8. Chelsea Finn

In Natural Language Processing

  1. Sergey Levine
  2. Michael Janner
  3. Qiyang Li
  4. Tiago Pimentel
  5. Charles Burton Snell
  6. Clara Meister
  7. Ryan Cotterell
  8. Ilya Kostrikov

In Machine Translation

  1. Sergey Levine
  2. Michael Janner
  3. Qiyang Li
  4. Clara Meister
  5. Ryan Cotterell

Citations in the corpus