Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models

77 citations recorded by the source corpus.

How researchers see this paper

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

Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, background): “In fact, better understanding the behavior and effect of beam search in seq2seq models remains an active research topic (Cohen and Beck, 2019; Koehn and Knowles, 2017; Hokamp and Liu, 2017), and we believe how to perform effective beam search in our setup could be an interesting research question th”
If Beam Search Is the Answer, What Was the Question? (2020, background): “While several works explore this phenomenon (Murray and Chiang, 2018; Yang et al., 2018; Stahlberg and Byrne, 2019; Cohen and Beck, 2019), no one has yet hypothesized what beam search’s hidden inductive bias may be.”
Language Model Evaluation Beyond Perplexity (2021, methodology): “More specifically, we take this as quantitative evidence for recent qualitative observations that when left to generate lots of text, neural language models based on the transformer architecture tend to babble repetitively (Holtzman et al., 2020; Cohen and Beck, 2019; Eikema and Aziz, 2020).”
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation (2020, background): “Cohen and Beck (2019) show that translations obtained with larger beam sizes often consist of an unlikely prefix with an almost deterministic suffix and are of lower quality.”