Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation

By Marianna J. Martindale, Marine Carpuat, Kevin Duh, Paul McNamee. 2019

34 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

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

In Natural Language Processing

1. Pascale Fung
2. Andrea Madotto
3. Luke S. Zettlemoyer
4. Chunting Zhou
5. Jiatao Gu
6. Graham Neubig
7. Marjan Ghazvininejad
8. Mohit Bansal

Citations in the corpus

• Survey of Hallucination in Natural Language Generation (2022, methodology): “[116] propose identifying sentence adequacy using bag-of-vectors sentence similarity (BVSS) metric.”
• Detecting Hallucinated Content in Conditional Neural Sequence Generation (2020, background): “, 2019), or contain hallucinated content that is not entailed by the input (Maynez et al., 2020; Martindale et al., 2019).”
• It’s not a Non-Issue: Negation as a Source of Error in Machine Translation (2020, background): “Negation should be taken into consideration especially when deploying realworld systems which might produce incredibly fluent but inadequate output (Martindale et al., 2019).”
• The Curious Case of Hallucinations in Neural Machine Translation (2021, unknown): “In terms of adequacy of the generated output (Martindale et al., 2019), hallucinations are egregious mistakes that lie at the extreme end of NMT pathologies.”