# Using CollGram to Compare Formulaic Language in Human and Neural Machine Translation

arXiv: https://arxiv.org/abs/2107.03625 · HTML: https://mlsanity.com/paper/2107.03625/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 28 references that are in the map.
- First posted on arXiv 8 Jul 2021.

## Builds on (most cited first, 3 of 3)

- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)

## Built on by (most cited first, 1 of 1)

- [Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus](https://mlsanity.com/paper/2206.10919/) (2022)

## Abstract (arXiv)

A comparison of formulaic sequences in human and neural machine translation of quality newspaper articles shows that neural machine translations contain less lower-frequency, but strongly-associated formulaic sequences, and more high-frequency formulaic sequences. These differences were statistically significant and the effect sizes were almost always medium or large. These observations can be related to the differences between second language learners of various levels and between translated and untranslated texts. The comparison between the neural machine translation systems indicates that some systems produce more formulaic sequences of both types than other systems.