# Not quite there yet: Combining analogical patterns and encoder-decoder networks for cognitively plausible inflection

arXiv: https://arxiv.org/abs/2108.03968 · HTML: https://mlsanity.com/paper/2108.03968/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 37 references that are in the map.
- First posted on arXiv 9 Aug 2021.

## Builds on (most cited first, 5 of 5)

- [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](https://mlsanity.com/paper/1512.05287/) (2015)
- [UniMorph 2.0: Universal Morphology](https://mlsanity.com/paper/1810.11101/) (2018)
- [Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate](https://mlsanity.com/paper/1807.04783/) (2018)
- [Morphological Inflection Generation Using Character Sequence to Sequence Learning](https://mlsanity.com/paper/1512.06110/) (2015)
- [Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection](https://mlsanity.com/paper/1906.01280/) (2019)

## Built on by (most cited first, 2 of 2)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model](https://mlsanity.com/paper/2310.15113/) (2023)

## Abstract (arXiv)

The paper presents four models submitted to Part 2 of the SIGMORPHON 2021 Shared Task 0, which aims at replicating human judgements on the inflection of nonce lexemes. Our goal is to explore the usefulness of combining pre-compiled analogical patterns with an encoder-decoder architecture. Two models are designed using such patterns either in the input or the output of the network. Two extra models controlled for the role of raw similarity of nonce inflected forms to existing inflected forms in the same paradigm cell, and the role of the type frequency of analogical patterns. Our strategy is entirely endogenous in the sense that the models appealing solely to the data provided by the SIGMORPHON organisers, without using external resources. Our model 2 ranks second among all submitted systems, suggesting that the inclusion of analogical patterns in the network architecture is useful in mimicking speakers' predictions.