# Another Dead End for Morphological Tags? Perturbed Inputs and Parsing

arXiv: https://arxiv.org/abs/2305.15119 · HTML: https://mlsanity.com/paper/2305.15119/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 16 of 16)

- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [Evaluating the Robustness of Neural Language Models to Input Perturbations](https://mlsanity.com/paper/2108.12237/) (2021)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [Left-to-Right Dependency Parsing with Pointer Networks](https://mlsanity.com/paper/1903.08445/) (2019)
- [Bracketing Encodings for 2-Planar Dependency Parsing](https://mlsanity.com/paper/2011.00596/) (2020)
- [Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs](https://mlsanity.com/paper/1508.00657/) (2015)
- [An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing](https://mlsanity.com/paper/1808.09060/) (2018)
- [Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?](https://mlsanity.com/paper/2003.03204/) (2020)
- [A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing](https://mlsanity.com/paper/2106.04222/) (2021)
- [What Taggers Fail to Learn, Parsers Need the Most](https://mlsanity.com/paper/2104.01083/) (2021)
- [Parsing linearizations appreciate PoS tags - but some are fussy about errors](https://mlsanity.com/paper/2210.15219/) (2022)

## Abstract (arXiv)

The usefulness of part-of-speech tags for parsing has been heavily questioned due to the success of word-contextualized parsers. Yet, most studies are limited to coarse-grained tags and high quality written content; while we know little about their influence when it comes to models in production that face lexical errors. We expand these setups and design an adversarial attack to verify if the use of morphological information by parsers: (i) contributes to error propagation or (ii) if on the other hand it can play a role to correct mistakes that word-only neural parsers make. The results on 14 diverse UD treebanks show that under such attacks, for transition- and graph-based models their use contributes to degrade the performance even faster, while for the (lower-performing) sequence labeling parsers they are helpful. We also show that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.