# Transformers in the loop: Polarity in neural models of language

arXiv: https://arxiv.org/abs/2109.03926 · HTML: https://mlsanity.com/paper/2109.03926/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 8 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://mlsanity.com/paper/1809.00042/) (2018)
- [Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs](https://mlsanity.com/paper/1909.02597/) (2019)
- [Can neural networks understand monotonicity reasoning?](https://mlsanity.com/paper/1906.06448/) (2019)
- [On the proper role of linguistically-oriented deep net analysis in linguistic theorizing](https://mlsanity.com/paper/2106.08694/) (2021)
- [Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items](https://mlsanity.com/paper/1808.10627/) (2018)
- [HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning](https://mlsanity.com/paper/1904.12166/) (2019)
- [Language Models Use Monotonicity to Assess NPI Licensing](https://mlsanity.com/paper/2105.13818/) (2021)
- [The Sensitivity of Language Models and Humans to Winograd Schema Perturbations](https://mlsanity.com/paper/2005.01348/) (2020)
- [Contextualized Word Embeddings Encode Aspects of Human-Like Word Sense Knowledge](https://mlsanity.com/paper/2010.13057/) (2020)
- [Language Modelling as a Multi-Task Problem](https://mlsanity.com/paper/2101.11287/) (2021)

## Abstract (arXiv)

Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not always the most adequate set-up. We probe polarity via so-called 'negative polarity items' (in particular, English 'any') in two pre-trained Transformer-based models (BERT and GPT-2). We show that - at least for polarity - metrics derived from language models are more consistent with data from psycholinguistic experiments than linguistic theory predictions. Establishing this allows us to more adequately evaluate the performance of language models and also to use language models to discover new insights into natural language grammar beyond existing linguistic theories. This work contributes to establishing closer ties between psycholinguistic experiments and experiments with language models.