# Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization

arXiv: https://arxiv.org/abs/2011.02417 · HTML: https://mlsanity.com/paper/2011.02417/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 16 of 16)

- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Event knowledge in large language models: the gap between the impossible and the unlikely](https://mlsanity.com/paper/2212.01488/) (2022)
- [CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models](https://mlsanity.com/paper/2310.08753/) (2023)
- [How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure](https://mlsanity.com/paper/2311.04900/) (2023)
- [I am a Strange Dataset: Metalinguistic Tests for Language Models](https://mlsanity.com/paper/2401.05300/) (2024)
- [Generative linguistics contribution to artificial intelligence: Where this contribution lies?](https://mlsanity.com/paper/2410.20221/) (2024)
- [What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis](https://mlsanity.com/paper/2411.19858/) (2024)
- [MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations](https://mlsanity.com/paper/2310.11634/) (2023)
- [Grammatical information in BERT sentence embeddings as two-dimensional arrays](https://mlsanity.com/paper/2312.09890/) (2023)
- [Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation](https://mlsanity.com/paper/2201.01845/) (2022)
- [Investigating grammatical abstraction in language models using few-shot learning of novel noun gender](https://mlsanity.com/paper/2403.10338/) (2024)
- [Humans and transformer LMs: Abstraction drives language learning](https://mlsanity.com/paper/2603.17475/) (2026)
- [Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction](https://mlsanity.com/paper/2511.10441/) (2025)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [Connecting degree and polarity: An artificial language learning study](https://mlsanity.com/paper/2109.06333/) (2021)

## Abstract (arXiv)

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during training. We address this issue by deploying a novel word-learning paradigm to test BERT's few-shot learning capabilities for two aspects of English verbs: alternations and classes of selectional preferences. For the former, we fine-tune BERT on a single frame in a verbal-alternation pair and ask whether the model expects the novel verb to occur in its sister frame. For the latter, we fine-tune BERT on an incomplete selectional network of verbal objects and ask whether it expects unattested but plausible verb/object pairs. We find that BERT makes robust grammatical generalizations after just one or two instances of a novel word in fine-tuning. For the verbal alternation tests, we find that the model displays behavior that is consistent with a transitivity bias: verbs seen few times are expected to take direct objects, but verbs seen with direct objects are not expected to occur intransitively.