Papers by Christian Clark
Categorial grammar induction from raw data (2023.findings-acl)
Copied to clipboard
| Challenge: | a new model for categorial grammar induction is based on raw data without part-of-speech information. |
| Approach: | They propose a grammar induction model that learns from raw data without part-of-speech information. |
| Outcome: | a new model for inducing a basic categorial grammar is developed . the model attains a recall-homogeneity of 0.33 on average, and a bias toward forward function application is added . |
Linear Recency Bias During Training Improves Transformers’ Fit to Reading Times (2025.coling-main)
Copied to clipboard
| Challenge: | Recent research has shown a strong fit between surprisal values from Transformers and reading times. |
| Approach: | They evaluate a Transformer model that uses a recency bias added to attention scores to improve the fit to human reading times. |
| Outcome: | The proposed model improves on a Transformer that includes a recency bias added to attention scores. |
Categorial Grammar Induction with Stochastic Category Selection (2024.lrec-main)
Copied to clipboard
| Challenge: | categorial grammar inducers have been used to learn from raw data, but they use shortcuts to ensure branching behavior. |
| Approach: | They propose a grammar inducer that learns from raw data and does not rely on bias terms . they show a recall-homogeneity of 0.48 on a corpus of English child-directed speech . |
| Outcome: | The proposed model achieves a recall-homogeneity of 0.48 on a corpus of English child-directed speech . |
Surprisal Estimators for Human Reading Times Need Character Models (2021.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that character models can be applied to a structural parser-based processing model to calculate word generation probabilities. |
| Approach: | They propose to use a character model to calculate word generation probabilities from a structural parser-based processing model. |
| Outcome: | The proposed model performs better on self-paced reading, eye-tracking, and fMRI data than large-scale language models trained on much more data. |