Andrea E. Martin


Displaying 1 - 3 of 3
  • Coopmans, C. W., De Hoop, H., Kaushik, K., Hagoort, P., & Martin, A. E. (2021). Structure-(in)dependent interpretation of phrases in humans and LSTMs. In Proceedings of the Society for Computation in Linguistics (SCiL 2021) (pp. 459-463).


    In this study, we compared the performance of a long short-term memory (LSTM) neural network to the behavior of human participants on a language task that requires hierarchically structured knowledge. We show that humans interpret ambiguous noun phrases, such as second blue ball, in line with their hierarchical constituent structure. LSTMs, instead, only do so after unambiguous training, and they do not systematically generalize to novel items. Overall, the results of our simulations indicate that a model can behave hierarchically without relying on hierarchical constituent structure.
  • Doumas, L. A. A., Martin, A. E., & Hummel, J. E. (2020). Relation learning in a neurocomputational architecture supports cross-domain transfer. In S. Denison, M. Mack, Y. Xu, & B. C. Armstrong (Eds.), Proceedings of the 42nd Annual Virtual Meeting of the Cognitive Science Society (CogSci 2020) (pp. 932-937). Montreal, QB: Cognitive Science Society.


    Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning have begun to approximate and even surpass human performance, but these systems struggle to generalize what they have learned to untrained situations. We present a model based on wellestablished neurocomputational principles that demonstrates human-level generalisation. This model is trained to play one video game (Breakout) and performs one-shot generalisation to a new game (Pong) with different characteristics. The model generalizes because it learns structured representations that are functionally symbolic (viz., a role-filler binding calculus) from unstructured training data. It does so without feedback, and without requiring that structured representations are specified a priori. Specifically, the model uses neural co-activation to discover which characteristics of the input are invariant and to learn relational predicates, and oscillatory regularities in network firing to bind predicates to arguments. To our knowledge, this is the first demonstration of human-like generalisation in a machine system that does not assume structured representa- tions to begin with.
  • Hashemzadeh, M., Kaufeld, G., White, M., Martin, A. E., & Fyshe, A. (2020). From language to language-ish: How brain-like is an LSTM representation of nonsensical language stimuli? In Findings of the Association for Computational Linguistics: EMNLP 2020 (pp. 645-655).


    The representations generated by many mod- els of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people read. However, these decoding results are usually based on the brain’s reaction to syntactically and semantically sound language stimuli. In this study, we asked: how does an LSTM (long short term memory) language model, trained (by and large) on semantically and syntac- tically intact language, represent a language sample with degraded semantic or syntactic information? Does the LSTM representation still resemble the brain’s reaction? We found that, even for some kinds of nonsensical lan- guage, there is a statistically significant rela- tionship between the brain’s activity and the representations of an LSTM. This indicates that, at least in some instances, LSTMs and the human brain handle nonsensical data similarly.

Share this page