Timezone: »
Neural networks models for NLP are typically implemented without the explicit encoding of language rules and yet they are able to break one performance record after another. This has generated a lot of research interest in interpreting the representations learned by these networks. We propose here a novel interpretation approach that relies on the only processing system we have that does understand language: the human brain. We use brain imaging recordings of subjects reading complex natural text to interpret word and sequence embeddings from 4 recent NLP models - ELMo, USE, BERT and Transformer-XL. We study how their representations differ across layer depth, context length, and attention type. Our results reveal differences in the context-related representations across these models. Further, in the transformer models, we find an interaction between layer depth and context length, and between layer depth and attention type. We finally hypothesize that altering BERT to better align with brain recordings would enable it to also better understand language. Probing the altered BERT using syntactic NLP tasks reveals that the model with increased brain-alignment outperforms the original model. Cognitive neuroscientists have already begun using NLP networks to study the brain, and this work closes the loop to allow the interaction between NLP and cognitive neuroscience to be a true cross-pollination.
Author Information
Mariya Toneva (Carnegie Mellon University)
Leila Wehbe (Carnegie Mellon University)
More from the Same Authors
-
2021 Poster: Can fMRI reveal the representation of syntactic structure in the brain? »
Aniketh Janardhan Reddy · Leila Wehbe -
2020 Session: Orals & Spotlights Track 35: Neuroscience/Probabilistic »
Leila Wehbe · Francisco Ruiz -
2020 Poster: Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction »
Mariya Toneva · Otilia Stretcu · Barnabas Poczos · Leila Wehbe · Tom Mitchell -
2019 : Closing remarks »
Leila Wehbe -
2019 : Poster Session + Lunch »
Maxwell Nye · Robert Kim · Toby St Clere Smithe · Takeshi D. Itoh · Omar U. Florez · Vesna G. Djokic · Sneha Aenugu · Mariya Toneva · Imanol Schlag · Dan Schwartz · Max Raphael Sobroza Marques · Pravish Sainath · Peng-Hsuan Li · Rishi Bommasani · Najoung Kim · Paul Soulos · Steven Frankland · Nadezhda Chirkova · Dongqi Han · Adam Kortylewski · Rich Pang · Milena Rabovsky · Jonathan Mamou · Vaibhav Kumar · Tales Marra -
2019 Poster: Inducing brain-relevant bias in natural language processing models »
Dan Schwartz · Mariya Toneva · Leila Wehbe -
2019 Poster: Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity »
Aria Wang · Michael Tarr · Leila Wehbe