activity
20172020
most citedBlackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brains

14 citations · 27 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG202013 cited

Transferring Inductive Biases through Knowledge Distillation

Samira Abnar, Mostafa Dehghani, Willem Zuidema

Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly represe…

cs.LG2020

Quantifying Attention Flow in Transformers

Samira Abnar, Willem Zuidema

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of th…

cs.CL2019

A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings

Niels van der Heijden, Samira Abnar, Ekaterina Shutova

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on z…

cs.AI201914 cited

Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brains

Samira Abnar, Lisa Beinborn, Rochelle Choenni +1

In this paper, we define and apply representational stability analysis (ReStA), an intuitive way of analyzing neural language models. ReStA is a variant of the popular representati…

cs.CL2017

Experiential, Distributional and Dependency-based Word Embeddings have Complementary Roles in Decoding Brain Activity

Samira Abnar, Rasyan Ahmed, Max Mijnheer +1

We evaluate 8 different word embedding models on their usefulness for predicting the neural activation patterns associated with concrete nouns. The models we consider include an ex…