Papers by Piotr Mardziel

1 papers
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models (2020.acl-main)

Copied to clipboard

Challenge: LSTMs can capture syntactic rules in artificial languages, but it is unclear whether they are as capable in natural languages.
Approach: They propose a causal account of structural properties as carried by paths across gates and neurons of a recurrent neural network that localizes and segments the concept into a set of gate or neuron-level paths.
Outcome: The proposed model improves on a widely-studied multi-layer LSTM language model showing that it can learn subject-verb number agreement in English.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations