85 citations · 95 across the 2 of their papers we have counts for
4 papers
Source Attribution in Retrieval-Augmented Generation
Ikhtiyor Nematov, Tarik Kalai, Elizaveta Kuzmenko +4
While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Larg…
Representing ELMo embeddings as two-dimensional text online
Andrey Kutuzov, Elizaveta Kuzmenko
We describe a new addition to the WebVectors toolkit which is used to serve word embedding models over the Web. The new ELMoViz module adds support for contextualized embedding arc…
CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech
Y. L. Chung, E. Kuzmenko, S. S. Tekiroglu +1
Although there is an unprecedented effort to provide adequate responses in terms of laws and policies to hate content on social media platforms, dealing with hatred online is still…
To lemmatize or not to lemmatize: how word normalisation affects ELMo performance in word sense disambiguation
Andrey Kutuzov, Elizaveta Kuzmenko
We critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding E…