activity
20182024
most citedAnalyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

70 citations · 86 across the 7 of their papers we have counts for

collaborators

13 papers

cs.CL20241 cited

Information Flow Routes: Automatically Interpreting Language Models at Scale

Javier Ferrando, Elena Voita

Information flows by routes inside the network via mechanisms implemented in the model. These routes can be represented as graphs where nodes correspond to token representations an…

cs.CL20242 cited

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models

Igor Tufanov, Karen Hambardzumyan, Javier Ferrando +1

We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previousl…

cs.CL2023

Neurons in Large Language Models: Dead, N-gram, Positional

Elena Voita, Javier Ferrando, Christoforos Nalmpantis

We analyze a family of large language models in such a lightweight manner that can be done on a single GPU. Specifically, we focus on the OPT family of models ranging from 125m to…

cs.CL2023

HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation

David Dale, Elena Voita, Janice Lam +6

Hallucinations in machine translation are translations that contain information completely unrelated to the input. Omissions are translations that do not include some of the input…

cs.CL2021

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT

Elena Voita, Rico Sennrich, Ivan Titov

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural ne…

cs.CL2020

Embedding Words in Non-Vector Space with Unsupervised Graph Learning

Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova +1

It has become a de-facto standard to represent words as elements of a vector space (word2vec, GloVe). While this approach is convenient, it is unnatural for language: words form a…