research
∙
02/01/2023
Feed-Forward Blocks Control Contextualization in Masked Language Models
Understanding the inner workings of neural network models is a crucial s...
share
research
∙
01/17/2023
Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers
How language models process complex input that requires multiple steps o...
research
∙
05/23/2022
Context Limitations Make Neural Language Models More Human-Like
Do modern natural language processing (NLP) models exhibit human-like la...
research
∙
10/09/2020
Langsmith: An Interactive Academic Text Revision System
Despite the current diversity and inclusion initiatives in the academic ...
research
∙
06/02/2020
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition
In general, the labels used in sequence labeling consist of different ty...
research
∙
04/30/2020
Word Rotator's Distance: Decomposing Vectors Gives Better Representations
One key principle for assessing semantic similarity between texts is to ...
research
∙
04/21/2020
Attention Module is Not Only a Weight: Analyzing Transformers with Vector Norms
Because attention modules are core components of Transformer-based model...
research
∙
10/10/2019
