5 papers
Quantifying Compositionality of Classic and State-of-the-Art Embeddings
Zhijin Guo, Chenhao Xue, Zhaozhen Xu +4
For language models to generalize correctly to novel expressions, it is critical that they exploit access compositional meanings when this is justified. Even if we don't know what…
Compositional Fusion of Signals in Data Embedding
Zhijin Guo, Zhaozhen Xu, Martha Lewis +1
Embeddings in AI convert symbolic structures into fixed-dimensional vectors, effectively fusing multiple signals. However, the nature of this fusion in real-world data is often unc…
EXTRACT: Explainable Transparent Control of Bias in Embeddings
Zhijin Guo, Zhaozhen Xu, Martha Lewis +1
Knowledge Graphs are a widely used method to represent relations between entities in various AI applications, and Graph Embedding has rapidly become a standard technique to represe…
QBERT: Generalist Model for Processing Questions
Zhaozhen Xu, Nello Cristianini
Using a single model across various tasks is beneficial for training and applying deep neural sequence models. We address the problem of developing generalist representations of te…
What makes us curious? analysis of a corpus of open-domain questions
Zhaozhen Xu, Amelia Howarth, Nicole Briggs +1
Every day people ask short questions through smart devices or online forums to seek answers to all kinds of queries. With the increasing number of questions collected it becomes di…