Steven Derby

TL;DR: This paper combines multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint Non-Negative Sparse Embedding and demonstrates their ability to predict interpretable linguistic descriptions of human ground-truth semantic knowledge.

TL;DR: The authors propose a method for mapping human property knowledge onto a distributional semantic space, which adapts the word2vec architecture to the task of modelling concept features, which makes for easy and efficient ranking of candidate human-derived semantic properties for arbitrary words.

TL;DR: A systematic analysis of how closely the intermediate layers from LSTM and trans former language models correspond to human semantic knowledge indicates that the transformer models are better at capturing semantic knowledge relating to lexical concepts, both during word prediction and when retention is required.

TL;DR: Comparisons are made between the input and output embeddings and other SOTA distributional models to gain a better understanding of the types of information they represent and create locally-optimal approximations for the intermediate representations from the language model.