Derivationally related words, such as "runner" and "running", exhibit
se...
Multimodal embeddings aim to enrich the semantic information in neural
r...
In many real-world scenarios, the absence of external knowledge source l...
Accurately reporting what objects are depicted in an image is largely a
...
Pretrained embeddings based on the Transformer architecture have taken t...
Word embeddings have advanced the state of the art in NLP across numerou...
Can language models learn grounded representations from text distributio...
Compositionality is a widely discussed property of natural languages,
al...
Contextualized word embeddings, i.e. vector representations for words in...
Defining words in a textual context is a useful task both for practical
...
In this submission I report work in progress on learning simplified
inte...
The paper gives an overview of the Russian Semantic Similarity Evaluatio...
Semantic relatedness of terms represents similarity of meaning by a nume...
We introduce LAMBADA, a dataset to evaluate the capabilities of computat...