A comprehensive survey on word representation models: From classical to state-of-the-art word representation language models

U Naseem, I Razzak, SK Khan, M Prasad - Transactions on Asian and …, 2021 - dl.acm.org
Word representation has always been an important research area in the history of natural
language processing (NLP). Understanding such complex text data is imperative, given that …

[HTML][HTML] A reproducible survey on word embeddings and ontology-based methods for word similarity: Linear combinations outperform the state of the art

JJ Lastra-Díaz, J Goikoetxea, MAH Taieb… - … Applications of Artificial …, 2019 - Elsevier
Human similarity and relatedness judgements between concepts underlie most of cognitive
capabilities, such as categorisation, memory, decision-making and reasoning. For this …

Intrinsic bias metrics do not correlate with application bias

S Goldfarb-Tarrant, R Marchant, RM Sánchez… - arxiv preprint arxiv …, 2020 - arxiv.org
Natural Language Processing (NLP) systems learn harmful societal biases that cause them
to amplify inequality as they are deployed in more and more situations. To guide efforts at …

Cross-lingual transfer learning for multilingual task oriented dialog

S Schuster, S Gupta, R Shah, M Lewis - arxiv preprint arxiv:1810.13327, 2018 - arxiv.org
One of the first steps in the utterance interpretation pipeline of many task-oriented
conversational AI systems is to identify user intents and the corresponding slots. Since data …

Learning general purpose distributed sentence representations via large scale multi-task learning

S Subramanian, A Trischler, Y Bengio… - arxiv preprint arxiv …, 2018 - arxiv.org
A lot of the recent success in natural language processing (NLP) has been driven by
distributed vector representations of words trained on large amounts of text in an …

From word to sense embeddings: A survey on vector representations of meaning

J Camacho-Collados, MT Pilehvar - Journal of Artificial Intelligence …, 2018 - jair.org
Over the past years, distributed semantic representations have proved to be effective and
flexible keepers of prior knowledge to be integrated into downstream applications. This …