Analysis methods in neural language processing: A survey

Y Belinkov, J Glass - … of the Association for Computational Linguistics, 2019 - direct.mit.edu
The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

Multimodal intelligence: Representation learning, information fusion, and applications

C Zhang, Z Yang, X He, L Deng - IEEE Journal of Selected …, 2020 - ieeexplore.ieee.org
Deep learning methods haverevolutionized speech recognition, image recognition, and
natural language processing since 2010. Each of these tasks involves a single modality in …

Language is not all you need: Aligning perception with language models

S Huang, L Dong, W Wang, Y Hao… - Advances in …, 2023 - proceedings.neurips.cc
A big convergence of language, multimodal perception, action, and world modeling is a key
step toward artificial general intelligence. In this work, we introduce KOSMOS-1, a …

Experience grounds language

Y Bisk, A Holtzman, J Thomason, J Andreas… - arXiv preprint arXiv …, 2020 - arxiv.org
Language understanding research is held back by a failure to relate language to the
physical world it describes and to the social interactions it facilitates. Despite the incredible …

Multimodal machine learning: A survey and taxonomy

T Baltrušaitis, C Ahuja… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Our experience of the world is multimodal-we see objects, hear sounds, feel texture, smell
odors, and taste flavors. Modality refers to the way in which something happens or is …

Diachronic word embeddings reveal statistical laws of semantic change

WL Hamilton, J Leskovec, D Jurafsky - arXiv preprint arXiv:1605.09096, 2016 - arxiv.org
Understanding how words change their meanings over time is key to models of language
and cultural evolution, but historical data on meaning is scarce, making theories hard to …

Directional skip-gram: Explicitly distinguishing left and right context for word embeddings

Y Song, S Shi, J Li, H Zhang - … of the 2018 Conference of the …, 2018 - aclanthology.org
In this paper, we present directional skip-gram (DSG), a simple but effective enhancement of
the skip-gram model by explicitly distinguishing left and right context in word prediction. In …

Microsoft coco captions: Data collection and evaluation server

X Chen, H Fang, TY Lin, R Vedantam, S Gupta… - arXiv preprint arXiv …, 2015 - arxiv.org
In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When
completed, the dataset will contain over one and a half million captions describing over …

Improving distributional similarity with lessons learned from word embeddings

O Levy, Y Goldberg, I Dagan - Transactions of the association for …, 2015 - direct.mit.edu
Recent trends suggest that neural-network-inspired word embedding models outperform
traditional count-based distributional models on word similarity and analogy detection tasks …

Neural word embedding as implicit matrix factorization

O Levy, Y Goldberg - Advances in neural information …, 2014 - proceedings.neurips.cc
We analyze skip-gram with negative-sampling (SGNS), a word embedding method
introduced by Mikolov et al., and show that it is implicitly factorizing a word-context matrix …