A survey of the usages of deep learning for natural language processing

DW Otter, JR Medina, JK Kalita - IEEE transactions on neural …, 2020‏ - ieeexplore.ieee.org
Over the last several years, the field of natural language processing has been propelled
forward by an explosion in the use of deep learning models. This article provides a brief …

Word sense disambiguation: A survey

R Navigli - ACM computing surveys (CSUR), 2009‏ - dl.acm.org
Word sense disambiguation (WSD) is the ability to identify the meaning of words in context
in a computational manner. WSD is considered an AI-complete problem, that is, a task …

Analyzing leakage of personally identifiable information in language models

N Lukas, A Salem, R Sim, S Tople… - … IEEE Symposium on …, 2023‏ - ieeexplore.ieee.org
Language Models (LMs) have been shown to leak information about training data through
sentence-level membership inference and reconstruction attacks. Understanding the risk of …

Underspecification presents challenges for credibility in modern machine learning

A D'Amour, K Heller, D Moldovan, B Adlam… - Journal of Machine …, 2022‏ - jmlr.org
Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are
deployed in real-world domains. We identify underspecification in ML pipelines as a key …

Learning from disagreement: A survey

AN Uma, T Fornaciari, D Hovy, S Paun, B Plank… - Journal of Artificial …, 2021‏ - jair.org
Abstract Many tasks in Natural Language Processing (NLP) and Computer Vision (CV) offer
evidence that humans disagree, from objective tasks such as part-of-speech tagging to more …

FLAIR: An easy-to-use framework for state-of-the-art NLP

A Akbik, T Bergmann, D Blythe, K Rasul… - Proceedings of the …, 2019‏ - aclanthology.org
We present FLAIR, an NLP framework designed to facilitate training and distribution of state-
of-the-art sequence labeling, text classification and language models. The core idea of the …

PAQ: 65 million probably-asked questions and what you can do with them

P Lewis, Y Wu, L Liu, P Minervini, H Küttler… - Transactions of the …, 2021‏ - direct.mit.edu
Abstract Open-domain Question Answering models that directly leverage question-answer
(QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in …

ScispaCy: fast and robust models for biomedical natural language processing

M Neumann, D King, I Beltagy, W Ammar - arxiv preprint arxiv …, 2019‏ - arxiv.org
Despite recent advances in natural language processing, many statistical models for
processing text perform extremely poorly under domain shift. Processing biomedical and …

[PDF][PDF] Recent trends in word sense disambiguation: A survey

M Bevilacqua, T Pasini… - … Joint Conference on …, 2021‏ - researchportal.helsinki.fi
Abstract Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word
in context by identifying the most suitable meaning from a predefined sense inventory …

Lessons from archives: Strategies for collecting sociocultural data in machine learning

ES Jo, T Gebru - Proceedings of the 2020 conference on fairness …, 2020‏ - dl.acm.org
A growing body of work shows that many problems in fairness, accountability, transparency,
and ethics in machine learning systems are rooted in decisions surrounding the data …