A survey of the usages of deep learning for natural language processing
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 …
forward by an explosion in the use of deep learning models. This article provides a brief …
Word sense disambiguation: A survey
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 …
in a computational manner. WSD is considered an AI-complete problem, that is, a task …
Analyzing leakage of personally identifiable information in language models
Language Models (LMs) have been shown to leak information about training data through
sentence-level membership inference and reconstruction attacks. Understanding the risk of …
sentence-level membership inference and reconstruction attacks. Understanding the risk of …
Underspecification presents challenges for credibility in modern machine learning
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 …
deployed in real-world domains. We identify underspecification in ML pipelines as a key …
Learning from disagreement: A survey
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 …
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
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 …
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
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 …
(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
Despite recent advances in natural language processing, many statistical models for
processing text perform extremely poorly under domain shift. Processing biomedical and …
processing text perform extremely poorly under domain shift. Processing biomedical and …
[PDF][PDF] Recent trends in word sense disambiguation: A survey
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 …
in context by identifying the most suitable meaning from a predefined sense inventory …
Lessons from archives: Strategies for collecting sociocultural data in machine learning
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 …
and ethics in machine learning systems are rooted in decisions surrounding the data …