Recent advances in processing negation

Abstract

Negation is a complex linguistic phenomenon present in all human languages. It can be seen as an operator that transforms an expression into another expression whose meaning is in some way opposed to the original expression. In this article, we survey previous work on negation with an emphasis on computational approaches. We start defining negation and two important concepts: scope and focus of negation. Then, we survey work in natural language processing that considers negation primarily as a means to improve the results in some task. We also provide information about corpora containing negation annotations in English and other languages, which usually include a combination of annotations of negation cues, scopes, foci, and negated events. We continue the survey with a description of automated approaches to process negation, ranging from early rule-based systems to systems built with traditional machine learning and neural networks. Finally, we conclude with some reflections on current progress and future directions.

Erforschung von Bewegungsbeschreibungen durch geovisuelle Analytik

“… 2009 ). Third, our negation detection techniques would also require adaption to support other languages (Morante and Blanco 2021 ). These changes are possible but need significant work as existing research is less robust than the equivalent in English.…”

“…Second, our geoparsing methods to extract place mentions and geocode them to their correct location on Earth would need to be adapted (Mandl et al, 2009). Third, our negation detection techniques would also require adaption to support other languages (Morante and Blanco, 2021). These changes are possible but need significant work as existing research is less robust than the equivalent in English.…”

Developmental Negation Processing in Transformer Language Models

“…Negation is an important construct in language for reasoning over the truth of propositions (Heinemann, 2015), garnering interest from philosophy (Horn, 1989), psycholinguistics (Zwaan, 2012), and natural language processing (NLP) (Morante and Blanco, 2020). While transformer language models (TLMs) (Vaswani et al, 2017) have achieved impressive performance across many NLP tasks, a great deal of recent work has found that they do not process negation well, and often make predictions that would be trivially false in the eyes of a human (Rogers et al, 2020;Ettinger, 2020;Laverghetta Jr. et al, 2021).…”

Negation-Instance Based Evaluation of End-to-End Negation Resolution

“…Negation is a complex semantic phenomenon in natural language that "transforms an expression into another expression whose meaning is in some way opposed to the original" (Morante and Blanco, 2021). It occurs frequently, with the proportion of sentences with negation in English corpora ranging between 9 and 32% (Jiménez-Zafra et al, 2020b).…”

“…Negation Resolution (Morante and Blanco, 2021) refers to the task of automatically retrieving the elements of a sentence that are affected by the negation introduced by a cue. The cue's scope is "the part of the meaning that is negated" (Huddleston and Pullum, 2002).…”