A distributional similarity approach to the detection of semantic change in the Google Books Ngram corpus.

By Kristina Gulordava, Marco Baroni. 2011

220 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change (2016, methodology): “methods (Sagi et al., 2011; Wijaya and Yeniterzi, 2011; Gulordava and Baroni, 2011; Jatowt and Duh, 2014; Kulkarni et al., 2014; Xu and Kemp, 2015), as well as recent work on detecting the emergence of novel word senses (Lau et al.”
Dynamic Language Models for Continuously Evolving Content (2021, background): “The more recent works aim to automatically detect word semantic changes where the semantics of words are in distributional representation (eg, word-context matrix) [9, 13, 36] or, recently more popular, distributed representation (ie, word embeddings) [14].”
An automatic approach to identify word sense changes in text media across timescales (2015, methodology): “Gulordava and Baroni (2011) used two diﬀerent time periods in the Google n-grams corpus and presented an approach to detect semantic change based on distributional similarity between word vectors.”
Harm inflation: Making sense of concept creep (2020, methodology): “For example, Gulordava and Baroni (2011) used an n-gram corpus to compare language usage in the 1960s and 1990s by applying a distributional semantics approach that estimates the similarity between word meanings as a similarity of contexts in which they are used.”
Word Sense Induction for Novel Sense Detection (2012, background): “For example, Sagi et al. (2009), Cook and Stevenson (2010), and Gulordava and Baroni (2011) propose type-based models of semantic change.”
Diachronic word embeddings and semantic shifts: a survey (2018, methodology): “Mihalcea and Nastase (2012) used this dataset to detect differences in word usage and meaning across 50-years time spans, while Gulordava and Baroni (2011) compared word meanings in the 1960s and in the 1990s, achieving good correlation with human judgments.”
Statistically Significant Detection of Linguistic Change (2014, background): “ant four areas of work: linguistic shift, word embeddings, change point detection, and Internet linguistics. 7.1 Linguistic Shift There has been a surge in the work about language evolution over time [11, 17, 18, 21, 27, 41]. Michel et al. [27] detected important political events by analyzing freque”
Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change (2019, unknown): “…Computational approaches to semantic change detection can be divided in different families: count-based semantic spaces (Sagi et al., 2009; Gulordava and Baroni, 2011) and more recently based on neural embed-dings (Kim et al., 2014; Basile et al., 2016; Kulka-rni et al., 2015; Hamilton et…”
A Bayesian Model of Diachronic Meaning Change (2016, methodology): “Instead of relying on a few hand-selected target words, we use larger sets sampled from our learning corpus or found to undergo meaning change in a judgment elicitation study (Gulordava and Baroni, 2011).”
Novel Word-sense Identification (2014, background): “Gulordava and Baroni (2011) identify diachronic sense change in an n -gram database, but using a model that is not restricted to any particular type of semantic change.”
A Computational Evaluation of Two Laws of Semantic Change (2015, background): “A second group of researchers has explored computational methods for detecting semantic change in large corpora (Sagi, Kaufmann, & Clark, 2011; Gulordava & Baroni, 2011).”
Temporal Analysis of Language through Neural Language Models (2014, background): “Gulordava and Baroni (2011) use co-occurrence counts of words from 1960s and 1990s to detect semantic change.”