natural-language-processing-8

Diachronic Word Embeddings

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in diachronic-word-embeddings-8

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find diachronic-word-embeddings-8 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change

J. Leskovec, Dan Jurafsky, William L. Hamilton•Sun May 29 2016

A robust methodology for quantifying semantic change is developed by evaluating word embeddings against known historical changes and it is revealed that words that are more polysemous have higher rates of semantic change.

970

Content

0

Paper Graph

Tracing Antisemitic Language Through Diachronic Embedding Projections: France 1789-1914

Rocco Tripodi, M. Warglien, S. Sullam, Deborah Paci•Mon Jun 03 2019

A large corpus of French books and periodicals issues that contain a keyword related to Jews are constructed and a diachronic word embedding over the 1789-1914 period is performed to track the evolution of antisemitic bias in the religious, economic, socio-politic, racial, ethic and conspiratorial domains.

21 0

Paper Graph

Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings

Terrence Szymanski•Thu Aug 03 2017

It is shown that temporal word analogies can effectively be modeled with diachronic word embeddings, provided that the independent embedding spaces from each time period are appropriately transformed into a common vector space.

65 0

Paper Graph

Training Temporal Word Embeddings with a Compass

Federico Bianchi, M. Palmonari, Valerio Di Carlo•Tue Jun 04 2019

A new heuristic to train temporal word embeddings based on the Word2vec model consists in using atemporal vectors as a reference, i.e., as a compass, when training the representations specific to a given time interval.

71 0

Paper Graph

Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models

Michael J. Paul, Xiaolei Huang•Sun Jun 30 2019

Two complementary ways to adapt classifiers to shifts across time are described, and it is shown that diachronic word embeddings, which were originally developed to study language change, can also improve document classification.

39 0

Paper Graph

Contextualized Diachronic Word Representations

Djamé Seddah, Ganesh Jawahar•Thu Aug 01 2019

A novel attentional model is devised, based on Bernoulli word embeddings, that is conditioned on contextual extra-linguistic features such as network, spatial and socio-economic variables, which are associated with Twitter users, as well as topic-based features that provide an inductive bias that helps the model to overcome the narrow time-span regime problem.

10 0

Paper Graph

Follow the leader: Documents on the leading edge of semantic change get more citations

Jacob Eisenstein, Kristina Lerman, Sandeep Soni•Sun Sep 08 2019

This work proposes a novel method to quantify the degree of semantic progressiveness in each word usage, and shows how these usages can be aggregated to obtain scores for each document.

14 0

Paper Graph

Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers

Jacob Eisenstein, Sandeep Soni, Lauren F. Klein•Sun Jan 17 2021

It is found that two newspapers edited by women led a large number of semantic changes in the corpus, lending additional credence to the argument that a multiracial coalition of women led the abolitionist movement in terms of both thought and action.

22 0

Paper Graph

Words with Consistent Diachronic Usage Patterns are Learned Earlier: A Computational Analysis Using Temporally Aligned Word Embeddings

M. Marelli, Federico Bianchi, Giovanni Cassani•Wed Mar 31 2021

A unique and reliable relation between measures of language change and age of acquisition (AoA) is shown while controlling for frequency, contextual diversity, concreteness, length, dominant part of speech, orthographic neighborhood density, and diachronic frequency variation.

10 0

Paper Graph

DUKweb: Diachronic word representations from the UK Web Archive corpus

Adam Tsakalidis, Pierpaolo Basile, Marya Bazzi, Mihai Cucuringu, Barbara McGillivray•Thu Jul 01 2021

DUKweb, a set of large-scale resources designed for the diachronic analysis of contemporary English, is presented and the reuse potential of DUKweb and its quality standards are shown via a case study on word meaning change detection.

4 0

Paper Graph

Adding a benchmark result helps the community track progress.