Who Cited It

Enriching Word Vectors with Subword Information

2017 · Transactions of the Association for Computational Linguistics · 9,900 citations · 7 from inside this corpus

Piotr Bojanowski, Édouard Grave, Armand Joulin, Tomáš Mikolov

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.

Enriching Word Vectors with Subword Information (2017)Enriching Word Vectors with S…Distributed Representations of Words and Phrases and their Compositionality (2013)Distributed Representations o…Indexing by latent semantic analysis (1990)Indexing by latent semantic a…Efficient Estimation of Word Representations in Vector Space (2013)Efficient Estimation of Word …[No title in the source record — Edinburgh Research Explorer (University of Edinburgh)][No title in the source recor…A unified architecture for natural language processing (2008)A unified architecture for na…From Frequency to Meaning: Vector Space Models of Semantics (2010)From Frequency to Meaning: Ve…Producing high-dimensional semantic spaces from lexical co-occurrence (1996)Producing high-dimensional se…Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018)Recent Trends in Deep Learnin…Deep Contextualized Word Representations (2018)Deep Contextualized Word Repr…Publicly Available Clinical (2019)Publicly Available ClinicalCross-lingual Language Model Pretraining (2019)Cross-lingual Language Model …Pre-trained models for natural language processing: A survey (2020)Pre-trained models for natura…A survey on sentiment analysis methods, applications, and challenges (2022)A survey on sentiment analysi…Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020)Stanza: A Python Natural Lang…
14 of 14 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.
this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

What this paper cites, inside the corpus

PaperYearCited
Distributed Representations of Words and Phrases and their Compositionality201318,054
Indexing by latent semantic analysis199012,850
Efficient Estimation of Word Representations in Vector Space201311,714
[No title in the source record — Edinburgh Research Explorer (University of Edinburgh)]7,291
A unified architecture for natural language processing20085,207
From Frequency to Meaning: Vector Space Models of Semantics20102,902
Producing high-dimensional semantic spaces from lexical co-occurrence19961,849

What cites it, inside the corpus

PaperYearCited
Recent Trends in Deep Learning Based Natural Language Processing [Review Article]20182,907
Deep Contextualized Word Representations20181,783
Publicly Available Clinical20191,743
Cross-lingual Language Model Pretraining20191,624
Pre-trained models for natural language processing: A survey20201,521
A survey on sentiment analysis methods, applications, and challenges20221,493
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages20201,463

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Topic ModelingComputer Science
Natural Language Processing TechniquesComputer Science
Text Readability and SimplificationComputer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

  • supports4 author record(s) attached.
  • supports47 reference(s) recorded.
  • neutralThe DOI carries no year to check against.
  • supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:40+00:00.

sha256 7e3d99a592f7f61f…