mlsanityData to 7 Oct 2026

Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation

arXiv 1508.02096 ↗First posted 9 Aug 2015cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a single vector per character type and a fixed set of parameters for the compositional model. Despite the compactness of this model and, more importantly, the arbitrary nature of the form-function relationship in language, our "composed" word representations yield state-of-the-art results in language modeling and part-of-speech tagging. Benefits over traditional baselines are particularly pronounced in morphologically rich languages (e.g., Turkish).

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Aug 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 6; 2023: 4; 2024: 2; 2025: 0; 2026: 1.

28 papers.

Sort:

  1. 2021Between words and characters: A Brief History of Open-Vocabulary Modeling and Tokenization in NLPcited by 130
  2. 2021RobeCzech: Czech RoBERTa, a monolingual contextualized language representation modelcited by 33
  3. 2022Pretraining with Artificial Language: Studying Transferable Knowledge in Language Modelscited by 28
  4. 2021Dynamic Language Models for Continuously Evolving Contentcited by 27
  5. 2021Conformal prediction for text infilling and part-of-speech predictioncited by 22
  6. 2021To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLPcited by 12
  7. 2021Capitalization and Punctuation Restoration: a Surveycited by 12
  8. 2026The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?cited by 10
  9. 2021Recent Trends in Named Entity Recognition (NER)cited by 9
  10. 2022A Survey of Implicit Discourse Relation Recognitioncited by 8
  11. 2021Language Modelling via Learning to Rankcited by 7
  12. 2023What is the best recipe for character-level encoder-only modelling?cited by 6
16 more
  1. 2021Integrating Approaches to Word Representationcited by 4
  2. 2022Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American Englishcited by 3
  3. 2024Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fieldscited by 3
  4. 2021Evaluating Models of Robust Word Recognition with Serial Reproductioncited by 2
  5. 2021Locally-Contextual Nonlinear CRFs for Sequence Labelingcited by 2
  6. 2021A Survey On Neural Word Embeddingscited by 2
  7. 2023Data Augmentation for Neural NLPcited by 2
  8. 2021UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learningcited by 1
  9. 2021UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detectioncited by 1
  10. 2022The boundaries of meaning: a case study in neural machine translationcited by 1
  11. 2022Leveraging knowledge graphs to update scientific word embeddings using latent semantic imputationcited by 1
  12. 2023Language Cognition and Language Computation -- Human and Machine Language Understandingcited by 1
  13. 2021Learning grounded word meaning representations on similarity graphscited by 0
  14. 2022Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approachescited by 0
  15. 2023Semantic Tagging with LSTM-CRFcited by 0
  16. 2024GWPT: A Green Word-Embedding-based POS Taggercited by 0