Copertina

Semantics or spelling? Probing contextual word embeddings with orthographic noise

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Matthews, Jacob A., Starr, John R., van Schijndel, Marten
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Code-switching in text and speech challenges information-theoretic speaker design
di: Bhattacharya, Debasmita, et al.
Pubblicazione: (2024)

Does Dependency Locality Predict Non-canonical Word Order in Hindi?
di: Ranjan, Sidharth, et al.
Pubblicazione: (2024)

Losing Phonotactic Distinctions in Context
di: John R. Starr, et al.
Pubblicazione: (2025)

Extracting domain-specific terms using contextual word embeddings
di: Repar, Andraž, et al.
Pubblicazione: (2025)

A graph-based analysis of semantic types and coercion in contextualized word embeddings
di: Chen, Long, et al.
Pubblicazione: (2026)

Neural spell-checker: Beyond words with synthetic data generation
di: Klemen, Matej, et al.
Pubblicazione: (2024)

A symbolic Perl algorithm for the unification of Nahuatl word spellings
di: Guzmán-Landa, Juan-José, et al.
Pubblicazione: (2025)

Semantic Properties of cosine based bias scores for word embeddings
di: Schröder, Sarah, et al.
Pubblicazione: (2024)

Effect of dimensionality change on the bias of word embeddings
di: Rai, Rohit Raj, et al.
Pubblicazione: (2023)

Does mBERT understand Romansh? Evaluating word embeddings using word alignment
di: Dolev, Eyal Liron
Pubblicazione: (2023)

Predicting drug-gene relations via analogy tasks with word embeddings
di: Yamagiwa, Hiroaki, et al.
Pubblicazione: (2024)

The SAME score: Improved cosine based bias score for word embeddings
di: Schröder, Sarah, et al.
Pubblicazione: (2022)

A computational system to handle the orthographic layer of tajwid in contemporary Quranic Orthography
di: Martínez, Alicia González
Pubblicazione: (2025)

Explaining word embeddings with perfect fidelity: Case study in research impact prediction
di: Dvorackova, Lucie, et al.
Pubblicazione: (2024)

Multilingual acoustic word embeddings for zero-resource languages
di: Jacobs, Christiaan
Pubblicazione: (2024)

From communities to interpretable network and word embedding: an unified approach
di: Prouteau, Thibault, et al.
Pubblicazione: (2024)

A nuclear families word list for French
di: Thomas Cobb, et al.
Pubblicazione: (2026)

Med-gte-hybrid: A contextual embedding transformer model for extracting actionable information from clinical texts
di: Kumar, Aditya, et al.
Pubblicazione: (2025)

Are we describing the same sound? An analysis of word embedding spaces of expressive piano performance
di: Peter, Silvan David, et al.
Pubblicazione: (2023)

Probing BERT for German Compound Semantics
di: Miletić, Filip, et al.
Pubblicazione: (2025)

Improving the quality of Persian clinical text with a novel spelling correction system
di: Dashti, Seyed Mohammad Sadegh, et al.
Pubblicazione: (2024)

Vocabulary embeddings organize linguistic structure early in language model training
di: Papadimitriou, Isabel, et al.
Pubblicazione: (2025)

What is a word?
di: Murphy, Elliot
Pubblicazione: (2024)

Introduction of a novel word embedding approach based on technology labels extracted from patent data
di: Standke, Mark, et al.
Pubblicazione: (2021)

A new kid on the block: Distributional semantics predicts the word-specific tone signatures of monosyllabic words in conversational Taiwan Mandarin
di: Jin, Xiaoyun, et al.
Pubblicazione: (2025)

Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languages
di: Elsner, Micha, et al.
Pubblicazione: (2025)

Can LLMs Extract Frame-Semantic Arguments?
di: Devasier, Jacob, et al.
Pubblicazione: (2025)

Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
di: Lo, Chun Hei, et al.
Pubblicazione: (2023)

Scaling few-shot spoken word classification with generative meta-continual learning
di: Beyers, Louise, et al.
Pubblicazione: (2026)

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
di: Diera, Andor, et al.
Pubblicazione: (2026)

Failure of contextual invariance in large language models
di: Kumar, Sagar, et al.
Pubblicazione: (2026)

How much do contextualized representations encode long-range context?
di: Sun, Simeng, et al.
Pubblicazione: (2024)

When does word order matter and when doesn't it?
di: Chen, Xuanda, et al.
Pubblicazione: (2024)

Automatic Real-word Error Correction in Persian Text
di: Dashti, Seyed Mohammad Sadegh, et al.
Pubblicazione: (2024)

Meaning at the Planck scale? Contextualized word embeddings for doing history, philosophy, and sociology of science
di: Simons, Arno
Pubblicazione: (2024)

Subword models struggle with word learning, but surprisal hides it
di: Bunzeck, Bastian, et al.
Pubblicazione: (2025)

Does language matter for spoken word classification? A multilingual generative meta-learning approach
di: Ziki, Batsirayi Mupamhi, et al.
Pubblicazione: (2026)

Task-Oriented Automatic Fact-Checking with Frame-Semantics
di: Devasier, Jacob, et al.
Pubblicazione: (2025)

Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics
di: Lin, Fangru, et al.
Pubblicazione: (2024)

Monitoring Latent World States in Language Models with Propositional Probes
di: Feng, Jiahai, et al.
Pubblicazione: (2024)