Imagen de Portada

OOVs in the Spotlight: How to Inflect them?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sourada, Tomáš, Straková, Jana, Rosa, Rudolf
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Corpus Frequencies in Morphological Inflection: Do They Matter?
por: Sourada, Tomáš, et al.
Publicado: (2025)

Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
por: Sourada, Tomáš, et al.
Publicado: (2025)

Open-Source Web Service with Morphological Dictionary-Supplemented Deep Learning for Morphosyntactic Analysis of Czech
por: Straka, Milan, et al.
Publicado: (2024)

NameTag 3: A Tool and a Service for Multilingual/Multitagset NER
por: Straková, Jana, et al.
Publicado: (2025)

ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution
por: Straka, Milan, et al.
Publicado: (2022)

ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
por: Straka, Milan, et al.
Publicado: (2024)

Refining Czech GEC: Insights from a Multi-Experiment Approach
por: Pechman, Petr, et al.
Publicado: (2025)

Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation
por: Singh, Pushpdeep
Publicado: (2023)

CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking
por: Vonášek, Josef, et al.
Publicado: (2024)

GPT Czech Poet: Generation of Czech Poetic Strophes with Language Models
por: Chudoba, Michal, et al.
Publicado: (2024)

Inconsistent dialogue responses and how to recover from them
por: Zhang, Mian, et al.
Publicado: (2024)

Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents
por: Mullick, Ankan, et al.
Publicado: (2025)

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
por: Yao, Jiayu, et al.
Publicado: (2025)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
por: Hines, Keegan, et al.
Publicado: (2024)

Historical/temporal necessities/possibilities, and a logical theory of them in branching time
por: Ju, Fengkui, et al.
Publicado: (2022)

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
por: Li, Wenhao, et al.
Publicado: (2025)

Spotlights and Blindspots: Evaluating Machine-Generated Text Detection
por: Stowe, Kevin, et al.
Publicado: (2026)

One ruler to measure them all: Benchmarking multilingual long-context language models
por: Kim, Yekyung, et al.
Publicado: (2025)

ChatGPT-generated texts show authorship traits that identify them as non-human
por: Dentella, Vittoria, et al.
Publicado: (2025)

One Joke to Rule them All? On the (Im)possibility of Generalizing Humor
por: Turgeman, Mor, et al.
Publicado: (2025)

Training language models to be warm and empathetic makes them less reliable and more sycophantic
por: Ibrahim, Lujain, et al.
Publicado: (2025)

States of LLM-generated Texts and Phase Transitions between them
por: Mikhaylovskiy, Nikolay
Publicado: (2025)

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
por: Agarwal, Utkarsh, et al.
Publicado: (2024)

Strong hallucinations from negation and how to fix them
por: Asher, Nicholas, et al.
Publicado: (2024)

Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work
por: Abilov, Anton, et al.
Publicado: (2025)

TRIM: Token Reduction and Inference Modeling for Cost-Effective Language Generation
por: Ruiz, Alfredo Garrachón, et al.
Publicado: (2024)

What are human values, and how do we align AI to them?
por: Klingefjord, Oliver, et al.
Publicado: (2024)

Why Misinformation is Created? Detecting them by Integrating Intent Features
por: Wang, Bing, et al.
Publicado: (2024)

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
por: Tan, Daniel, et al.
Publicado: (2025)

LLMs cannot find reasoning errors, but can correct them given the error location
por: Tyen, Gladys, et al.
Publicado: (2023)

Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student
por: Jana, Soumyadeep, et al.
Publicado: (2025)

LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma
por: Juroš, Jana, et al.
Publicado: (2024)

CodeSCM: Causal Analysis for Multi-Modal Code Generation
por: Gupta, Mukur, et al.
Publicado: (2025)

On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data
por: Ruiz, Alfredo Garrachón, et al.
Publicado: (2025)

CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
por: Nikeghbal, Nafiseh, et al.
Publicado: (2025)

Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection
por: Jana, Soumyadeep, et al.
Publicado: (2025)

Adapter-state Sharing CLIP for Parameter-efficient Multimodal Sarcasm Detection
por: Jana, Soumyadeep, et al.
Publicado: (2025)

Dual Modality-Aware Gated Prompt Tuning for Few-Shot Multimodal Sarcasm Detection
por: Jana, Soumyadeep, et al.
Publicado: (2025)

Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles
por: Lazzaroni, Ruggero Marino, et al.
Publicado: (2026)

Sign Language Sense Disambiguation
por: Grimm, Jana, et al.
Publicado: (2024)