A look at prompt-tuning and its impact on attention in language models.
― 6 min read
Computer Science - Computation and Language
RSSNew dataset highlights AI performance in creative tasks with distractions.
― 5 min read
Exploring methods for detecting hate speech in audio broadcasts of under-resourced languages.
― 4 min read
A new method enhances labeling accuracy for social science studies using LLMs.
― 5 min read
Selecting relevant examples boosts language model performance across tasks and languages.
― 5 min read
A study on using machine learning to predict gender in Swedish nouns.
― 6 min read
A new method to improve language models while preserving knowledge.
― 7 min read
New methods in AMR parsing enhance language comprehension and graph accuracy.
― 6 min read
A model generates keyphrases without the need for labeled data.
― 6 min read
A new dataset and model improve remote sensing image analysis.
― 5 min read
A fresh approach to assess the quality of generated text in large language models.
― 6 min read
Introducing NADO as an effective method for controlled text generation.
― 6 min read
AgriBERT uses NLP to improve food analysis in agriculture.
― 6 min read
Contextual biasing enhances ASR systems, improving accuracy in specialized tasks.
― 5 min read
Essential steps for effective AI research paper submission.
― 4 min read
A semi-automated method for better machine translation data creation.
― 5 min read
A tool that helps researchers efficiently summarize academic papers.
― 5 min read
EvolveMT enhances machine translation by continuously adapting and selecting the best output.
― 5 min read
This system simplifies data management for diverse users with varying skills.
― 6 min read
phi-1 shows strong performance in coding tasks with quality training data.
― 4 min read
New method improves image captions with more detail and diversity.
― 7 min read
A study examines how sociodemographic factors influence labeling behavior in natural language processing.
― 6 min read
Exploring new methods for effective text summarization in Slovene language.
― 5 min read
A novel dataset improves understanding of structured data through natural language descriptions.
― 6 min read
A new task designed to help language models better generalize information.
― 6 min read
New dataset improves language models' understanding across languages.
― 7 min read
A study on the reasoning behind document-level relation extraction model predictions.
― 5 min read
A new method enhances text-to-speech quality and emotional expression.
― 5 min read
Boosting language models' performance for languages with limited data.
― 5 min read
A method to detect systematic failures in multimodal models before real-world use.
― 5 min read
New benchmark assesses language models' understanding of human thoughts and feelings.
― 6 min read
Techniques to reduce model size while preserving performance are emerging.
― 4 min read
This project uses NLP to assess the quality of classroom discussions automatically.
― 4 min read
A new framework simplifies data retrieval for language researchers on TalkBank.
― 5 min read
AI models struggle to assist researchers with paper revisions based on reviewer feedback.
― 7 min read
Examining how AI handles human-like reasoning and its biases.
― 5 min read
A closer look at the problems with the RVL-CDIP benchmark dataset.
― 5 min read
Research investigates stacked layers in language models for enhanced performance.
― 7 min read
VisoGender dataset examines gender bias in image and text models in professional contexts.
― 5 min read
A new model reduces size while improving multilingual speech recognition.
― 6 min read