State-of-the-art NLP benchmarks require interpretation of natural language that specifies conditions, procedures, and exceptions, often relying on implicit assumptions and external knowledge. Constructing complete semantic…
Machine learning
13 Articles
13
Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evaluation methods, largely based on…
Large language models (LLMs) such as ChatGPT are increasingly used in the cultural heritage domain for tasks like metadata creation, semantic enrichment, and artwork captioning….
Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping to gradual loss of…
Heading Large language models (LLMs) have achieved remarkable progress in naturallanguage generation, yet they continue to display puzzling behaviors—such asrepetition and incoherence—even when exhibiting low…
This paper proposes formulating Zipf’s meaning-frequency law, the power law between word frequency and the number of meanings, as a relationship between word frequency and…
Clustering is a fundamental technique in machine learning and data mining, offering a powerful lens to understand self-organizing patterns in the real world. At its…
This paper shows a novel machine learning model for realized volatility (RV) prediction using a normalizing flow, an invertible neural network. Since RV is known to…
We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document x∈X is indexed by t∈T, and a neural autoregressive model is…
Templates are multi-word expressions with slots, such as “Starting at _ on _ ” or “regard _ as _”, that appear frequently in text and…