2022/05/16 by Mark Anderson, Anderson, Mark, José Camacho-Collados +1
Biochemistry, Genetics and Molecular Biology · Computer Science · Psychology · #Artificial Intelligence (cs.AI) #Artificial intelligence #Biomedical Text Mining and Ontologies #Cognitive psychology #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Data science #FOS: Computer and information sciences #Focus (optics) #Geography #Interpretability #Linguistics #Natural Language Processing Techniques #Natural language #Natural language processing #Psychology #Reciprocal #Topic Modeling #Trait
paper · pdf · doi:10.48550/arxiv.2205.07603
openalex publication_date 2022/05/16 · openalex created_date 2022/05/22 · openalex updated_date 2026/08/05
The increase in performance in NLP due to the prevalence of distributional models and deep learning has brought with it a reciprocal decrease in interpretability. This has spurred a focus on what neural networks learn about natural language with less of a focus on how. Some work has focused on the data used to develop data-driven models, but typically this line of work aims to highlight issues with the data, e.g. highlighting and offsetting harmful biases. This work contributes to the relatively untrodden path of what is required in data for models to capture meaningful representations of natural language. This entails evaluating how well English and Spanish semantic spaces capture a particular type of relational knowledge, namely the traits associated with concepts (e.g. bananas-yellow), and exploring the role of co-occurrences in this context.