23 citations · 31 across the 4 of their papers we have counts for
7 papers · 1 filter
ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering
Alexander Hoyle, Lorena Calvo-Bartolomé, Jordan Boyd-Graber +1
Topic model and document-clustering evaluations either use automated metrics that align poorly with human preferences or require expert labels that are intractable to scale. We des…
Are Neural Topic Models Broken?
Alexander Hoyle, Pranav Goel, Rupak Sarkar +1
Recently, the relationship between automated and human evaluation of topic models has been called into question. Method developers have staked the efficacy of new topic model varia…
Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence
Alexander Hoyle, Pranav Goel, Denis Peskov +3
Topic model evaluation, like evaluation of other unsupervised methods, can be contentious. However, the field has coalesced around automated estimates of topic coherence, which rel…
Promoting Graph Awareness in Linearized Graph-to-Text Generation
Alexander Hoyle, Ana Marasović, Noah Smith
Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graph-encoding neural networks. However, recent ap…
Improving Neural Topic Models using Knowledge Distillation
Alexander Hoyle, Pranav Goel, Philip Resnik
Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of…
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling
Alexander Hoyle, Wolf-Sonkin, Hanna Wallach +2
Studying the ways in which language is gendered has long been an area of interest in sociolinguistics. Studies have explored, for example, the speech of male and female characters…