3 accepted papers
Text embeddings are typically evaluated on a narrow set of tasks, limited in terms of languages, domains, and task types. To circumvent this limitation and to provide a more comprehensive evaluation, we introduce the Massive Multilingual Text Embedding Benchmark (MMTEB) -- a large-scale community-dr…
Topic models are useful tools for discovering latent semantic structures in large textual corpora. Recent efforts have been oriented at incorporating contextual representations in topic modeling and have been shown to outperform classical topic models. These approaches are typically slow, volatile,…
The way we talk carries information about who we are. Demographics, personality, clinical conditions, political preferences influence what we speak about and how, suggesting that many individual attributes could be inferred from adequate encodings of linguistic behavior. Conversely, conditioning tex…