Domain-specific word embeddings for patent classification

By Julian Risch, Ralf Krestel. 2019

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Hayden S. Helm
2. Carey E. Priebe
3. Brandon Duderstadt
4. Youngser Park

In Representation & Self-Supervised Learning

1. Hayden S. Helm
2. Carey E. Priebe
3. Youngser Park
4. Brandon Duderstadt

Citations in the corpus

• Tracking the perspectives of interacting language models (2024, methodology): “…for comparing models, general-purpose embedding functions (Reimers and Gurevych, 2019; Nussbaum et al., 2024) should be sufficient for capturing the majority of signal, and domain-specific embedding functions (Risch and Krestel, 2019) should be used when the difference in models is highly nuanced.”