Incorporating Demographic Embeddings Into Language Understanding
Citations Over TimeTop 1% of 2019 papers
Abstract
Meaning depends on context. This applies in obvious cases like deictics or sarcasm as well as more subtle situations like framing or persuasion. One key aspect of this is the identity of the participants in an interaction. Our interpretation of an utterance shifts based on a variety of factors, including personal history, background knowledge, and our relationship to the source. While obviously an incomplete model of individual differences, demographic factors provide a useful starting point and allow us to capture some of this variance. However, the relevance of specific demographic factors varies between situations-where age might be the key factor in one context, ideology might dominate in another. To address this challenge, we introduce a method for combining demographics and context into situated demographic embeddings-mapping representations into a continuous geometric space appropriate for the given domain, showing the resulting representations to be functional and interpretable. We further demonstrate how to make use of related external data so as to apply this approach in low-resource situations. Finally, we show how these representations can be incorporated into improve modeling of real-world natural language understanding tasks, improving model performance and helping with issues of data sparsity.
Related Papers
- → Personality correlates and utilitarian judgments in the everyday context: Psychopathic traits and differential effects of empathy, social dominance orientation, and dehumanization beliefs(2019)19 cited
- → Amount of altruistic punishment accounts for subsequent emotional gratification in participants with primary psychopathy(2011)14 cited
- → The Information Used to Judge Supportiveness Depends on Whether the Judgment Reflects the Personality of Perceivers, the Objective Characteristics of Targets, or their Unique Relationships(2004)15 cited
- → The Mental Representations Of High And Low Entitativity Groups(2003)12 cited
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)