A Unified Feature Representation for Lexical Connotations
| Autor: | Kathleen R. McKeown, Emily Allaway |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer science media_common.quotation_subject Representation (arts) Space (commercial competition) Linguistics Task (project management) Feature (linguistics) Noun Connotation (semiotics) Embedding Ideology Computation and Language (cs.CL) media_common |
| Zdroj: | EACL |
| DOI: | 10.48550/arxiv.2006.00635 |
| Popis: | Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant labeling to create a new lexical resource representing connotation aspects for nouns and adjectives. Our analysis shows that it aligns well with human judgments. Additionally, we present a method for creating lexical representations that captures connotations within the embedding space and show that using the embeddings provides a statistically significant improvement on the task of stance detection when data is limited. Comment: EACL 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|