Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates
This work addresses a specific linguistic challenge in political discourse analysis, but it is incremental as it builds on existing pronoun resolution methods applied to a new domain.
The paper tackles the problem of disambiguating first-person plural pronouns in political speeches by developing an annotation schema and creating an annotated corpus from German Bundestag debates, with preliminary results reported for automated resolution using data augmentation.
This paper investigates the use of first person plural pronouns as a rhetorical device in political speeches. We present an annotation schema for disambiguating pronoun references and use our schema to create an annotated corpus of debates from the German Bundestag. We then use our corpus to learn to automatically resolve pronoun referents in parliamentary debates. We explore the use of data augmentation with weak supervision to further expand our corpus and report preliminary results.