Natural language traffic in social media (blogs, microblogs, talkbacks) enjoys vast monitoring and analysis efforts. However, the question whether computer systems can generate such content in order to effectively interact with humans has been only sparsely attended to. This paper presents an architecture for generating subjective responses to opinionated articles based on users' agenda, documents' topics, sentiments and a knowledge graph. We present an empirical evaluation method for quantifying the humanlikeness and relevance of the generated responses. We show that responses generated using world knowledge in the input are regarded as more human-like than those that rely on topic, sentiment and agenda only, whereas the use of world knowledge does not affect perceived relevance.
Opinionated natural language generation (ONLG) is a new, challenging, NLG task in which we aim to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users' agendas, based on automatically acquired wide-coverage generative grammars. We compare three types of grammatical representations that we design for ONLG. The grammars interleave different layers of linguistic information, and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima'an, 2008) inspired grammar gets better language model scores than lexicalized grammarsà la Collins (2003), and that the latter gets better humanevaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.