From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains

Findings of the Association for Computational Linguistics: ACL 2022, pages 3354 - 3367 May 22-27, 2022 c⃝2022 Association for Computational Linguistics From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains Brodie Mather and Bonnie Dorr and Adam Dalton and William de Beaumont Institute for Human & Machine Cognition Owen Rambow Stony Brook University Sonja Schmer-Galunder Smart Information Flow Technologies Abstract We present a generalized paradigm for adap- tation of propositional analysis (predicate- argument pairs) to new tasks and domains. We leverage an analogy between stances (belief- driven sentiment) and concerns (topical issues with moral dimensions/endorsements) to pro- duce an explanatory representation. A key con- tribution is the combination of semi-automatic resource building for extraction of domain- dependent concern types (with 2-4 hours of human labor per domain) and an entirely au- tomatic procedure for extraction of domain- independent moral dimensions and endorse- ment values. Prudent (automatic) selection of terms from propositional structures for lexical expansion (via semantic similarity) produces new moral dimension lexicons at three levels of granularity beyond a strong baseline lexicon. We develop a ground truth (GT) based on expert annotators and compare our concern detection output to GT, to yield 231% improvement in re- call over baseline, with only a 10% loss in preci- sion. F1 yields 66% improvement over baseline and 97.8% of human performance. Our lexi- cally based approach yields large savings over approaches that employ costly human labor and model building. We provide to the community a newly expanded moral dimension/value lexi- con, annotation guidelines, and GT. 1 Introduction This paper presents a generalized paradigm for adaptation of tasks involving predicate-argument pairs, i.e., combinations of actions and their par- ticipants, to new tasks and domains. Predicate- argument analysis has been a longstanding area of research for many tasks: event detection (Du and Cardie, 2020; Zhang et al., 2020), opinion extrac- tion (Yang and Cardie, 2013), textual entailment (Stern and Dagan, 2014), and coreference (Shibata and Kurohashi, 2018). We refer to the induction of such representations as propositional analysis. We induce a proposition PREDICATE(x1,x2,...) to represent sentences such as John wears a mask: wear(John,mask). We pivot off this explanatory representation to answer questions such as What is John’s stance towards mask wearing? or What concerns does John have about mask wearing? Stance detection has recently (re-)emerged as a very active research area, yet many approaches gen- erally equate stance to raw (bag-of-word) sentiment and often employ machine-learning based models requiring large amounts of (labeled or unlabeled) training data. Within such approaches, the notion of stance varies, but generally falls into one of a handful of “sentiment-like” categories for stance holder X regarding topic Y, i.e., X agrees/disagrees with Y (Umer et al., 2020), X favors/disfavors Y (Krejzl et al., 2017), X is pro/anti Y (Samih and Darwish, 2021), X has a positive/negative opinion about Y (AlDayel and Magdy, 2021), or X is in favor/against/neither Y (Küçük and Can, 2020). We adopt the stance definition of Mather et al. (2021), originally formulated …

Content truncated to 500 words