Inducing Event Types and Roles in Reverse: Using Function to Discover Theme

Abstract

With growing interest in automated event extraction, there is an increasing need to overcome the labor costs of hand-written event templates, entity lists, and annotated corpora. In the last few years, more inductive approaches have emerged, seeking to discover unknown event types and roles in raw text. The main recent efforts use probabilistic generative models, as in topic modeling, which are formally concise but do not always yield stable or easily interpretable results. We argue that event schema induction can benefit from greater structure in the process and in linguistic features that distinguish words' functions and themes. To maximize our use of limited data, we reverse the typical schema induction steps and introduce new similarity measures, building an intuitive process for inducing the structure of unknown events.

Open Domain Event Extraction Using Neural Latent Variable Models

“…Schemas Matching. We follow previous work and use precision, recall and F1-score as the metrics for schema matching (Chambers and Jurafsky, 2011;Chambers, 2013;Cheung et al, 2013;Nguyen et al, 2015;Sha et al, 2016;Ahn, 2017). The matching between model answers and references is based on the head word.…”

“…Event Schema Induction seminal work studies patterns (Shinyama and Sekine, 2006;Filatova et al, 2006;Qiu et al, 2008) and event chains (Chambers and Jurafsky, 2011) for template induction. For MUC 4, the current dominant methods include probabilistic generative methods (Chambers, 2013;Cheung et al, 2013;Nguyen et al, 2015) that jointly model predicate and ar-gument assignment, and ad-hoc clustering algorithms for inducing slots (Sha et al, 2016;Ahn, 2017;Yuan et al, 2018). These methods all rely on hand-crafted discrete features without fully model the textual redundancy.…”

“…In addition, we also perform slot mapping, between slots that our model learns and slots in the annotation. Following previous work on MUC 4 (Chambers, 2013;Cheung et al, 2013;Nguyen et al, 2015;Sha et al, 2016;Ahn, 2017), we implement automatic greedy slot mapping. Each reference slot is mapped to a learned slot that ranks the best according to the F1-score metric on GNBusiness-Dev.…”

“…Extracting events from news text has received much research attention. The task typically consists of two subtasks, namely schema induction, which is to extract event templates that specify argument slots for given event types (Chambers, 2013;Cheung et al, 2013;Nguyen et al, 2015;Sha et al, 2016;Ahn, 2017;Yuan et al, 2018), and event extraction, which is to identify events with filled slots from a piece of news (Nguyen et al, 2016b;Sha et al, 2018;Liu et al, 2018a;Chen et al, 2018Chen et al, , 2015Nguyen and Grishman, 2016;Liu et al, 2018b). Previous work focuses on extracting events from single news documents according to a set of pre-specified event types, such as arson, attack or earthquakes.…”