For the 2nd EVENTS Workshop, we will have a genuine “working” meeting with interactive discussion sessions on the following topics:
"Implicit Causal Relations among Events in Text"
Jerry Hobbs, USC/ISI
Abstract: I will discuss the notion of causality that we need in natural language processing, listing its principal properties. Then I will look at several ways causality is encoded in discourse, including in conjunctions, modals, implicit coherence relations between discourse segments, and implicit causal relations within clauses. Discovering these causal relations can be viewed as a very general kind of coreference relation that serves to bind a discourse together.
Call for Papers:
The workshop invites the submissions of papers related to EVENTS.
Relevant topics for the workshop include, but are not limited to, the following areas:
The organizers will provide small number of annotated texts from the results of the first EVENTS workshop to each person who wishes to participate. We may use the UT-Dallas; Stanford annotated data; and IC domain annotated data provided by CMU. Using a part of the unified guidelines developed in the first workshop, participants will be asked to update event mentions and the coreference relation types (full or partial). With these results, participants will be asked to build a prototype small event hierarchy or one or more event scripts, based on the working documents. During the workshop, there will be some presentations by the participants in each session, followed by comparisons of people’s work and discussion.
Previous EVENTS workshop Information:
The 1st workshop focused on the following questions, and from the answers we produced a summary that gave rise to event annotation guidelines:
Eduard Hovy, Teruko Mitamura, Felisa Verdejo, Jun Araki, and Andrew Philpot. 2013. Events are Not Simple: Identity, Non-Identity, and Quasi-Identity. In Proceedings of the Workshop on Events: Definition, Detection, Coreference, and Representation, pages 21–28.