Tim O'Gorman

Challenges of Adding Causation to Richer Event Descriptions

The goal of this study is to create guidelines for annotating cause-effect relations as part of the Richer Event Description schema. We present the challenges faced using the definition of causation in terms of counterfactual dependence and propose new guidelines for cause-effect annotation using an alternative definition which treats causation as an intrinsic relation between events. To support the use of such an intrinsic definition, we examine the theoretical problems that the counterfactual definition faces, show how the intrinsic definition solves those problems, and explain how the intrinsic definition adheres to psychological reality, at least for our annotation purposes, better than the counterfactual definition. We then evaluate the new guidelines by presenting results obtained from pilot annotations of ten documents, showing that an inter-annotator agreement (F1-score) of 0.5753 was achieved. The results provide a benchmark for future studies concerning cause-effect annotation in the RED schema.

A Corpus of Preposition Supersenses

We present the first corpus annotated with preposition supersenses, unlexicalized categories for semantic functions that can be marked by English prepositions (Schneider et al., 2015). The preposition supersenses are organized hierarchically and designed to facilitate comprehensive manual annotation. Our dataset is publicly released on the web. 1

Building a Cross-document Event-Event Relation Corpus

We propose a new task of extracting eventevent relations across documents. We present our efforts at designing an annotation schema and building a corpus for this task. Our schema includes five main types of relations: Inheritance, Expansion, Contingency, Comparison and Temporality, along with 21 subtypes. We also lay out the main challenges based on detailed inter-annotator disagreement and error analysis. We hope these resources can serve as a benchmark to encourage research on this new problem.

A Comparison of Event Representations in DEFT

This paper will discuss and compare event representations across a variety of types of event annotation: Rich Entities, Relations, and Events (Rich ERE), Light Entities, Relations, and Events (Light ERE), Event Nugget (EN), Event Argument Extraction (EAE), Richer Event Descriptions (RED), and Event-Event Relations (EER). Comparisons of event representations are presented, along with a comparison of data annotated according to each event representation. An event annotation experiment is also discussed, including annotation for all of these representations on the same set of sample data, with the purpose of being able to compare actual annotation across all of these approaches as directly as possible. We walk through a brief example to illustrate the various annotation approaches, and to show the intersections among the various annotated data sets.

Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation

There have been a wide range of recent annotated corpora concerning events, either regarding event coreference, the temporal order of events, hierarchical “subevent” structure of events, or causal relationships between events. However, although some believe that these different phenomena will display rich interactions, relatively few corpora annotate all of those layers of annotation in a unified fashion. This paper describes the annotation methodology for the Richer Event Descriptions corpus, which annotates entities, events, times, their coreference and partial coreference relations, and the temporal, causal and subevent relationships between the events. It suggests that such rich annotations of within-document event phenomena can be built with high quality through a multi-stage annotation pipeline, and that the resultant corpus could be useful for systems hoping to transition from the detection of isolated mentions of events toward a richer understanding of events grounded in the temporal, causal, referential and bridging relations that define them.

AMPN: a semantic resource for Arabic morphological patterns

Abstract In this paper, we present a pilot Arabic morphological Pattern Net study based on a lexical semantic resource. During this study, a limited number of Arabic Morphological Patterns have been selected in order to analyze the structure and the behavior of the verbs in the Arabic PropBank, which is a semantically annotated corpus of newswire text from the Annahar Journal. Our goal is twofold: (a) to study whether there is a direct relationship between morphological patterns and verbal semantic roles; and, (b) to verify that this direct relationship is a pervasive component of Arabic verb morphology. The approach to building our morphological Patterns database is based on linguistic generalization of the semantic roles of the verbal predicates. The results obtained show promising outcome for a future, more comprehensive study.

The Logic of AMR: Practical, Unified, Graph-Based Sentence Semantics for NLP

The Abstract Meaning Representation formalism is rapidly emerging as an important practical form of structured sentence semantics which, thanks to the availability of largescale annotated corpora, has potential as a convergence point for NLP research. This tutorial unmasks the design philosophy, data creation process, and existing algorithms for AMR semantics. It is intended for anyone interested in working with AMR data, including parsing text into AMRs, generating text from AMRs, and applying AMRs to tasks such as machine translation and summarization. The goals of this tutorial are twofold. First, it will describe the nature and design principles behind the representation, and demonstrate that it can be practical for annotation. In Part I: The AMR Formalism, participants will be coached in the basics of annotation so that, when working with AMR data in the future, they will appreciate the benefits and limitations of the process by which it was created. Second, the tutorial will survey the state of the art for computation with AMRs. Part II: Algorithms and Applications will focus on the task of parsing English text into AMR graphs, which requires algorithms for alignment, for structured prediction, and for statistical learning. The tutorial will also address graph grammar formalisms that have been recently developed, and future applications such as AMR-based machine translation and summarization. Participants with laptops are encouraged to bring them to the tutorial. Instructors Part I: The AMR Formalism Nathan Schneider is an annotation schemer and computational modeler for natural language. He has been involved in the design of the AMR formalism since 2012, when he interned with Kevin Knight at ISI. His 2014 dissertation introduced a coarse-grained representation for lexical semantics that facilitates rapid annotation and is practical for broad-coverage statistical NLP. He has also worked on semantic parsing for the FrameNet representation and other forms of syntactic/semantic annotation and processing for social media text. For most of these projects, he led the design of the annotation scheme, guidelines, and workflows, and the training and supervision of annotators.