Language Technologies Thesis Defense
- Gates Hillman Centers
- ASA Conference Room 6115
- JUN ARAKI
- Ph.D. Student
- Language Technologies Institute
- Carnegie Mellon University
Extraction of Event Structures from Text
Events are a key semantic component integral to information extraction and natural language understanding, enhancing many downstream applications. Despite their importance, they have received less attention in research on natural language processing. Salient properties of events are that they are a ubiquitous linguistic phenomenon appearing in various domains and that they compose rich discourse structures via event coreferences, forming a coherent story over multiple sentences.
The central goal of this thesis is to devise a computational method that models the structural property of events in a principled framework to enable more sophisticated event detection and event coreference resolution. To achieve this goal, we address five important problems in these areas: (1) restricted domains of events, (2) data sparsity in event detection, (3) lack of subevent detection, (4) event interdependencies via event coreference, and (5) limited applications of events. For the first two problems, we introduce a new paradigm of open-domain event detection and show that it is feasible for our distant supervision method to build models detecting events robustly in various domains while obviating the need for human annotation of events. For the third and fourth problems, we show how structured learning models are capable of capturing event interdependencies and making more informed decisions on event coreference resolution and subevent detection. Lastly, we present a novel application of event structures for question generation, illustrating important roles of event structures in natural language understanding by humans.
Teruko Mitamura (Chair)
Luke Zettlemoyer (University of Washington)