Building large datasets annotated with semantic information, such as FrameNet, is an expensive process. Consequently, such resources are unavailable for many languages and specific domains. This problem can be alleviated by using unsupervised approaches to induce the frames evoked by a collection of documents. That is the objective of the second task of SemEval 2019, which comprises three subtasks: clustering of verbs that evoke the same frame and clustering of arguments into both frame-specific slots and semantic roles. We approach all the subtasks by applying a graph clustering algorithm on contextualized embedding representations of the verbs and arguments. Using such representations is appropriate in the context of this task, since they provide cues for word-sense disambiguation. Thus, they can be used to identify different frames evoked by the same words. Using this approach we were able to outperform all of the baselines reported for the task on the test set in terms of Purity F 1 , as well as in terms of BCubed F 1 in most cases.
The SEAGULL project aims at the development of intelligent systems to support maritime situation awareness based on unmanned aerial vehicles. It proposes to create an intelligent maritime surveillance system by equipping unmanned aerial vehicles (UAVs) with different types of optical sensors. Optical sensors such as cameras (visible, infrared, multi and hyper spectral) can contribute significantly to the generation of situational awareness of maritime events such as (i) detection and georeferencing of oil spills or hazardous and noxious substances; (ii) tracking systems (e.g. vessels, shipwrecked, lifeboat, debris, etc.); (iii) recognizing behavioral patterns (e.g. vessels rendezvous, high-speed vessels, atypical patterns of navigation, etc.); and (iv) monitoring parameters and indicators of good environmental status. On-board transponders will be used for collision detection and avoidance mechanism (sense and avoid). This paper describes the core of the research and development work done during the first 2 years of the project with particular emphasis on the following topics: system architecture, automatic detection of sea vessels by vision sensors and custom designed computer vision algorithms; and a sense and avoid system developed in the theoretical framework of zero-sum differential games.
Resources such as FrameNet, which provide sets of semantic frame definitions and annotated textual data that maps into the evoked frames, are important for several NLP tasks. However, they are expensive to build and, consequently, are unavailable for many languages and domains. Thus, approaches able to induce semantic frames in an unsupervised manner are highly valuable. In this paper we approach that task from a network perspective as a community detection problem that targets the identification of groups of verb instances that evoke the same semantic frame and verb arguments that play the same semantic role. To do so, we apply a graph-clustering algorithm to a graph with contextualized representations of verb instances or arguments as nodes connected by edges if the distance between them is below a threshold that defines the granularity of the induced frames. By applying this approach to the benchmark dataset defined in the context of SemEval 2019, we outperformed all of the previous approaches to the task, achieving the current state-of-the-art performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.