Leveraging FrameNet to Improve Automatic Event Detection

Abstract

Frames defined in FrameNet (FN) share highly similar structures with events in ACE event extraction program. An event in ACE is composed of an event trigger and a set of arguments. Analogously, a frame in FN is composed of a lexical unit and a set of frame elements, which play similar roles as triggers and arguments of ACE events respectively. Besides having similar structures, many frames in FN actually express certain types of events. The above observations motivate us to explore whether there exists a good mapping from frames to event-types and if it is possible to improve event detection by using FN. In this paper, we propose a global inference approach to detect events in FN. Further, based on the detected results, we analyze possible mappings from frames to event-types. Finally, we improve the performance of event detection and achieve a new state-of-the-art result by using the events automatically detected from FN.

Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms

“…ANN performs unexpectedly poorly, which indicates that unsupervised-attention mechanisms do not work well for ED. We believe the reason is that the training data of ACE 2005 corpus is insufficient to train a precise attention in an unsupervised manner, considering that data sparseness is an important issue of ED (Zhu et al, 2014;Liu et al, 2016a).…”

“…As illustrated in figure 1, we employ a threelayer (an input layer, a hidden layer and a softmax output layer) Artificial Neural Networks (ANNs) (Hagan et al, 1996) to model the ED task, which has been demonstrated very effective for event detection by Liu et al (2016a).…”

“…Recently, Liu et al (2016a) used events automatically detected from FN as extra training data to alleviate the data-sparseness problem for event detection. To further demonstrate the effectiveness of the proposed approach, we also use the events from FN to augment the performance of our approach.…”

“…In this work, we use the events published by Liu et al (2016a) 5 as extra training data. However, their data can not be used in the proposed approach without further processing, because it lacks of both argument and entity information.…”

Event Detection Using Frame-Semantic Parser

“…This property implies that a mapping from FrameNet Frames to ACE types and subtypes can be extremely helpful in Event Detection (Liu et al, 2016).…”