One of the main strengths of the web is that it allows any party of its global community to share information with any other party. This goal has been achieved by making use of a u...
Supervised and unsupervised learning methods have traditionally focused on data consisting of independent instances of a single type. However, many real-world domains are best des...
This paper proposes a Unified Dynamic Relation Tree (DRT) span for tree kernel-based semantic relation extraction between entity names. The basic idea is to apply a variety of lin...
Many real-world domains are relational in nature, consisting of a set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type...
Benjamin Taskar, Ming Fai Wong, Pieter Abbeel, Dap...
Named Entity (NE) recognition from the results of Automatic Speech Recognition (ASR) is challenging because of ASR errors. To detect NEs, one of the options is to use a statistica...