We propose a generic, memory-based approach for the detection of implicit semantic roles. While state-of-the-art methods for this task combine hand-crafted rules with specialized and costly lexical resources, our models use large corpora with automated annotations for explicit semantic roles only to capture the distribution of predicates and their associated roles. We show that memory-based lea...

When first introduced in 1981, angiotensin-converting enzyme (ACE) inhibitors were indicated only for treatment of refractory hypertension. Since then, they have been shown to reduce morbidity or mortality in congestive heart failure, myocardial infarction, diabetes mellitus, chronic renal insufficiency, and atherosclerotic cardiovascular disease. Pathologies underlying these conditions are, in...

The ongoing reading process of digital meters is time-consuming and prone to errors, as operators capture images manually update the system with new readings. This work proposes automate this operation through a deep learning-powered solution for universal controllers flow that can be seamlessly incorporated into operators’ existing workflow. Firstly, display area equipment extracted screen det...

We study the usefulness of intermediate semantic concepts in bridging the semantic gap in automatic video retrieval. The results of a series of large-scale retrieval experiments, which combine text-based search, content-based retrieval, and concept-based retrieval, is presented. The experiments use the common video data and sets of queries from three successive TRECVID evaluations. By including...

In this paper we will describe Berkeley’s approach to the ImageCLEFphoto task for CLEF 2007. Once again (as in ImageCLEFphoto for CLEF 2006) we used entirely text-based methods for retrieval. For some runs this year, however, we exploited the basic similarity of the topics and database from 2006 to acquire the metadata descriptions of the “example images” in the 2007 queries, and used that meta...

Available visual temporal querying tools do not provide the means for formulating complex temporal queries. For these queries users have to adopt text-based querying languages, such as SQL. The problem, however, is that using text-based languages is less comfortable than using visual tools and, most important, in some cases temporal queries can be extremely difficult to formulate for users that...

This paper shows by a quantitative evaluation that nonrestrictive modi cation in Japanese is a marked factor of prosody, and describes how to extract non-restrictive modication. In Japanese, restrictive and non-restrictive modi cation have the same syntactic structure, so it is di cult to distinguish them. We propose rules to extract non-restrictive modi cation in news-text based on the classi ...

Author profiling task aims to identify different traits of an author by analyzing his/her written text. This study presents a Stylometry-based approach for detection of author traits (gender and age) for cross-genre author profiles. In our proposed approach, we used different types of stylistic features including 7 lexical features, 16 syntactic features, 26 character-based features and 6 vocab...