Abstract. Distributed Human Computation (DHC) is used to solve computational problems by incorporating the collaborative effort of a large number of humans. It is also a solution to AI-complete problems such as natural language processing. The Semantic Web with its root in AI has many research problems that are considered as AI-complete. E.g. co-reference resolution, which involves determining whether different URIs refer to the same entity, is a significant hurdle to overcome in the realisation of large-scale Semantic Web applications. In this paper, we propose a framework for building a DHC system on top of the Linked Data Cloud to solve various computational problems. To demonstrate the concept, we are focusing on handling the co-reference resolution when integrating distributed datasets. Traditionally machine-learning algorithms are used as a solution for this but they are often computationally expensive, error-prone and do not scale. We designed a DHC system named iamResearcher, which solves the scientific publication author identity coreference problem when integrating distributed bibliographic datasets. In our system, we aggregated 6 million bibliographic data from various publication repositories. Users can sign up to the system to audit and align their own publications, thus solving the co-reference problem in a distributed manner. The aggregated results are dereferenceable in the Open Linked Data Cloud.
Ad-hoc microphone arrays has recieved attention, in which the number and arrangement of microphones are unknown. Traditional multi-channel processing methods can not be directly used in ad-hoc. Recently, to solve this problem, an utterance-level ASV with ad-hoc microphone arrays has been proposed, which first extracts utterance-level speaker embeddings from each channel of an ad-hoc microphone array, and then fuses the embeddings for the final verification. However, this method cannot make full use of the cross-channel information. In this paper, we present a novel multi-channel ASV model at the frame-level. Specifically, we add spatiotemporal processing blocks (STB) before the pooling layer, which models the contextual relationship within and between channels and across time, respectively. The channel-attended outputs from STB are sent to the pooling layer to obtain an utterance-level speaker representation. Experimental results demonstrate the effectiveness of the proposed method.
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.