Recent neural architectures in sequence labeling have yielded state-of-the-art performance on single domain data such as newswires. However, they still suffer from (i) requiring massive amounts of training data to avoid overfitting; (ii) huge performance degradation when there is a domain shift in the data distribution between training and testing. In this paper, we investigate the problem of domain adaptation for sequence labeling under homogeneous and heterogeneous settings. We propose MetaSeq, a novel meta-learning approach for domain adaptation in sequence labeling. Specifically, MetaSeq incorporates meta-learning and adversarial training strategies to encourage robust, general and transferable representations for sequence labeling. The key advantage of MetaSeq is that it is capable of adapting to new unseen domains with a small amount of annotated data from those domains. We extensively evaluate MetaSeq on named entity recognition, part-of-speech tagging and slot filling tasks under homogeneous and heterogeneous settings. The experimental results show that MetaSeq achieves state-of-the-art performance against eight baselines. Impressively, MetaSeq surpasses the in-domain performance using only 16.17% and 7% of target domain data on average for homogeneous settings, and 34.76%, 24%, 22.5% of target domain data on average for heterogeneous settings.

In this paper, we study the following problem: given a knowledge graph (KG) and a set of input vertices (representing concepts or entities) and edge labels, we aim to find the smallest connected subgraphs containing all of the inputs. This problem plays a key role in KG-based search engines and natural language question answering systems, and it is a natural extension of the Steiner tree problem, which is known to be NP-hard. We present RECON, a system for finding approximate answers. RECON aims at achieving high accuracy with instantaneous response (i.e., sub-second/millisecond delay) over KGs with hundreds of millions edges without resorting to expensive computational resources. Furthermore, when no answer exists due to disconnection between concepts and entities, RECON refines the input to a semantically similar one based on the ontology, and attempts to find answers with respect to the refined input. We conduct a comprehensive experimental evaluation of RECON. In particular we compare it with five existing approaches for finding approximate Steiner trees. Our experiments on four large real and synthetic KGs show that RECON significantly outperforms its competitors and incurs a much smaller memory footprint.

Shifting from Big Data to Big Knowledge requires systems that are able to cope with the large volume and high-velocity dimensions in a scalable and inference-enabled manner. In this work, we are focusing on stream processing and reasoning using the graph-based RDF data model. We are aiming to explore the ability of modern distributed computing frameworks to process highly expressive knowledge inference queries over Big Data streams. To do so, we consider queries expressed as a positive fragment of a temporal logic framework based on Answer Set Programming and propose solutions to process such queries, based on the two main execution models adopted by major parallel and distributed execution frameworks: Bulk Synchronous Parallel (BSP) and Recordat-A-Time (RAT). We implement our solution named BigSR and conduct a series of experiments with 15 queries from 4 different datasets. Our experiments show that BigSR achieves high throughput beyond million-triples per second using a rather small cluster of machines.

Reasoning over semantically annotated data is an emerging trend in stream processing aiming to produce sound and complete answers to a set of continuous queries. It usually comes at the cost of finding a trade-off between data throughput and the cost of expressive inferences. StriderRproposes such a trade-off and combines a scalable RDF stream processing engine with an efficient reasoning system. The main reasoning tasks are based on a query rewriting approach for SPARQL that benefits from an intelligent encoding of an extension of the RDFS (i.e., RDFS with owl:sameAs) ontology elements. StriderRruns in production at a major international water management company to detect anomalies from sensor streams. The system is evaluated along different dimensions and over multiple datasets to emphasize its performance.

Real-time processing of data streams emanating from sensors is becoming a common task in industrial scenarios. An increasing number of processing jobs executed over such platforms are requiring reasoning mechanisms. The key implementation goal is thus to efficiently handle massive incoming data streams and support reasoning, data analytic services. Moreover, in an on-going industrial project on anomaly detection in large potable water networks, we are facing the effect of dynamically changing data and work characteristics in stream processing. The Strider system addresses these research and implementation challenges by considering scalability, fault-tolerance, high throughput and acceptable latency properties. We will demonstrate the benefits of Strider on an Internet of Things-based real world and industrial setting.