No Arabic abstract
In the last decade, a large number of Knowledge Graph (KG) information extraction approaches were proposed. Albeit effective, these efforts are disjoint, and their collective strengths and weaknesses in effective KG information extraction (IE) have not been studied in the literature. We propose Plumber, the first framework that brings together the research communitys disjoint IE efforts. The Plumber architecture comprises 33 reusable components for various KG information extraction subtasks, such as coreference resolution, entity linking, and relation extraction. Using these components,Plumber dynamically generates suitable information extraction pipelines and offers overall 264 distinct pipelines.We study the optimization problem of choosing suitable pipelines based on input sentences. To do so, we train a transformer-based classification model that extracts contextual embeddings from the input and finds an appropriate pipeline. We study the efficacy of Plumber for extracting the KG triples using standard datasets over two KGs: DBpedia, and Open Research Knowledge Graph (ORKG). Our results demonstrate the effectiveness of Plumber in dynamically generating KG information extraction pipelines,outperforming all baselines agnostics of the underlying KG. Furthermore,we provide an analysis of collective failure cases, study the similarities and synergies among integrated components, and discuss their limitations.
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than standard information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than 100 documents) are sufficient to achieve reasonable accuracy. We integrate our models into an end-to-end cloud platform that provides both an easy-to-use annotation interface as well as an inference interface that allows users to upload documents and inspect model outputs.
Systematic reviews, which entail the extraction of data from large numbers of scientific documents, are an ideal avenue for the application of machine learning. They are vital to many fields of science and philanthropy, but are very time-consuming and require experts. Yet the three main stages of a systematic review are easily done automatically: searching for documents can be done via APIs and scrapers, selection of relevant documents can be done via binary classification, and extraction of data can be done via sequence-labelling classification. Despite the promise of automation for this field, little research exists that examines the various ways to automate each of these tasks. We construct a pipeline that automates each of these aspects, and experiment with many human-time vs. system quality trade-offs. We test the ability of classifiers to work well on small amounts of data and to generalise to data from countries not represented in the training data. We test different types of data extraction with varying difficulty in annotation, and five different neural architectures to do the extraction. We find that we can get surprising accuracy and generalisability of the whole pipeline system with only 2 weeks of human-expert annotation, which is only 15% of the time it takes to do the whole review manually and can be repeated and extended to new data with no additional effort.
We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by selecting the most confident entity spans and linking these nodes with confidence-weighted relation types and coreferences. The dynamic span graph allows coreference and relation type confidences to propagate through the graph to iteratively refine the span representations. This is unlike previous multi-task frameworks for information extraction in which the only interaction between tasks is in the shared first-layer LSTM. Our framework significantly outperforms the state-of-the-art on multiple information extraction tasks across multiple datasets reflecting different domains. We further observe that the span enumeration approach is good at detecting nested span entities, with significant F1 score improvement on the ACE dataset.
Existing works for extracting navigation objects from webpages focus on navigation menus, so as to reveal the information architecture of the site. However, web 2.0 sites such as social networks, e-commerce portals etc. are making the understanding of the content structure in a web site increasingly difficult. Dynamic and personalized elements such as top stories, recommended list in a webpage are vital to the understanding of the dynamic nature of web 2.0 sites. To better understand the content structure in web 2.0 sites, in this paper we propose a new extraction method for navigation objects in a webpage. Our method will extract not only the static navigation menus, but also the dynamic and personalized page-specific navigation lists. Since the navigation objects in a webpage naturally come in blocks, we first cluster hyperlinks into different blocks by exploiting spatial locations of hyperlinks, the hierarchical structure of the DOM-tree and the hyperlink density. Then we identify navigation objects from those blocks using the SVM classifier with novel features such as anchor text lengths etc. Experiments on real-world data sets with webpages from various domains and styles verified the effectiveness of our method.
For IoT to reach its full potential, the sharing and reuse of information in different applications and across verticals is of paramount importance. However, there are a plethora of IoT platforms using different representations, protocols and interaction patterns. To address this issue, the Fed4IoT project has developed an IoT virtualization platform that, on the one hand, integrates information from many different source platforms and, on the other hand, makes the information required by the respective users available in the target platform of choice. To enable this, information is translated into a common, neutral exchange format. The format of choice is NGSI-LD, which is being standardized by the ETSI Industry Specification Group on Context Information Management (ETSI ISG CIM). Thing Visors are the components that translate the source information to NGSI-LD, which is then delivered to the target platform and translated into the target format. ThingVisors can be implemented by hand, but this requires significant human effort, especially considering the heterogeneity of low level information produced by a multitude of sensors. Thus, supporting the human developer and, ideally, fully automating the process of extracting and enriching data and translating it to NGSI-LD is a crucial step. Machine learning is a promising approach for this, but it typically requires large amounts of hand-labelled data for training, an effort that makes it unrealistic in many IoT scenarios. A programmatic labelling approach called knowledge infusion that encodes expert knowledge is used for matching a schema or ontology extracted from the data with a target schema or ontology, providing the basis for annotating the data and facilitating the translation to NGSI-LD.