Active learning attempts to maximize a task model’s performance gain by obtaining a set of informative samples from an unlabeled data pool. Previous active learning methods usually rely on specific network architectures or task-dependent sample acquisition algorithms. Moreover, when selecting a batch sample, previous works suffer from insufficient diversity of batch samples because they only consider the informativeness of each sample. This paper proposes a task-independent batch acquisition method using triplet loss to distinguish hard samples in an unlabeled data pool with similar features but difficult to identify labels. To assess the effectiveness of the proposed method, we compare the proposed method with state-of-the-art active learning methods on two tasks, relation extraction and sentence classification. Experimental results show that our method outperforms baselines on the benchmark datasets.

Both entity typing and relation extraction from text corpora are widely used to identify the semantic types of an entity and a relation in a knowledge graph (KG). Most existing approaches rely on a pre-defined set of entity types and relation types in a KG. They thus cannot map entity mentions (relation mentions) to unseen entity types (relation types). To fundamentally overcome the limitations, we should add new semantic types of entities and relations to a KG schema. However, schema expansion traditionally requires manual conceptualization through a user’s observation on the text corpus while assuming the existence of suitable target KG schemas. In this work, we propose anActive learning framework forKnowledge graphSchemaExpansion (AKSE), which can generate a new semantic type for KG schemas, without depending on a set of target schemas and human users’ observation. Specifically, a granularity based active learning algorithm determines whether a KG schema requires new semantic types or not. We also introduce a KG schema attention-based neural method which assigns semantic types to the entities and relationships extracted. To the best of our knowledge, our work is the first study to expand a KG schema with active learning.

The accurate prediction of stress in a person’s life has a significant effect on improving personal health and the national economy. Since individuals have different historical circumstances and personality traits, stress symptoms and levels may vary from person to person. Thus, most studies on stress prediction pay attention to personalized models, which determine the personal stress level using user-specific information and heterogeneous stress-related data. However, these models cannot elaborately handle the uncertainty caused by the sparsity, data imbalance, irregularity, and high-dimensionality of user-specific information. In particular, out-of-sample users increase uncertainty. To cope with the problem, we propose a personalized stress-level prediction model with inductive Gaussian representation (PSP-IGR), which exploits heterogeneous inputs with a unified end-to-end approach. PSP-IGR extracts feature vectors from the heterogeneous inputs via Gaussian sampling, domain rules, and deep learning, depending on the characteristics of each input. Especially, PSP-IGR inductively generates a Gaussian feature vector called IGR by Gaussian sampling from the shared contents of user-specific information. Thus, PSP-IGR not only generalizes to both in-sample and out-of-sample users effectively but also deals with the uncertainty problem caused by limitations of healthcare datasets. Also, since we fuse the extracted feature vectors considering their characteristics (Gaussian and point vectors), we can preserve the expressiveness of each feature vector. Experiments on a real-world dataset, including survey results, wearable sensor signals, and contexts, demonstrate that PSP-IGR shows higher accuracy in predicting individual stress-level than previous models.

News recommendation systems? purpose is to tackle the immense amount of news and offer personalized recommendations to users. A major issue in news recommendation is to capture the precise news representations for the efficacy of recommended items. Commonly, news contents are filled with well-known entities of different types. However, existing recommendation systems overlook exploiting external knowledge about entities and topical relatedness among the news. To cope with the above problem, in this paper, we propose Topic-Enriched Knowledge Graph Recommendation System(TEKGR). Three encoders in TEKGR handle news titles in two perspectives to obtain news representation embedding: (1) to extract meaning of news words without considering latent knowledge features in the news and (2) to extract semantic knowledge of news through topic information and contextual information from a knowledge graph. After obtaining news representation vectors, an attention network compares clicked news to the candidate news in order to get the user's final embedding. Our TEKGR model is superior to existing news recommendation methods by manipulating topical relations among entities and contextual features of entities. Experimental results on two public datasets show that our approach outperforms state-of-the-art deep recommendation approaches.

This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). Unlike previous approaches, the proposed method focuses on an entity link, which consists of dependency edges between entities, and discourse relations between sentences. Specifically, the proposed model consists of two main sub-models. The first one encodes sentences with a higher weight on the entity link while considering the other edges with an attention mechanism. To consider various latent discourse relations between sentences, the second sub-model encodes discourse relations between adjacent sentences considering the contents of each sentence. Experiment results on the cross-sentence relation extraction dataset, PubMed, and the document-level relation extraction dataset, DocRED, show that the proposed model outperforms state-of-the-art methods of extracting relations across sentences. Furthermore, ablation study proves that both the two main sub-models have noticeable effect on the relation extraction task.

Byungkook Oh, Seungmin Seo, Cheolheon Shin, Eunju Jo, Kyong-Ho Lee. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

The amount of RDF data being published on the Web is increasing at a massive rate. MapReduce-based distributed frameworks have become the general trend in processing SPARQL queries against RDF data. Currently, query processing systems that use MapReduce have not been able to keep up with the increase of semantic annotated data, resulting in non-interactive SPARQL query processing. The principal reason is that intermediate query results from join operations in a MapReduce framework are so massive that they consume all available network bandwidth. In this article, the authors present an efficient SPARQL processing system that uses MapReduce and HBase. The system runs a job optimized query plan using their proposed abstract RDF data to decrease the number of jobs and also decrease the amount of input data. The authors also present an efficient algorithm of using Map-side joins while also using the abstract RDF data to filter out unneeded RDF data. Experimental results show that the proposed approach demonstrates better performance when processing queries with a large amount of input data than those found in previous works.

The main focus of relational learning for knowledge graph completion (KGC) lies in exploiting rich contextual information for facts. Many state-of-the-art models incorporate fact sequences, entity types, and even textual information. Unfortunately, most of them do not fully take advantage of rich structural information in a KG, i.e., connectivity patterns around each entity. In this paper, we propose a context-aware convolutional learning (CACL) model which jointly learns from entities and their multi-hop neighborhoods. Since we directly utilize the connectivity patterns contained in each multi-hop neighborhood, the structural role similarity among entities can be better captured, resulting in more informative entity and relation embeddings. Specifically, CACL collects entities and relations from the multi-hop neighborhood as contextual information according to their relative importance and uniquely maps them to a linear vector space. Our convolutional architecture leverages a deep learning technique to represent each entity along with its linearly mapped contextual information. Thus, we can elaborately extract the features of key connectivity patterns from the context and incorporate them into a score function which evaluates the validity of facts. Experimental results on the newest datasets show that CACL outperforms existing approaches by successfully enriching embeddings with neighborhood information.

Fog computing is a promising paradigm in terms of extending cloud computing to an edge network. In a broad sense, fog computing in Internet-of-Vehicles(IoV) provides low-latency services since fog nodes are closely located with moving cars and are locally distributed. In this paper, we propose a fog computing architecture based on a publish/subscribe model. After that, we describe a traffic congestion control scenario using a smart traffic light system which operates on top of the proposed architecture. Furthermore, we propose an upper-level domain ontology in order to enhance the expressivity of knowledge and describe a variety of semantic properties which interlink spatial information in IoV. Finally, we present an active rule where supports the exchange of event-driven messages between publishing and subscribing fog nodes.