Wikipedia, one of the best-known wikis and the world’s largest free online encyclopedia, has embraced the power of collaborative editing to harness collective intelligence. However, using such a wiki to create high-quality articles is not as easy as people imagine, given for instance the difficulty of reusing knowledge already available in Wikipedia. As a result, the heavy burden of upbuilding and maintaining the ever-growing online encyclopedia still rests on a small group of people. In this article, we aim at facilitating wiki authoring by providing annotation recommendations, thus lightening the burden of both contributors and administrators. We leverage the collective wisdom of the users by exploiting Semantic Web technologies with Wikipedia data and adopt a unified algorithm to support link, category, and semantic relation recommendation. A prototype system named EachWiki is proposed and evaluated. The experimental results show that it has achieved considerable improvements in terms of effectiveness, efficiency and usability. The proposed approach can also be applied to other wiki-based collaborative editing systems.
The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging. Firstly, the states need to be able to represent compound entities such as symptoms with their body part or diseases with degrees of severity to provide enough information for decision support. Secondly, these named entities in the utterance might be discontinuous and scattered across sentences and speakers. These also make it difficult to annotate a large corpus which is essential for most methods. Therefore, we first define a multi-hierarchical state structure. We annotate and publish a medical dialogue dataset in Chinese. To the best of our knowledge, there are no publicly available ones before. Then we propose a Prompt-based Generative Approach which can generate slot values with multi-hierarchies incrementally using a top-down approach. A dialogue style prompt is also supplemented to utilize the large unlabeled dialogue corpus to alleviate the data scarcity problem. The experiments show that our approach outperforms other DST methods and is rather effective in the scenario with little data.
Semantic Wikipedia aims to enhance Wikipedia by adding explicit semantics to links between Wikipedia entities. However, we have observed that it currently suffers the following limitations: lack of semantic annotations and lack of semantic annotators. In this paper, we resort to relation population to automatically extract relations between any entity pair to enrich semantic data, and predicate suggestion to recommend proper relation labels to facilitate semantic annotating. Both tasks leverage relation classification which tries to classify extracted relation instances into predefined relations. However, due to the lack of labeled data and the excessiveness of noise in Semantic Wikipedia, existing approaches cannot be directly applied to these tasks to obtain high-quality annotations. In this paper, to tackle the above problems brought by Semantic Wikipedia, we use a label propagation algorithm and exploit semantic features like domain and range constraints on categories as well as linguistic features such as dependency trees of context sentences in Wikipedia articles. The experimental results on 7 typical relation types show the effectiveness and efficiency of our approach in dealing with both tasks.
Nowadays, the demand on querying and searching the Semantic Web is increasing. Some systems have adopted IR (Information Retrieval) approaches to index and search the Semantic Web data due to its capability to handle the Web-scale data and efficiency on query...
Named entity recognition and relation extraction are two important core subtasks of information extraction, which aim to identify named entities and extract relations between them. In recent years, span representation methods have received a lot of attention and are widely used to extract entities and corresponding relations from plain texts. Most recent works focus on how to obtain better span representations from pre-trained encoders, but ignore the negative impact of a large number of span candidates on slowing down the model performance. In our work, we propose a joint entity and relation extraction model with an attention mechanism and position-attentive markers. The attention score of each candidate span is calculated, and most of the candidate spans with low attention scores are pruned before being fed into the span classifier, thus achieving the goal of removing the most irrelevant spans. At the same time, in order to explore whether the position information can improve the performance of the model, we add position-attentive markers to the model. The experimental results show that our model is effective. With the same pre-trained encoder, our model achieves the new state-of-the-art on standard benchmarks (ACE05, CoNLL04 and SciERC), obtaining a 4.7%-17.8% absolute improvement in relation F1.
Multi-hop Knowledge Base Question Answering (KBQA) aims to predict answers that require multi-hop reasoning from the topic entity in the question over the Knowledge Base (KB). Relation extraction is a core step in KBQA, which extracts the relation path from the topic entity to the answer entity. Compared with single-hop questions, multi-hop ones have more complex syntactic structures to understand, and multi-hop relation paths lead to a larger search space, which makes it much more challenging to extract the correct relation paths. To tackle the above challenges, most existing relation extraction approaches focus on the semantic similarity between questions and relation paths. However, those approaches only consider the word semantics of the relation names but ignore the graph semantics inside the knowledge base. As a result, their generalization ability relying on the naming rules of the relations, making it more difficult to generalize over large knowledge bases. To address the current limitations and take advantage of the graph semantics of relations, we propose a novel translational embedding-based relation extractor that utilizes pretrained embeddings from TransE. In particular, we treat the multi-hop relation path as a translation from the first relation to the last one in the semantic space of TransE. Then we map the question into this space under the supervision of the path embeddings. To take full advantage of the pretrained graph semantics in TransE, we propose a KBQA framework that leverages pretrained relation semantics in relation extraction and pretrained entity semantics in answer selection. Our approach achieves state-of-the-art performance on two benchmark datasets, WebQuestionSP and MetaQA, demonstrating its effectiveness on the multi-hop KBQA task.
The Web of Data keeps growing rapidly. However, the full exploitation of this large amount of structured data faces numerous challenges like usability, scalability, imprecise information needs and data change. We present Semplore, an IR-based system that aims at addressing these issues. Semplore supports intuitive faceted search and complex queries both on text and structured data. It combines imprecise keyword search and precise structured query in a unified ranking scheme. Scalable query processing is supported by leveraging inverted indexes traditionally used in IR systems. This is combined with a novel block-based index structure to support efficient index update when data changes. The experimental results show that Semplore is an efficient and effective system for searching the Web of Data and can be used as a basic infrastructure for Web-scale Semantic Web search engines.
Recently, more and more short texts (e.g., ads, tweets) appear on the Web. Classifying short texts into a large taxonomy like ODP or Wikipedia category system has become an important mining task to improve the performance of many applications such as contextual advertising and topic detection for micro-blogging. In this paper, we propose a novel multi-stage classification approach to solve the problem. First, explicit semantic analysis is used to add more features for both short texts and categories. Second, we leverage information retrieval technologies to fetch the most relevant categories for an input short text from thousands of candidates. Finally, a SVM classifier is applied on only a few selected categories to return the final answer. Our experimental results show that the proposed method achieved significant improvements on classification accuracy compared with several existing state of art approaches.
The Web contains a large amount of documents and increasingly, also semantic data in the form of RDF triples. Many of these triples are annotations that are associated with documents. While structured query is the principal mean to retrieve semantic data, keyword queries are typically used for document retrieval. Clearly, a form of hybrid search that seamlessly integrates these formalisms to query both documents and semantic data can address more complex information needs. In this paper, we present CE2, an integrated solution that leverages mature database and information retrieval technologies to tackle challenges in hybrid search on the large scale. For scalable storage, CE2 integrates database with inverted indices. Hybrid query processing is supported in CE2 through novel algorithms and data structures, which allow for advanced ranking schemes to be integrated more tightly into the process. Experiments conducted on Dbpedia and Wikipedia show that CE2 can provide good performance in terms of both effectiveness and efficiency.
Efficient support for querying large-scale resource description framework (RDF) triples plays an important role in semantic web data management. This paper presents an efficient RDF query engine to evaluate SPARQL queries, where the inverted index structure is employed for indexing the RDF triples. A set of operators on the inverted index was developed for query optimization and evaluation. Then a main-tree-shaped optimization algorithm was developed that transforms a SPARQL query graph into the optimal query plan by effectively reducing the search space to determine the optimal joining order. The optimization collects a set of RDF statistics for estimating the execution cost of the query plan. Finally the optimal query plan is evaluated using the defined operators for answering the given SPARQL query. Extensive tests were conducted on both synthetic and real datasets containing up to 100 million triples to evaluate this approach with the results showing that this approach can answer most queries within 1 s and is extremely efficient and scalable in comparison with previous best state-of-the-art RDF stores.
