We propose Neural Variational Set Expansion to extract actionable information from a noisy knowledge graph (kg) and propose a general approach for increasing the interpretability of recommendation systems. We demonstr...
详细信息
Automated construction of knowledge hierarchies is gaining increasing attention to tackle the infeasibility of manually extracting and semantically linking millions of concepts. With the evolution of knowledge hierarc...
详细信息
The proceedings contain 12 papers. The topics discussed include: search and recommendation in the enterprise;research challenges in legal discovery and investigations;automatic shortlisting of candidates in recruitmen...
The proceedings contain 12 papers. The topics discussed include: search and recommendation in the enterprise;research challenges in legal discovery and investigations;automatic shortlisting of candidates in recruitment;searching for relevant lessons learned using hybrid information retrieval classifiers: a case study in software engineering;refresh strategies in continuous active learning;validating the importance of work tasks for professional search;challenges in the development of effective systems for professional legal search;distributional representation of complex semantics;learning new type representations from knowledgegraphs;neural variational entity set expansion for automatically populated knowledgegraphs;and summarizing entities using distantly supervised information extractors.
The lessons learned (LL) repository is one of the most valuable sources of knowledge for a software organization. It can provide distinctive guidance regarding previous working solutions for historical software manage...
详细信息
The proceedings contain 8 papers. The topics discussed include: predicting asymmetric transitive relations in knowledge bases;measuring demonstrated potential domain knowledge with knowledgegraphs;entity attribute ra...
The proceedings contain 8 papers. The topics discussed include: predicting asymmetric transitive relations in knowledge bases;measuring demonstrated potential domain knowledge with knowledgegraphs;entity attribute ranking using learning to rank;test collection for evaluating actionable knowledgegraphs;enhancing categorization of computer science research papers using knowledge bases;natural language supported relation matching for question answering with knowledgegraphs;and early fusion strategy for entity-relationship retrieval.
Current search and recommendation engines enable us to effectively retrieve a set of documents based on topical relevance. What is not taken into account is the knowledge a user may already have about a topic, e.g., w...
详细信息
暂无评论