Knowledge base completion via search-based question answering

By Robert West, Evgeniy Gabrilovich, Kevin P. Murphy, Shaohua Sun, Rahul Gupta, Dekang Lin. The Web Conference, 2014

336 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/d2567a7de43ad073d68e12dec0df23f5d72c2022

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Open Domain Question Answering via Semantic Enrichment (2015, background): “However, despite their large size, existing knowledge bases are still far from complete and not updated in a timely fashion [14, 32, 42].”
Knowledge Graph Embedding for Link Prediction (2020, background): “For instance, it has been observed that over 70% of person entities have no known place of birth, and over 99% have no known ethnicity [12, 69] in FreeBase, one of the largest and most widely used KGs for research purposes.”
Ultra-Fine Entity Typing (2018, background): “This approach has two limitations: recall can suffer due to KB incompleteness (West et al., 2014), and precision can suffer when the selected types do not fit the context (Ritter et al.”
A Review of Relational Machine Learning for Knowledge Graphs (2015, background): “In addition to missing facts, there are many entities that are mentioned on the Web but are currently missing in knowledge graphs like Freebase and YAGO.”
Training a Ranking Function for Open-Domain Question Answering (2018, background): “The drawback of this approach is that these knowledge bases are not complete (West et al., 2014), and are expensive to construct and maintain.”
Knowledge graph refinement: A survey of approaches and evaluation methods (2016, background): “[104] propose the use of web search engines to fill gaps in knowledge graphs.”
Diagnostic Inferencing via Improving Clinical Concept Extraction with Deep Reinforcement Learning: A Preliminary Study (2017, background): “However, KBs have certain limitations such as knowledge incompleteness, sparsity, and fixed schema (Socher et al., 2013; West et al., 2014; Bordes et al., 2014), which motivate researchers to use unstructured textual resources like Wikipedia for various related tasks (Katz et al., 2005; Wu and…”
Quasar: Datasets for Question Answering by Search and Reading (2017, background): “However, even the largest KBs are often incomplete (Miller et al., 2016; West et al., 2014), and hence can only answer a limited subset of all possible factoid questions.”
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages (2018, background): “West et al. (2014) focuses on the problem of knowledge base completion, through question answering and tries to complete missing facts in Freebase based on templates.”
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases (2016, background): “, as primitives in information extraction, knowledge base population [10, 52], and question-answering systems [48, 3].”
Scalable Semantic Parsing with Partial Ontologies (2015, background): “For example, a recent study (West et al., 2014) showed that over 70% of people in FB have no birth place, and 99% have no ethnicity.”
Learning to Diagnose: Assimilating Clinical Narratives using Deep Reinforcement Learning (2017, background): “However, KBs are known to have limitations such as knowledge in-completeness, sparsity, and ﬁxed schema (Socher et al., 2013; West et al., 2014; Bordes et al., 2014), which have motivated researchers to use unstructured textual resources like Wikipedia for various related tasks (Katz et al., 2005;…”
Towards a Continuous Knowledge Learning Engine for Chatbots (2018, background): “Even if some existing systems can use very large knowledge bases either harvested from a large data source such as the Web or built manually, these KBs still miss a large number of facts (knowledge) (West et al., 2014).”
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning (2016, background): “West et al. (2014) explore query reformulation in the context of KBC.”
Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs (2019, background): “However, KGs typically ∗ Equal Contribution suffer from missing relations (Socher et al., 2013a; West et al., 2014).”
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network (2017, background): “However, the KBs are still incomplete, i.e., missing a lot of valid triples (Socher et al., 2013; West et al., 2014).”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, background): “However, the incompleteness [52] of the KBs limits the scope of their applications.”