Toward an Architecture for Never-Ending Language Learning
Explore this paper's citation graph
Summary
This work proposes an approach and a set of design principles for an intelligent computer agent that runs forever and describes a partial implementation of such a system that has already learned to extract a knowledge base containing over 242,000 beliefs.
- Type
- article
- Published
- 2010-07-05
- Cited by
- 2,264
- References
- 30
- Access
- Open access
- OpenAlex
- https://openalex.org/W1512387364
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:8423494
Keywords
Computer science, Task (project management), Architecture, Knowledge base, Set (abstract data type)
References
- A Probabilistic Model of Redundancy in Information Extraction
- Learning Dictionaries for Information Extraction by Multi-Level Bootstrapping
- Methods for Domain-Independent Information Extraction from the Web: An Experimental Comparison
- Lifelong robot learning
- PRODIGY: an integrated architecture for planning and learning
- Character-level Analysis of Semi-Structured Documents for Set Expansion
- Combining labeled and unlabeled data with co-training
- The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty
- A design for the ICARUS architecture
- Strategies for lifelong knowledge extraction from the web
- Automatic Acquisition of Hyponyms from Large Text Corpora
- Entity Extraction via Ensemble Semantics
- Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
- A Mutually Beneficial Integration of Data Mining and Information Extraction
- Names and Similarities on the Web: Fact Extraction in the Fast Lane
- Guiding Semi-Supervision with Constraint-Driven Learning
- Coupled semi-supervised learning for information extraction
- An integrated theory of the mind.
- SOAR: An Architecture for General Intelligence
- Heterogeneous multitask learning with joint sparsity constraints
Cited by
- Diversifiable Bootstrapping for Acquiring High-Coverage Paraphrase Resource
- Serendipitous learning: learning beyond the predefined label space
- Epistemological Databases for Probabilistic Knowledge Base Construction
- Robust Disambiguation of Named Entities in Text
- Hybrid human-machine vision systems: image annotation using crowds, experts and machines
- Automatic knowledge extraction from documents
- Bootstrapping Biomedical Ontologies for Scientific Text using NELL
- Lifelong Learning of Discriminative Representations
- Relation Acquisition using Word Classes and Partial Patterns
- Towards Distributed MCMC Inference in Probabilistic Knowledge Bases
- Multi-step classification approaches to cumulative citation recommendation
- Autonomously reviewing and validating the knowledge base of a never-ending learning system
- A graph-based approach to commonsense concept extraction and semantic similarity detection
- Mining Tera-Scale Graphs: Theory, Engineering and Discoveries
- Improving Learning and Inference in a Large Knowledge-Base using Latent Syntactic Cues
- An Ontology-Driven Sociomedical Web 3.0 Framework
- Weakly Supervised Training of Semantic Parsers
- Interactive Learning of Relation Extractors with Weak Supervision
- Incorporating Vector Space Similarity in Random Walk Inference over Knowledge Bases
- Parallel and distributed systems for probabilistic reasoning
Related papers
- W・ホッジズによる建築の起源としての洞窟観 : W・ホッジズの「ヒンドゥー、ムーア、ゴシック建築の原型にかんする論文」について
- Architecture as an Art
- Making space for degenerate thinking: revaluing architecture with Friedrich Nietzsche
- Analysis on Academic Earmark of Contemporary Lingnan Architecture School
- On the Base of Educational Knowledge
- Application of Artificial Intelligence in the Construction of Intelligent Knowledge Base