Universal Machine Learning Methods for Detecting and Temporal Anchoring of Events
Explore this paper's citation graph
Summary
An extensive evaluation of an architecture that is based on bidirectional long short-term memory networks (BiLSTM) and conditional random fields (CRF) and its individual components and parameters is provided and an automatic system that uses a decision tree with convolutional neural networks as local classifiers is proposed.
- Type
- dissertation
- Published
- 2018-01-01
- Cited by
- 1
- References
- 105
- Access
- Open access
- OpenAlex
- https://openalex.org/W2908944636
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:57663467
Keywords
Computer science, Automatic summarization, Event (particle physics), Artificial intelligence, Machine learning
References
- ADADELTA: An Adaptive Learning Rate Method
- Temporal information in newswire articles : an annotation scheme and corpus study
- An Empirical Investigation of Statistical Significance in NLP
- Learning representations by back-propagating errors
- ModeS TimeBank: A Modern Spanish TimeBank Corpus
- Efficient Estimation of Word Representations in Vector Space
- TRIPS and TRIOS System for TempEval-2: Extracting Temporal Information from Text
- Building a Large Annotated Corpus of English: The Penn Treebank
- On the difficulty of training recurrent neural networks
- Bidirectional LSTM-CRF Models for Sequence Tagging
- Learning to rank search results for time-sensitive queries
- On the individuation of events
- SemEval-2007 Task 15: TempEval Temporal Relation Identification
- Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network
- Jointly Combining Implicit Constraints Improves Temporal Ordering
- Long Short-Term Memory
- Inducing Temporal Graphs
- FRAME SEMANTICS AND THE NATURE OF LANGUAGE *
- The Syntax of Event Structure
- Heuristics of instability and stabilization in model selection
Cited by
Related papers
- How Far Can We Go with Data Selection? A Case Study on Semantic Sequence Tagging Tasks
- Idest: Learning a Distributed Representation for Event Patterns
- Improving the Effectiveness of Information Extraction from Biomedical Text
- Towards Practical Active Learning for Classification
- A feature-free and parameter-light multi-task clustering framework
- Diverse Complexity Measures for Dataset Curation in Self-Driving