Completed
Problem w/ Weakly Supervised Learning: Spurious Logical Forms . Sometimes you can get the right answer without actually doing the generalizable thing (Guu et al. 2017)
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2018 - Neural Semantic Parsing
Automatically move to the next video in the Classroom when playback concludes
- 1 Tree Structures of Syntax
- 2 Representations of Semantics
- 3 Meaning Representations
- 4 Example Special-purpose Representations
- 5 Example Query Tasks
- 6 Example Command and Control Tasks
- 7 Example Code Generation Tasks
- 8 A Better Attempt: Tree-based Parsing Models • Generate from top-down using hierarchical sequence- to-sequence model (Dong and Lapata 2016)
- 9 Code Generation: Handling Syntax • Code also has syntax, e.g. in form of Abstract Syntax Trees
- 10 Problem w/ Weakly Supervised Learning: Spurious Logical Forms . Sometimes you can get the right answer without actually doing the generalizable thing (Guu et al. 2017)
- 11 Meaning Representation Desiderata (Jurafsky and Martin 17.1)
- 12 First-order Logic
- 13 Abstract Meaning Representation (Banarescu et al. 2013)
- 14 Other Formalisms
- 15 Parsing to Graph Structures
- 16 Linearization for Graph Structures (Konstas et al. 2017)
- 17 CCG and CCG Parsing
- 18 Neural Module Networks: Soft Syntax-driven Semantics (Andreas et al. 2016) . Standard syntax semantic interfaces use symbolic representations . It is also possible to use syntax to guide structure of…
- 19 Neural Models for Semantic Role Labeling . Simple model w/ deep highway LSTM tagger works well (Le et al. 2017)