Completed
Discussion Question
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
CMU Multilingual NLP - Dependency Parsing
Automatically move to the next video in the Classroom when playback concludes
- 1 Two Types of Linguistic Structure
- 2 Why Dependencies?
- 3 Universal Dependencies Treebank Standard format for parse trees in many languages
- 4 Adding Inductive Bias to Neural Models • Bias self attention to follow syntax
- 5 Understanding Language Structure Example of extracting morphological agreement rules using dependency relations
- 6 Searching over Parsed Corpora Search using 'syntactic regex'
- 7 Analysis of Other Linguistic Phenomena • Examining power and agency in film scripts
- 8 Arc Standard Shift-Reduce Parsing (Yamada & Matsumoto 2003, Nivre 2003)
- 9 Shift Reduce Example
- 10 Classification for Shift-reduce
- 11 Encoding Stack Configurations w/ RNNS
- 12 Transition-based parsing State embeddings
- 13 (First Order) Graph-based Dependency Parsing
- 14 Graph-based vs. Transition Based
- 15 Chu-Liu-Edmonds (Chu and Liu 1965, Edmonds 1967)
- 16 Find the Best Incoming
- 17 Subtract the Max for Each
- 18 Recursively Call Algorithm
- 19 Expand Nodes and Delete Edge Deleted from cycle
- 20 Sequence Model Feature Extractors (Kipperwasser and Goldberg 2016)
- 21 BiAffine Classifier (Dozat and Manning 2017)
- 22 Difficulty In Multilingual Dependency Parsing
- 23 Example Improvement 1: Order-insensitive Encoders . Standard cross-lingual transfer can fail with large word order differences between source and target Change model structure to be order-insensitive…
- 24 Generative Model Fine-tuning • Use generative model that can be trained unsupervised, and fine-tune on the target language
- 25 Example Improvement 3: Linguistically Informed Constraints • Add constraints based on a priori knowledge of the language structure
- 26 Discussion Question
