Published Jan 8, 2018

46 - Parsing with Traces, with Jonathan Kummerfeld

Jonathan Kummerfeld delves into advanced parsing techniques that capture traces and null elements, enhancing NLP applications like information extraction and machine translation. Through the exploration of graph-based and syntax-focused parsing systems, he evaluates the ongoing challenges and trade-offs in achieving accuracy and efficiency in sentence structure analysis.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

91 - (Executable) Semantic Parsing, with Jonathan Berant
Answers 383 questions
05 - Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Answers 383 questions
22 - Deep Multitask Learning for Semantic Dependency Parsing, with Noah Smith
Answers 383 questions
04 - Recurrent Neural Network Grammars, with Chris Dyer
Answers 383 questions
25 - Neural Semantic Parsing over Multiple Knowledge-bases
Answers 383 questions
38 - A Corpus of Natural Language for Visual Reasoning, with Alane Suhr
Answers 383 questions
49 - A Joint Sequential and Relational Model for Frame-Semantic Parsing, with Bishan Yang
Answers 383 questions
124 - Semantic Machines and Task-Oriented Dialog, with Jayant Krishnamurthy and Hao Fang
Answers 383 questions
116 - Grounded Language Understanding, with Yonatan Bisk
Answers 383 questions
83 - Knowledge Base Construction, with Sebastian Riedel
Answers 383 questions
27 - What do Neural Machine Translation Models Learn about Morphology?, with Yonatan Belinkov
Answers 383 questions
10 - A Syntactic Neural Model for General-Purpose Code Generation
Answers 383 questions
34 - Translating Neuralese, with Jacob Andreas
Answers 383 questions
44 - Truly Low Resource NLP, with Anders Søgaard
Answers 383 questions
16 - Arc-swift: A Novel Transition System for Dependency Parsing
Answers 383 questions

Dexa/NLP Highlights

46 - Parsing with Traces, with Jonathan Kummerfeld

Topics covered

Popular Clips

Parsing Challenges

Parsing Decisions Impact

Graph Structures Explained

Recovering Sentence Structure

Structure vs. Neural Models

Embracing Rejection

Parsing Challenges

Graph-Based Parsing

Parsing Performance Insights

Conjunctions in NLP

Parsing Structures Explained

Syntax Debate Revisited

One Endpoint Crossing

Episode Highlights

Application Benefits

Graph-Based Parsing

Parsing Challenges

Syntax and Traces

Related Episodes

91 - (Executable) Semantic Parsing, with Jonathan Berant

05 - Transition-Based Dependency Parsing with Stack Long Short-Term Memory

22 - Deep Multitask Learning for Semantic Dependency Parsing, with Noah Smith

04 - Recurrent Neural Network Grammars, with Chris Dyer

25 - Neural Semantic Parsing over Multiple Knowledge-bases

38 - A Corpus of Natural Language for Visual Reasoning, with Alane Suhr

49 - A Joint Sequential and Relational Model for Frame-Semantic Parsing, with Bishan Yang

124 - Semantic Machines and Task-Oriented Dialog, with Jayant Krishnamurthy and Hao Fang

116 - Grounded Language Understanding, with Yonatan Bisk

83 - Knowledge Base Construction, with Sebastian Riedel

27 - What do Neural Machine Translation Models Learn about Morphology?, with Yonatan Belinkov

10 - A Syntactic Neural Model for General-Purpose Code Generation

34 - Translating Neuralese, with Jacob Andreas

44 - Truly Low Resource NLP, with Anders Søgaard

16 - Arc-swift: A Novel Transition System for Dependency Parsing

46 - Parsing with Traces, with Jonathan Kummerfeld

Topics covered

Popular Clips

Episode Highlights

Application BenefitsJonathan Kummerfeld explores how parsing techniques that capture traces and null elements can enhance information extraction and machine translation. These methods address challenges in sentence structure, improving accuracy and efficiency in various NLP tasks.

Application Benefits

Graph-Based ParsingJonathan Kummerfeld explores the intricacies of graph-based parsing, focusing on capturing traces and null elements in sentence structures. His work emphasizes the importance of handling these elements to improve parsing accuracy and flexibility.

Graph-Based Parsing

Parsing ChallengesJonathan Kummerfeld explores the intricate balance between coverage and accuracy in parsing algorithms, focusing on the challenges posed by null elements. He compares various systems, highlighting the trade-offs and performance metrics that define current parsing methodologies.

Parsing Challenges

Syntax and TracesJonathan Kummerfeld explores the significance of traces in parsing algorithms and their impact on understanding sentence structure. He discusses the ongoing debate about the necessity of syntactic structures in NLP amidst the rise of neural network models.

Syntax and Traces

Related Episodes