Syntactic Scaffolds for Semantic Structures

2018/08/30 by Swabha Swayamdipta, Swayamdipta, Swabha, Sam Thomson +9 · 7 citations
Computer Science · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Coreference #FOS: Computer and information sciences #Frame (networking) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Natural language processing #Parsing #Programming language #Resolution (logic) #Semantic role labeling #Semantics (computer science) #Sentence #Syntactic structure #Syntax #Topic Modeling #Treebank #cs.CL

paper · pdf · doi:10.48550/arxiv.1808.10485

published in arXiv (Cornell University) (Cornell University) · Accepted at EMNLP 2018

arxiv created 2018/08/30 · openalex publication_date 2018/08/30 · arxiv updated 2018/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08

Abstract

We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a treebank during training, through a multitask objective. We improve over strong baselines on PropBank semantics, frame semantics, and coreference resolution, achieving competitive performance on all three tasks.

Citations

• Learning to Map Sentences to Logical Form: Structured Classification\n with Probabilistic Categorial Grammars
• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Adversarial Multi-Criteria Learning for Chinese Word Segmentation
• Deep Multitask Learning for Semantic Dependency Parsing
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Learning Joint Semantic Parsers from Disjoint Data

Related

• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Retrofitting Structure-aware Transformer Language Model for End Tasks
• Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach
• Parsing All: Syntax and Semantics, Dependencies and Spans
• Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs