Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
arXiv:1706.09528
Abstract
We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates. Built using an extension to the segmental RNN that emphasizes recall, our basic system achieves competitive performance without any calls to a syntactic parser. We then introduce a method that uses phrase-syntactic annotations from the Penn Treebank during training only, through a multitask objective; no parsing is required at training or test time. This "syntactic scaffold" offers a cheaper alternative to traditional syntactic pipelining, and achieves state-of-the-art performance.
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- DyNet: The Dynamic Neural Network Toolkit
- A Decomposable Attention Model for Natural Language Inference
- Segmental Recurrent Neural Networks for End-to-end Speech Recognition
- Adversarial Multi-Criteria Learning for Chinese Word Segmentation
- Deep Multitask Learning for Semantic Dependency Parsing
- Neural Semantic Role Labeling with Dependency Path Embeddings
Cited by in corpus (23)
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
- Automatic extraction of materials and properties from superconductors scientific literature
- A Crowdsourced Frame Disambiguation Corpus with Ambiguity
- Does Data Augmentation Improve Generalization in NLP?
- A Double-Graph Based Framework for Frame Semantic Parsing
- Targeted Syntactic Evaluation of Language Models
- Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks
- Syntactic Scaffolds for Semantic Structures
- Learning Joint Semantic Parsers from Disjoint Data
- VASTA: A Vision and Language-assisted Smartphone Task Automation System
- MAVEN: A Massive General Domain Event Detection Dataset
- Open-Domain Frame Semantic Parsing Using Transformers
- Positional Attention-based Frame Identification with BERT: A Deep Learning Approach to Target Disambiguation and Semantic Frame Selection
- A Span Selection Model for Semantic Role Labeling
- Dixit: Interactive Visual Storytelling via Term Manipulation
- Kicktionary-LOME: A Domain-Specific Multilingual Frame Semantic Parsing Model for Football Language
- Knowledge-Enriched Visual Storytelling
- Knowledge Authoring with Factual English
- Semantic Frame Forecast
- A Graph-Based Neural Model for End-to-End Frame Semantic Parsing
- Plot and Rework: Modeling Storylines for Visual Storytelling
- Assessing Semantic Frames to Support Program Comprehension Activities
- Sister Help: Data Augmentation for Frame-Semantic Role Labeling