Getting More Out Of Syntax with PropS

Abstract

Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences. Yet, while much semantic structure is indeed expressed by syntax, many phenomena are not easily read out of dependency trees, often leading to further ad-hoc heuristic post-processing or to information loss. To directly address the needs of semantic applications, we present PropS -- an output representation designed to explicitly and uniformly express much of the proposition structure which is implied from syntax, and an associated tool for extracting it from dependency trees.

Cited by in corpus (14)

• Graphene: Semantically-Linked Propositions in Open Information Extraction
• Summarizing Unstructured Logs in Online Services
• A Survey on Open Information Extraction
• Span Model for Open Information Extraction on Accurate Corpus
• Context-Preserving Text Simplification
• Semantic Hypergraphs
• Better Highlighting: Creating Sub-Sentence Summary Highlights
• Dependency-based Hybrid Trees for Semantic Parsing
• Learning Open Information Extraction of Implicit Relations from Reading Comprehension Datasets
• Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
• Syntactic and Semantic-driven Learning for Open Information Extraction
• Improving Open Information Extraction via Iterative Rank-Aware Learning
• Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
• Content Differences in Syntactic and Semantic Representations