AMR Dependency Parsing with a Typed Semantic Algebra

May 29, 2018 · Entered Twilight · 🏛 Annual Meeting of the Association for Computational Linguistics

"No code URL or promise found in abstract"
"Code repo scraped from project page (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE.txt, README.md, cupy_utils.py, embeddings.py, eval_analogy.py, eval_similarity.py, eval_translation.py, get_data.sh, map_embeddings.py, normalize_embeddings.py

Authors Jonas Groschwitz, Matthias Lindemann, Meaghan Fowlie, Mark Johnson, Alexander Koller arXiv ID 1805.11465 Category cs.CL: Computation & Language Citations 62 Venue Annual Meeting of the Association for Computational Linguistics Repository https://github.com/artetxem/vecmap ⭐ 654 Last Checked 29 days ago

Abstract

We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph. This allows us to use standard neural techniques for supertagging and dependency tree parsing, constrained by a linguistically principled type system. We present two approximative decoding algorithms, which achieve state-of-the-art accuracy and outperform strong baselines.