paper-with-me

Papers

End-to-end Graph-based TAG Parsing with Neural Networks

2018-04-18 · NAACL 2018 6 · Jungo Kasai, Robert Frank, Pauli Xu, William Merrill, Owen Rambow

We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.

📄 PDF Abstract BibTeX arXiv:1804.06610

Code (1)

jungokasai/graph_parser 공식 구현 tf

Tasks

POSPOS TaggingTAG

Similar Papers 제목 키워드 기반

Graphonomy: Universal Human Parsing via Graph Transfer Learning

2019-04-09 · CVPR 2019 6 · Ke Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen 외

Prior highly-tuned human parsing models tend to fit towards each dataset in a specific domain or with discrepant label granularity, and can hardly be adapted to other human parsing tasks without extensive re-training. In…

Human ParsingTransfer Learning

Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models

2022-07-01 · NAACL (DLG4NLP) 2022 7 · Woo Suk Choi, Yu-Jung Heo, Dharani Punithan, Byoung-Tak Zhang

In this work, we propose the application of abstract meaning representation (AMR) based semantic parsing models to parse textual descriptions of a visual scene into scene graphs, which is the first work to the best of ou…

Abstract Meaning RepresentationAMR ParsingDependency ParsingSemantic Parsing

Coarse-To-Fine Parsing for Expressive Grammar Formalisms

2017-09-01 · WS 2017 9 · Christoph Teichmann, Alex Koller, er, Jonas Groschwitz

We generalize coarse-to-fine parsing to grammar formalisms that are more expressive than PCFGs and/or describe languages of trees or graphs. We evaluate our algorithm on PCFG, PTAG, and graph parsing. While we achieve th…

SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation

2022-10-17 · Woo Suk Choi, Yu-Jung Heo, Byoung-Tak Zhang

Scene graph is structured semantic representation that can be modeled as a form of graph from images and texts. Image-based scene graph generation research has been actively conducted until recently, whereas text-based s…

Abstract Meaning RepresentationDependency ParsingGraph GenerationImage Retrieval+5

Joint Video and Text Parsing for Understanding Events and Answering Queries

2013-08-29 · Kewei Tu, Meng Meng, Mun Wai Lee, Tae Eun Choe 외

We propose a framework for parsing video and text jointly for understanding events and answering user queries. Our framework produces a parse graph that represents the compositional structures of spatial information (obj…

Semantic Parsing