paper-with-me

Papers

Improving Coverage and Runtime Complexity for Exact Inference in Non-Projective Transition-Based Dependency Parsers

2018-04-27 · NAACL 2018 6 · Tianze Shi, Carlos Gómez-Rodríguez, Lillian Lee

We generalize Cohen, G\'omez-Rodr\'iguez, and Satta's (2011) parser to a family of non-projective transition-based dependency parsers allowing polynomial-time exact inference. This includes novel parsers with better coverage than Cohen et al. (2011), and even a variant that reduces time complexity to $O(n^6)$, improving over the known bounds in exact inference for non-projective transition-based parsing. We hope that this piece of theoretical work inspires design of novel transition systems with better coverage and better run-time guarantees. Code available at https://github.com/tzshi/nonproj-dp-variants-naacl2018

📄 PDF Abstract BibTeX arXiv:1804.10615

Code (1)

tzshi/nonproj-dp-variants-naacl2018 공식 구현

Similar Papers 제목 키워드 기반

Efficient Parsing for Head-Split Dependency Trees

2013-01-01 · TACL 2013 1 · Giorgio Satta, Marco Kuhlmann

Head splitting techniques have been successfully exploited to improve the asymptotic runtime of parsing algorithms for projective dependency trees, under the arc-factored model. In this article we extend these techniques…

ARCDependency Parsing

Headed-Span-Based Projective Dependency Parsing

2021-08-10 · ACL 2022 5 · Songlin Yang, Kewei Tu

We propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. …

Constituency ParsingDependency Parsing

Headed-Span-Based Projective Dependency Parsing

2021-09-17 · ACL ARR September 2021 9 · Anonymous

We propose a new paradigm for projective dependency parsing based on headed spans. In a projective dependency tree, the subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. We c…

Dependency Parsingglobal-optimization

LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis

2026-04-22 · Faruk Alpay, Bugra Kilictas arxiv

Structured sequence generation often requires a model to satisfy several input-derived constraints in a single output. Standard decoding methods may assign high probability to fluent continuations while placing low mass …

Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling

2023-08-19 · Jiaqi Yin, Cunxi Yu

Scheduling on dataflow graphs (also known as computation graphs) is an NP-hard problem. The traditional exact methods are limited by runtime complexity, while reinforcement learning (RL) and heuristic-based approaches st…

Combinatorial OptimizationReinforcement Learning (RL)Scheduling