Results 11 to 20 of about 66,908 (277)
Dependency parsing with bottom-up Hierarchical Pointer Networks
Information Fusion, 2023 Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications. In particular, left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches for performing dependency parsing.
Daniel Fernández-González +1 more
+7 more sources
Bottom-Up/Top-Down Image Parsing with Attribute Grammar [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009 This paper presents a simple attribute graph grammar as a generative representation for made-made scenes, such as buildings, hallways, kitchens, and living rooms, and studies an effective top-down/bottom-up inference algorithm for parsing images in the process of maximizing a Bayesian posterior probability or equivalently minimizing a description ...
Feng Han, Song-Chun Zhu
openaire +7 more sources
A pipeline model for bottom-up dependency parsing [PDF]
Proceedings of the Tenth Conference on Computational Natural Language Learning - CoNLL-X '06, 2006 We present a new machine learning framework for multi-lingual dependency parsing. The framework uses a linear, pipeline based, bottom-up parsing algorithm, with a look ahead local search that serves to make the local predictions more robust. As shown, the performance of the first generation of this algorithm is promising.
Dan Roth, Ming-Wei Chang, Quang Do
openaire +3 more sources
Noncanonical Extensions of Bottom-Up Parsing Techniques [PDF]
SIAM Journal on Computing, 1976 A bottom-up parsing technique which can make non-leftmost possible reductions in sentential forms is said to be non-canonical. Nearly every existing parsing technique can be extended to a non-canonical method which operates on larger classes of grammars and languages than the original technique.
John H. Williams, Thomas G. Szymanski
openaire +4 more sources
Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks [PDF]
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022 Constituency parsing and nested named entity recognition (NER) are similar tasks since they both aim to predict a collection of nested and non-crossing spans. In this work, we cast nested NER to constituency parsing and propose a novel pointing mechanism for bottom-up parsing to tackle both tasks.
Yang, Songlin, Tu, Kewei
+6 more sources
Faster shift-reduce constituent parsing with a non-binary, bottom-up strategy [PDF]
Artificial Intelligence, 2019 Final peer-reviewed manuscript accepted for ...
Fernández-González, Daniel +1 more
openaire +5 more sources
Bottom-up/top-down image parsing by attribute graph grammar [PDF]
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005 In this paper, we present an attribute graph grammar for image parsing on scenes with man-made objects, such as buildings, hallways, kitchens, and living moms. We choose one class of primitives - 3D planar rectangles projected on images and six graph grammar production rules.
Song-Chun Zhu, Feng Han
openaire +3 more sources
Bottom-Up Recognition and Parsing of the Human Body
2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007 Recognizing humans, estimating their pose and segmenting their body parts are key to high-level image understanding. Because humans are highly articulated, the range of deformations they undergo makes this task extremely challenging. Previous methods have focused largely on heuristics or pairwise part models in approaching this problem.
Jianbo Shi, Praveen Srinivasan
openaire +5 more sources
A new design of prolog-based bottom-up parsing system with Government-Binding theory [PDF]
Proceedings of the 12th conference on Computational linguistics -, 1988 This paper addresses the problems of movement transformation in Prolog-based bottom-up parsing system. Three principles of Government-Binding theory are employed to deal with these problems. They are Empty Category Principle, C-command Principle, and Subjacency Principle. A formalism based upon them is proposed.
I. Peng Lin +2 more
openaire +4 more sources
Efficient disjunctive unification for bottom-up parsing [PDF]
Proceedings of the 13th conference on Computational linguistics -, 1990 This paper describes two novel techniques which, when applied together, in practice significantly reduce the time required for unifying disjunctive feature structures. The first is a safe but fast method for discarding irrelevant disjunctions from newly-created structures.
David Carter
openaire +4 more sources