Results 11 to 20 of about 228,482 (264)
Top-Down RST Parsing Utilizing Granularity Levels in Documents
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 Some downstream NLP tasks exploit discourse dependency trees converted from RST trees. To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures.
Naoki Kobayashi +4 more
semanticscholar +4 more sources
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years.
Longyin Zhang +4 more
semanticscholar +5 more sources
A new top-down parsing algorithm for left-recursive DCGs [PDF]
Symposium on Programming Language Implementation and Logic Programming, 1993 In this paper we introduce a new parsing algorithm, called cancellation parsing. Deterministic cancellation parsing with lookahead k can handle the C(k) grammars, which include the LL(k) grammars and are contained in the LC(k) grammars.
Mark-Jan Nederhof
semanticscholar +3 more sources
Parsing macro grammars top down
Information and Control, 1979 A top-down parsing scheme for macro grammars is proposed. It extends the recursive descent method frequently used in context-free parsing. It is shown to be decidable if a macro grammar is top-down parsable. Nearly matching lower and upper bounds for the complexity of the decision procedure are derived.
Kurt Mehlhorn
openalex +4 more sources
Bottom-Up/Top-Down Image Parsing with Attribute Grammar [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008 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
openalex +7 more sources
Deriving lexical and syntactic expectation-based measures for psycholinguistic modeling via incremental top-down parsing [PDF]
Conference on Empirical Methods in Natural Language Processing, 2009 A number of recent publications have made use of the incremental output of stochastic parsers to derive measures of high utility for psycholinguistic modeling, following the work of Hale (2001; 2003; 2006).
Brian Roark +3 more
openalex +2 more sources
Efficient probabilistic top-down and left-corner parsing [PDF]
Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics -, 1999 8 pages, 3 tables, 3 ...
Brian Roark, Mark Johnson
openalex +5 more sources
Top-Down Parsing with Parsing Contexts A Simple Approach to Context-Sensitive Parsing
, 2014 The domain of context-free languages has been extensively explored and there exist numerous techniques for parsing (all or a subset of) context-free languages. Unfortunately, some programming languages are not context-free. Using standard context-free parsing techniques to parse a context-sensitive programming language poses a considerable challenge ...
Jan Kurs, M. Lungu, Oscar Nierstrasz
semanticscholar +5 more sources
A hybrid top-down parsing technique [PDF]
, 1991 0 Recursive descent parsing allows local semantic objects within each grammar rule. These semantic objects are automatically stacked upon recognition of recursive nonterminals. Parsing speed is maximal, as the recognition of a terminal defaults to a simple comparison instruction. The drawbacks are a grammar-dependent static parser size as well as a lot
Heinz Dobler
openalex +4 more sources
Efficient Top-Down BTG Parsing for Machine Translation Preordering [PDF]
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2015 We present an efficient incremental topdown parsing method for preordering based on Bracketing Transduction Grammar (BTG). The BTG-based preordering framework (Neubig et al., 2012) can be applied to any language using only parallel text, but has the problem of computational efficiency.
Tetsuji Nakagawa
openalex +3 more sources