Results 81 to 90 of about 296,979 (166)

Predicting Discourse Structure using Distant Supervision from Sentiment [PDF]

arXiv, 2019
Discourse parsing could not yet take full advantage of the neural NLP revolution, mostly due to the lack of annotated datasets. We propose a novel approach that uses distant supervision on an auxiliary task (sentiment classification), to generate abundant data for RST-style discourse structure prediction.
arxiv  

User-friendly Support for Common Concepts in a Lightweight Verifier [PDF]

, 2010
Machine verification of formal arguments can only increase our confidence in the correctness of those arguments, but the costs of employing machine verification still outweigh the benefits for some common kinds of formal reasoning activities. As a result,
Lapets, Andrei
core   +1 more source

Automatic Prediction of the Performance of Every Parser [PDF]

arXiv
We present a new parser performance prediction (PPP) model using machine translation performance prediction system (MTPPS), statistically independent of any language or parser, relying only on extrinsic and novel features based on textual, link structural, and bracketing tree structural information.
arxiv  

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy [PDF]

arXiv, 2016
Two extensions to the AMR smatch scoring script are presented. The first extension com-bines the smatch scoring script with the C6.0 rule-based classifier to produce a human-readable report on the error patterns frequency observed in the scored AMR graphs.
arxiv  

Selective Magic HPSG Parsing [PDF]

Proceedings of EACL99, Bergen, Norway, June 8-11, 1999
We propose a parser for constraint-logic grammars implementing HPSG that combines the advantages of dynamic bottom-up and advanced top-down control. The parser allows the user to apply magic compilation to specific constraints in a grammar which as a result can be processed dynamically in a bottom-up and goal-directed fashion. State of the art top-down
arxiv  

Session Type Inference in Haskell

, 2011
We present an inference system for a version of the Pi-calculus in Haskell for the session type proposed by Honda et al. The session type is very useful in checking if the communications are well-behaved.
Agusa, Kiyoshi, Imai, Keigo, Yuen, Shoji
core   +2 more sources

Adapting a general parser to a sublanguage [PDF]

Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP'05) (2005) 89-93, 2006
In this paper, we propose a method to adapt a general parser (Link Parser) to sublanguages, focusing on the parsing of texts in biology. Our main proposal is the use of terminology (identication and analysis of terms) in order to reduce the complexity of the text to be parsed.
arxiv  

Constraint Generation for the Jeeves Privacy Language [PDF]

, 2014
Our goal is to present a completed, semantic formalization of the Jeeves privacy language evaluation engine, based on the original Jeeves constraint semantics defined by Yang et al at POPL12, but sufficiently strong to support a first complete ...
Rose, Eva
core  

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning [PDF]

arXiv, 2019
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept ...
arxiv  

Towards rule-based visual programming of generic visual systems

, 2000
This paper illustrates how the diagram programming language DiaPlan can be used to program visual systems. DiaPlan is a visual rule-based language that is founded on the computational model of graph transformation.
Hoffmann, Berthold, Minas, Mark
core   +3 more sources