The Experts below are selected from a list of 17298 Experts worldwide ranked by ideXlab platform
Christopher D Manning - One of the best experts on this subject based on the ideXlab platform.
-
a fast unified model for parsing and sentence understanding
arXiv: Computation and Language, 2016Co-Authors: Samuel R Bowman, Christopher D Manning, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christopher PottsAbstract:Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two key technical problems that make them slow and unwieldy for large-scale NLP tasks: they usually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducing the Stack-augmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single tree-sequence hybrid model by integrating tree-structured sentence interpretation into the linear sequential structure of a shift-reduce parser. Our model supports batched computation for a speedup of up to 25 times over other tree-structured models, and its integrated parser can operate on unparsed data with little loss in accuracy. We evaluate it on the Stanford NLI entailment task and show that it significantly outperforms other sentence-encoding models.
-
a fast unified model for parsing and sentence understanding
Meeting of the Association for Computational Linguistics, 2016Co-Authors: Samuel R Bowman, Christopher D Manning, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christopher PottsAbstract:Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suer from two key technical problems that make them slow and unwieldyforlarge-scaleNLPtasks: theyusually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducingtheStack-augmentedParser-Interpreter NeuralNetwork(SPINN),whichcombines parsing and interpretation within a single tree-sequence hybrid model by integrating tree-structured sentence interpretation into the linear sequential structure of a shiftreduceparser. Ourmodelsupportsbatched computation for a speedup of up to 25◊ over other tree-structured models, and its integrated parser can operate on unparsed data with little loss in accuracy. We evaluate it on the Stanford NLI entailment task and show that it significantly outperforms other sentence-encoding models.
-
a fast and accurate dependency parser using neural networks
Empirical Methods in Natural Language Processing, 2014Co-Authors: Danqi Chen, Christopher D ManningAbstract:Almost all current dependency parsers classify based on millions of sparse indicator features. Not only do these features generalize poorly, but the cost of feature computation restricts parsing speed significantly. In this work, we propose a novel way of learning a neural network classifier for use in a greedy, transition-based dependency parser. Because this classifier learns and uses just a small number of dense features, it can work very fast, while achieving an about 2% improvement in unlabeled and labeled attachment scores on both English and Chinese datasets. Concretely, our parser is able to parse more than 1000 sentences per second at 92.2% unlabeled attachment score on the English Penn Treebank.
-
Generating typed dependency parses from phrase structure parses
Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC 2006), 2006Co-Authors: Marie-catherine De Marneffe, Bill Maccartney, Christopher D ManningAbstract:This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be critical in real-world applications, many NP relations are included in the set of grammatical relations used. We provide a comparison of our system with Minipar and the Link parser. The typed dependency extraction facility described here is integrated in the Stanford Parser, available for download.
Bernd Bohnet - One of the best experts on this subject based on the ideXlab platform.
-
stacking of dependency and phrase structure parsers
International Conference on Computational Linguistics, 2012Co-Authors: Richard Farkas, Bernd BohnetAbstract:We investigate the stacking of dependency and phrase structure parsers, i.e. we define features from the output of a phrase structure parser for a dependency parser and vice versa. Our features are based on the original form of the external parses and we also compare this approach to converting phrase structures to dependencies then applying standard stacking on the converted output. The proposed method provides high accuracy gains for both phrase structure and dependency parsing. With the features derived from the phrase structures, we achieved a gain of 0.89 percentage points over a state-of-the-art parser and reach 93.95 UAS, which is the highest reported accuracy score on dependency parsing of the Penn Treebank. The phrase structure parser obtains 91.72 F-score with the features derived from the dependency trees, and this is also competitive with the best reported PARSEVAL scores for the Penn Treebank.
Richard Farkas - One of the best experts on this subject based on the ideXlab platform.
-
stacking of dependency and phrase structure parsers
International Conference on Computational Linguistics, 2012Co-Authors: Richard Farkas, Bernd BohnetAbstract:We investigate the stacking of dependency and phrase structure parsers, i.e. we define features from the output of a phrase structure parser for a dependency parser and vice versa. Our features are based on the original form of the external parses and we also compare this approach to converting phrase structures to dependencies then applying standard stacking on the converted output. The proposed method provides high accuracy gains for both phrase structure and dependency parsing. With the features derived from the phrase structures, we achieved a gain of 0.89 percentage points over a state-of-the-art parser and reach 93.95 UAS, which is the highest reported accuracy score on dependency parsing of the Penn Treebank. The phrase structure parser obtains 91.72 F-score with the features derived from the dependency trees, and this is also competitive with the best reported PARSEVAL scores for the Penn Treebank.
Helmut Prendinger - One of the best experts on this subject based on the ideXlab platform.
-
hilda a discourse parser using support vector machine classification
Dialogue & Discourse, 2010Co-Authors: Hugo Hernault, Helmut Prendinger, David A Duverle, Mitsuru IshizukaAbstract:Discourse structures have a central role in several computational tasks, such as question-answering or dialogue generation. In particular, the framework of the Rhetorical Structure Theory (RST) offers a sound formalism for hierarchical text organization. In this article, we present HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification. SVM classifiers are trained and applied to discourse segmentation and relation labeling. By combining labeling with a greedy bottom-up tree building approach, we are able to create accurate discourse trees in linear time complexity. Importantly, our parser can parse entire texts, whereas the publicly available parser SPADE (Soricut and Marcu 2003) is limited to sentence level analysis. HILDA outperforms other discourse parsers for tree structure construction and discourse relation labeling. For the discourse parsing task, our system reaches 78.3% of the performance level of human annotators. Compared to a state-of-the-art rule-based discourse parser, our system achieves an performance increase of 11.6%.
-
a novel discourse parser based on support vector machine classification
International Joint Conference on Natural Language Processing, 2009Co-Authors: David A Duverle, Helmut PrendingerAbstract:This paper introduces a new algorithm to parse discourse within the framework of Rhetorical Structure Theory (RST). Our method is based on recent advances in the field of statistical machine learning (multivariate capabilities of Support Vector Machines) and a rich feature space. RST offers a formal framework for hierarchical text organization with strong applications in discourse analysis and text generation. We demonstrate automated annotation of a text with RST hierarchically organised relations, with results comparable to those achieved by specially trained human annotators. Using a rich set of shallow lexical, syntactic and structural features from the input text, our parser achieves, in linear time, 73.9% of professional annotators' human agreement F-score. The parser is 5% to 12% more accurate than current state-of-the-art parsers.
Joao Saraiva - One of the best experts on this subject based on the ideXlab platform.
-
expressing disambiguation filters as combinators
ACM Symposium on Applied Computing, 2020Co-Authors: Jose Nuno Macedo, Joao SaraivaAbstract:Contrarily to most conventional programming languages where certain symbols are used so as to create non-ambiguous grammars, most recent programming languages allow ambiguity. These ambiguities are solved using disambiguation rules, which dictate how the software that parses these languages should behave when faced with ambiguities. Such rules are highly efficient but come with some limitations - they cannot be further modified, their behaviour is hidden, and changing them implies re-building a parser. We propose a different approach for disambiguation. A set of disambiguation filters (expressed as combinators) are provided, and disambiguation can be achieved by composing combinators. New combinators can be created and, by having the disambiguation step separated from the parsing step, disambiguation rules can be changed without modifying the parser.
