Notes:
Parse selection, also known as disambiguation or parsing, is the process of choosing the most likely parse or interpretation for a sentence in natural language. This is a challenging problem in natural language processing, because a single sentence can often have multiple possible parses, depending on factors such as word order, context, and ambiguities in the language.
To perform parse selection, a natural language processing system typically uses a combination of linguistic knowledge, statistical models, and other algorithms to evaluate and compare the different possible parses for a sentence. For example, the system may use grammatical rules and vocabulary to identify the syntactic structure of a sentence, and may use statistical models trained on large corpora of language data to estimate the likelihood of each parse based on how common it is in the language. The system may also use additional information, such as the context of the sentence or the intended meaning of the text, to disambiguate between multiple possible parses.
Overall, parse selection is an essential component of natural language processing systems, as it allows the system to accurately interpret and understand the meaning of sentences in natural language. It is a complex and ongoing research area in the field of artificial intelligence and computational linguistics.
See also:
Ensemble-based Active Learning for Parse Selection. M Osborne, J Baldridge – HLT-NAACL, 2004 – acl.ldc.upenn.edu Abstract Supervised estimation methods are widely seen as being superior to semi and fully unsupervised methods. However, supervised methods crucially rely upon training sets that need to be manually annotated. This can be very expensive, especially when skilled … Cited by 50 Related articles All 15 versions Cite Save More
The leaf projection path view of parse trees: Exploring string kernels for HPSG parse selection K Toutanova, P Markova, C Manning – Proceedings of EMNLP, 2004 – acl.ldc.upenn.edu Abstract We present a novel representation of parse trees as lists of paths (leaf projection paths) from leaves to the top level of the tree. This representation allows us to achieve significantly higher accuracy in the task of HPSG parse selection than standard models, … Cited by 39 Related articles All 25 versions Cite Save More
Exploiting semantic information for HPSG parse selection S Fujita, F Bond, S Oepen, T Tanaka – Research on Language and …, 2010 – Springer Abstract In this article, we investigate the use of semantic information in parse selection. We show that fully disambiguated sense-based semantic features smoothed using ontological information are effective for parse selection. Training and testing was undertaken using … Cited by 25 Related articles All 30 versions Cite Save
Active learning and logarithmic opinion pools for HPSG parse selection J Baldridge, M Osborne – Natural Language Engineering, 2008 – Cambridge Univ Press Abstract For complex tasks such as parse selection, the creation of labelled training sets can be extremely costly. Resource-efficient schemes for creating informative labelled material must therefore be considered. We investigate the relationship between two broad … Cited by 19 Related articles All 6 versions Cite Save
Partial parse selection for robust deep processing Y Zhang, V Kordoni, E Fitzgerald – … of the Workshop on Deep Linguistic …, 2007 – dl.acm.org Abstract This paper presents an approach to partial parse selection for robust deep processing. The work is based on a bottom-up chart parser for HPSG parsing. Following the definition of partial parses in (Kasper et al., 1999), different partial parse selection … Cited by 16 Related articles All 22 versions Cite Save
A comparison of structural correspondence learning and self-training for discriminative parse selection B Plank – Proceedings of the NAACL HLT 2009 Workshop on …, 2009 – dl.acm.org Abstract This paper evaluates two semi-supervised techniques for the adaptation of a parse selection model to Wikipedia domains. The techniques examined are Structural Correspondence Learning (SCL)(Blitzer et al., 2006) and Self-training (Abney, 2007; … Cited by 8 Related articles All 15 versions Cite Save
Unsupervised parse selection for HPSG R Dridan, T Baldwin – Proceedings of the 2010 Conference on Empirical …, 2010 – dl.acm.org Abstract Parser disambiguation with precision grammars generally takes place via statistical ranking of the parse yield of the grammar using a supervised parse selection model. In the standard process, the parse selection model is trained over a hand-disambiguated … Cited by 6 Related articles All 14 versions Cite Save
Parse selection with a German HPSG grammar B Crysmann – Proceedings of the Workshop on Parsing German, 2008 – dl.acm.org Abstract We report on some recent parse selection experiments carried out with GG, a large- scale HPSG grammar for German. Using a manually disambiguated treebank derived from the Verbmobil corpus, we achieve over 81% exact match accuracy compared to a 21.4% … Cited by 3 Related articles All 9 versions Cite Save
Ensemblebased active learning for parse selection J Baldridge, M Osborne – … of the 5th Conference of the …, 2004 – homepages.inf.ed.ac.uk … Baldridge and Osborne Active Learning December 15, 2003 Page 11. 10 Parse selection: 1 • A conditional log-linear model: P(t | s,Mk) = 1 Z(s) exp( n ? … Active Learning December 15, 2003 Page 12. 11 Parse selection: 2 • Product model: P(t | s,M1,…,Mn) = ?n 1=1 P(t | s,Mi) Z … Cited by 2 Related articles All 2 versions Cite Save More
Treeblazing: Using External Treebanks to Filter Parse Forests for Parse Selection and Treebanking. A MacKinlay, R Dridan, D Flickinger, S Oepen… – IJCNLP, 2011 – folk.uio.no Abstract We describe “treeblazing”, a method of using annotations from the GENIA treebank to constrain a parse forest from an HPSG parser. Combining this with self-training, we show significant dependency score improvements in a task of adaptation to the biomedical … Cited by 2 Related articles All 10 versions Cite Save More
Stochastic parse tree selection for an existing rbmt system C Federmann, S Hunsicker – Proceedings of the Sixth Workshop on …, 2011 – dl.acm.org … alleged NO NST persecution $ PNCT . Figure 2: Improved analysis tree resulting from stochastic parse selection good indication of which trees lead to good transla- tions, as is depicted in Table 1. Still, in many cases an alternative tree would have lead to a better trans- lation. … Cited by 8 Related articles All 12 versions Cite Save
Cross-domain effects on parse selection for precision grammars A MacKinlay, R Dridan, D Flickinger… – Research on Language …, 2010 – Springer Abstract We examine the impact of domain on parse selection accuracy, in the context of precision HPSG parsing using the English Resource Grammar, using two training corpora and four test corpora and evaluating using exact tree matches as well as dependency F- … Cited by 2 Related articles All 16 versions Cite Save
Using Lexical and Compositional Semantics to Improve HPSG Parse Selection Z Pozen – 2013 – digital.lib.washington.edu Accurate parse ranking is essential for deep linguistic processing applications and is one of the classic problems for academic research in NLP. Despite significant advances, there remains a big need for improvement, especially for domains where gold-standard training … Cited by 1 Related articles All 2 versions Cite Save
Extrinsic parse selection D Goss-Grubbs – Proceedings of the NAACL HLT 2010 Student …, 2010 – dl.acm.org Abstract This paper reports on one aspect of Locutus, a natural language interface to databases (NLIDB) which uses the output of a high-precision broad-coverage grammar to build semantic representations and ultimately SQL queries. Rather than selecting just a … Related articles All 6 versions Cite Save
[BOOK] Parse Selection with Support Vector Machines FD Borges – 2010 – dissertations.ub.rug.nl Abstract EN The goal of our research was to apply SVMs (Support Vector Machines) to the problem of parse selection. More specifically, to the parse trees produced by Alpino, and to compare its performance with the current Alpino disambiguation component, which is … Cite Save More
Precision-biased Parsing and High-Quality Parse Selection Y Goldberg, M Elhadad – arXiv preprint arXiv:1205.4387, 2012 – arxiv.org Abstract: We introduce precision-biased parsing: a parsing task which favors precision over recall by allowing the parser to abstain from decisions deemed uncertain. We focus on dependency-parsing and present an ensemble method which is capable of assigning … Related articles All 3 versions Cite Save
Parsing of partially bracketed structures for parse selection MJ Nederhof, R Sánchez-Sáez – … of the 12th International Conference on …, 2011 – dl.acm.org Abstract We consider the problem of parsing a sentence that is partially annotated with information about where phrases start and end. The application domain is interactive parse selection with probabilistic grammars. It is explained that the main obstacle is spurious … Related articles All 12 versions Cite Save
Wide Coverage Parse Selection with log-linear Models R Malouf, G van Noord – odur.let.rug.nl Alpino is a wide-coverage computational analyzer of Dutch which aims at accurate, full, parsing of unrestricted text. For English, tremendous progress has been made in the area of wide-coverage parsing of unrestricted text. Many of the proposed systems are statistical … Related articles All 6 versions Cite Save More