| Sleator, D. and D. Temperley, 1991: Parsing english with a link grammar. Tech. rep., CMU. Taskar, B., D. Klein, M. Collins, D. Koller and C. Manning, 2004: Max-margin parsing. in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). Barcelona, Spain. |
....contains linking requirements of words. The words of a syntactic structure are connected in such a way, that the links satisfy the linking requirements for eachword of the sentence (satisfaction) that the links do not cross (planarity) and that all words form a connected graph (connectivity) [12]. For example LinkGrammar provides the following syntactic structure for the sentence The ATM customer inserts the ATM card into the card reader. Xp MVp ....
Sleator, D. D. and Temperley, D., (1991) Parsing English with a Link Grammar, Technical Report CMU-CS-91-196, Carnegie Mellon University,School of Computer Science, Pittsburgh, PA
....Figure 2: example of an index expression These rules are applied recursively up the index expression tree. Note that index expressions are not the only means for representing syntactic structures. Other syntactic representations could also be employed in their place, for example, link grammars [18]. Extended index expressions are syntactic structures used to represent pre semantic context in utterances. The next stage, which involves introducing aspects of semantic context, is the resolution of anaphora. Basic anaphora resolution Anaphora is the co reference of one expression with an ....
Sleator, D. and Temperley, D. Parsing English with Link Grammar. In Proceedings Third International Workshop on Parsing Technologies. 1993. Available: www.link.cs.cmu.edu/link/papers/index.html
....ARCHITECTURE The system initially analyses incoming questions formulated in NL. The architecture of the system is illustrated in Figure 3. The design of the NLP processor is eleborated in Figure 4. As illustrated in Figure 2, the questions are syntactically parsed using the Link Parser [18] and are finally represented by a 3 tuple: a question verb, a focus and a set of modifiers. The 3 tuple representation of the question is similar to the work of [16] in question answering. Once the question is parsed, we map its 3 tuple representation to a metarepresentation of the database ....
....(resource, write, S) Rules for accepted questions: author, who) Rules for the object class: author, name, name) resource, publish date, date) The rules generated by the pre processor are used at the run time by the NLP processor. The NLP processor has been integrated with the Link Parser [18] The user input is tokenized and tagged. The Link Parser finds the possible links between tokens. The NLP processor uses these links to identify the question word, the action verb, the direct object and its determiners. The NLP can also process sentences that start with an imperative verb, as in ....
Sleator D., Davy Temperley, D. (1993) Parsing English with A Link Grammar. Proceedings of the Third Annual Workshop on Parsing Technologies.
....In recent years, much of the parsing literature has focused on so called lexicalized grammars, that is grammars in which each individual rule is specialized for one or more lexical items. Formalisms of this sort include dependency grammar [14] lexicalized tree adjoining grammar [18] link grammar [21], head driven phrase structure grammar [15] tree insertion grammar [19] combinatorial categorial grammar [22] and bilexical grammar [8] Probabilistic lexicalized grammars have also been exploited in state of the art, real world parsers, as reported in [12] 1] 7] 3] 5] and [10] Other ....
D. Sleator and D. Temperley. Parsing english with a link grammar. In Proceedings of the 3 Int. Workshop on Parsing Technologies, Tilburg, Durbuy, Germany, August 1993.
....collection and have the full set of evaluation questions by May 15, 2002. Perform the evaluation and analysis of the system, and prepare the nal manuscript through the summer of 2002. Milestone: Complete the work by August 1, 2002. 5. 1 Tools used We propose to use the Link Grammar Parser [44, 50] as the underlying parsing technology and FramerD [24] for the storage model and the language in which Learner is implemented. Each is described in more detail in Appendices A and B, respectively. 5.2 Natural language processing required There are potentially fascinating ways to apply our ....
D. Sleator and D. Temperley. Parsing English with a link grammar. In Third International Workshop on Parsing Technologies, 1993. Available through: ftp://bobo.link.cs.cmu.edu/pub/sleator/link-grammar/.
....terms (from the referencing node or one of its ancestors) in two sentences, on the average. We have tested the training phase of our method on a sample of 14,500 sentences containing the heading terms. The syntactical analysis has been carried out using the free Link Grammar Parser [10]. Our working hypothesis was that the abovementioned indicative function is, in most cases, conveyed by verbs (and verb phrases) Therefore, in the initial experiments, the verbs that occurred the closest (in the parse tree) to informative terms have been counted, arranged into a frequency table, ....
D. Sleator and D. Temperley, Parsing English with a Link Grammar. In Third International Workshop on Parsing Technologies, August 1993.
....dictionaries, thesauruses or ontologies for the words component. Fig. 1: System architecture 2.2 Details The first task of the structure component is to build a graph representation of the query, preferably as a tree or a lattice. In our implementation, we use the Link Grammar Parser (LGP) [ST93, TSL] for this task. The query is split into sentences by a simple algorithm based on punctuation characters; for each sentence, the LGP provides a set of possible parses. Each parse can be represented as a constituent tree (although this is not the native format of the link grammar) the trees are ....
Sleator, D.; Temperley, D.: Parsing English with a Link Grammar. In: Proc. 3 rd Intl. Workshop on Parsing Technologies, 1993.
....An idiosyncratic behavior of a single word is very likely to go unnoticed for lack of data. This divergence in interest might be the reason why hardly any attempt was made to have a lexicalized grammar learned. In this paper, I will describe an approach to learning a link grammar. Link grammar (Sleator Temperley 1991) is highly lexicalized, and therefore the problem of data sparseness will be immense. As a consequence, I have chosen a fuzzy representation. The fuzziness in this case models uncertainty rather than vagueness inherent in the language. The learning algorithm tries to extract as much information as ....
....learning algorithm tries to extract as much information as possible from a grammar fragment, partial parses provided by this grammar, and wordclass information (for unknown words or to corroborate decision made by the system) 2 . Link Grammar Link grammar (Grinberg, Lafferty Sleator, 1995; Sleator Temperley 1991) is a highly lexical, context free formalism that does not rely on constituent structure. Instead, it models connections between word pairs without building a hierarchical structure. The link grammar formalism is best explained with an example of a linkage (i.e. a link grammar parse) Figure 1 ....
[Article contains additional citation context not shown here]
Sleator, D. & Temperley, D. (1991). Parsing English with a link grammar (Tech. Rep. CMU-CS-91196) . Pittsburgh, PA: Carnegie Mellon University, School of Computer Science.
....System Richard J Cooper and Stefan M Ruger Department of Computing Imperial College of Science, Technology and Medicine 180 Queen s Gate, London SW7 2BZ, England s.rueger doc.ic.ac.uk Abstract. We describe our simple question answering system written in perl that uses the CMU Link parser (Sleator and Temperley 1991), Princeton University s WordNet (Miller 1995) the REX system for XML parsing (Cameron 1998) and the Managing Gigabyte search engine (Witten, Mo#at and Bell 1999) This work is based on an MSc project (Cooper 2000) Introduction The main task of question answering is providing a short answer to ....
Sleator, D. and D. Temperley (1991). Parsing English with a link grammar. Technical Report CMU-CS-91-196, Computer Science, Canegie Mellon University.
....in a speech recognition error rate in the ATIS domain. They did so by parsing the utterances with a CFG to produce a sequence of grammatical fragments of various types, then constructing a trigram of fragment types to supplant the standard ngram. Link grammar is a lexicalized grammar proposed by [43]. Each word is associated with one or more ordered sets of typed links; each such link must be connected to a similarly typed link of another word in the sentence. A legal parse consists of satisfying all links in the sentence via a planar graph. Link grammar has the same expressive power as a ....
Danny Sleator and Davy Temperley. Parsing English with a link grammar. Technical Report CMU-CS-91196, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, October 1991.
No context found.
D. Sleator and D. Temperley. Parsing English with a Link Grammar. Technical report CMUCS -91-196, Department of Computer Science, Carnegie Mellon University, 1991.
No context found.
Sleator, D. and D. Temperley, 1991: Parsing english with a link grammar. Tech. rep., CMU. Taskar, B., D. Klein, M. Collins, D. Koller and C. Manning, 2004: Max-margin parsing. in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). Barcelona, Spain.
No context found.
Sleator, D. D., & Temperley, D. (1993). Parsing English with a link grammar. Third International Workshop on Parsing Technologies.
No context found.
D. Sleator and D. Temperley. Parsing English with a Link Grammar. Technical report, Carnegie Mellon University, 1991.
No context found.
Sleator, Daniel and Davy Temperley. 1993. "Parsing English with a Link Grammar". Third International Workshop on Parsing Technologies, Tilburg, The Netherlands and Durbuy, Belgium.
No context found.
D. Sleator and D. Temperley. Parsing English with a link grammar. In International Workshop on Parsing Technologies, 1993.
No context found.
D. Sleator and D. Temperley, "Parsing English with a Link Grammar," CMU-CS-91-196, Tech. Rep., 1991.
No context found.
D. Sleator and D. Temperley. 1993. Parsing English with a Link Grammar. In Proceedings, Third International Workshop on Parsing Technologies, pp. 277--292.
No context found.
D. D. Sleator and D. Temperley. Parsing English with a link grammar. In Third International Workshop on Parsing Technologies, 1993.
No context found.
Slater, D. and Temperley, D., 1998. Parsing English with a link grammar. Technical report, School of Computer Science, Carnegie Mellon University.
No context found.
D. D. Sleator and D. Temperley. Parsing English with a link grammar. In Third International Workshop on Parsing Technologies, 1993.
No context found.
D. Sleator and D. Temperley. Parsing english with a link grammar. Technical Report CMU-CS-91-196, Computer Science, Carnegie Mellon University, October 1991.
No context found.
D. D. K. Sleator and D. Temperley, "Parsing English with a Link Grammar," School of Computer Science Carnegie Mellon University, Pitsburg, PA CMU-CS-91-196, October 1991.
No context found.
Sleator, D. D. and Temperley, D., (1991) Parsing English with a Link Grammar, Technical Report CMU-CS-91-196, Carnegie Mellon University, School of Computer Science, Pittsburgh, PA
No context found.
D. Sleator, D. Temperley, Parsing English with a Link Grammar, Third International Workshop on Parsing Technologies, August 1993.
First 50 documents Next 50
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC