K. W. Church, "A stochastic parts program and noun phrase parser for unrestricted text," Proceedings of the Second Conference on Applied Natural Language Processing, vol. 136, 1988.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... (for instance [Lau et al. 1993] but have also been applied to optical character recognition [Hull, 1992] and a wide variety of problems in natural language processing including author identification [Mosteller and Wallace, 1964] language identification [Dunning, 1994] part of speech tagging [Church, 1988], text compression [Suen, 1979] and spelling correction [Kukich, 1992] One advantage of using word frequency to detect shifts in topic over merely counting the number of word repetitions is that repetitions of words can be weighted differently depending on their probability. Simply because the ....

Church, K. W. (1988). A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, pages 136--143.

....are also utilized to further evaluate the effectiveness of our database selection algorithm. A side effect of our database representative is that it captures essentially all meaningful 2 word noun phrases completely automatically. Existing noun phrase identification systems (see, for example, [6, 7]) require substantial manual labor to create a tagged corpus. In the Internet environment, there are numerous collections with specialized vocabularies and it is essential that all operations can be carried out automatically. The rest of the paper is organized as follows. In Section 2, related ....

K. Church. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. ANLP-2, 1988.

....system called Candide, which in a 1994 ARPA evaluation [7] performed at about the same level as Pangloss [51] a state of the art system with a long lineage in traditional MT research. This encouraging result, along with successes in other applications such as part of speech tagging [32], led to the widespread adoption of statistical techniques, with the consequence that most research oriented MT systems now comprise at least some statistical components, though pure statistical systems are still probably in the minority. See Hutchins [58] for a much more detailed account of ....

K. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the 2nd Conference on Applied Natural Language Processing (ANLP), Austin, Texas, 1988.

....they can represent the boundaries of syntactic features, such as noun phrases and verb phrases. Boundary markers can be considered invisible tags, or hypertags, which have probabilistic relationships with adjacent tags in the same way that words do. Atwell [21, 1987] introduced this idea. Church [54, 1989] adopted the approach and applied probabilistic principles to phrase and clause structure analysis. By marking the boundaries of features, or constituents, with brackets the probability of a feature occurring in a given context can be calculated from manually prepared training texts. The results ....

K W Church. A stochastic parts program and noun phrase parser for unrestricted text. In ICASSP. Bell Laboratories, 1989.

....measure the tendency of a verb to be followed within a few words by an infinitive, Church uses his statistical disambiguator 2Error rates computed by hand verification of 200 examples for each SF using the tagged mode. These are estimated independently of the error rates for verb detection. 212 (Church, 1988) to distinguish between to as an infinitive marker and to as a preposition. Then he measures the mutual information between occurrences of the verb and occurrences of infinitives following within a certain number of words. Unlike our system, Church s approach does not aim to de cide whether or ....

K. Church. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of the nd A CL Conference on Applied NLP. ACL, 1988.

....trainable, consistent and easy to meet cer tain optimum criteria. They can also provide more objective preference measures for soft re jection. Hence, they are attractive for a large sys tem. The current probabilistic approaches have a wide coverage including lexical analysis [DeRose 88, Church 88] syntactic analysis [Garside 87, Fujisaki 89, Su 88, 89, 9lb] restricted semantic analysis [Church 89, Liu 89, 90] and experimental translation systems [Brown 90] However, there is still no integrated approach for modeling the joint effects of lexical, syntactic and semantic information on ....

Church, K., "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text," ACL Proc. 2nd Conf on Applied Natural Language Processing, pp. 136-143, Austin, Texas, USA, 9-12 Feb. 1988. 183

....and Merialdo, 1986] At first, a relatively small amount of text is manually tagged and used to train a partially accurate model. The model is then used to tag more text, and the tags are manually corrected and then used to retrain the model. Church uses the tagged Brown corpus for training [Church, 1988]. These models involve probabilities for each word in the lexicon, so large tagged corpora are required for reliable estimation. The second method of training does not require a tagged training corpus. In this situation the Baum Welch algorithm (also known as the forward backward algorithm) can ....

....of the Brown corpus [Francis and Kuera, 1982] training on one half of the corpus (about 500,000 words) and tagging the other, 96 of word instances were assigned the correct tag. Eight iterations of training were used. This level of accuracy is comparable to the best achieved by other taggers [Church, 1988, Merialdo, 1991] The Brown Corpus contains fragments and ungrammaticalities, thus providing a good demonstration of robust ness. 5.3 Tunable and Reusable A tagger should be tunable, so that systematic tagging errors and anomalies can be addressed. Similarly, it is important that it be fast ....

K. W. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing (A CL), pages 136-143, 1988.

....inition of anchor (v) reads: to lower an anchor (1 to keep (a ship) from moving . This indicates a reference to sense 1 of the first homograph. Zero affix morphology is also present implicitly, and we conducted an experiment to try to identify instances of it using a probabilistic tagger [2]. The hypothesis is that if the word that s being defined (the definiendum) occurs within the text of its own definition, but occurs with a different part of speech, then it will be an instance of zero affix morphology. The question is: How do we tell whether or not we have an instance of ....

Church K., "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text", in Proceedings of the nd Conference on Applied Natural Language Processing, pp. 136-143, 1988.

.... part of speech taggers, as an alternative to laboriously hand crafting rules for tagging, as was done in the past [Klein and Simmons, 1963; Harris, 1962] Almost all of the work in the area of automatically trained taggers has explored Markov model based part of speech tagging [Jelinek, 1985; Church, 1988; Derose, 1988; DeMarcken, 1990; Cutting et al. 1992; Kupiec, 1992; Chaxniak et al. 1993; Weischedel et al. 1993; Schutze and Singer, 1994; Lin et al. 1994; Elworthy, 1994; Merialdo 1995] 2 For a Markov model based tagger, training consists of learning both lexical probabilities (P(wordltag) ....

Church, K. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, A CL.

....of prod ucts Tagging In order to investigate the role of syntactic information, the texts have been tagged. A tagged version of the English text was supplied by Umist, Manchester. The Dutch version was tagged automatically using a tagger inspired on the En glish tagger described in [Church, 1988]. This tag ger uses as contextual information a trigram model constructed using a previously tagged corpus, viz. the Eindhovense corpus . The system furthermore uses as lexical information a dictionary derived from a subset of the Celex lexical database, which contains information about the ....

K. Church. A stochastic parts pro- gram and noun phrase parser for unrestricted text. In nd Conference on Applied Natural Language Processing (A CL), 1988.

....the syntactic relation of the two words among VO, SV, N J, NN and assigns this label to the sentence. If no such relation is observed, Xtract associates the label U (for undefined) to the sentence. We note labellid] the label associated For this, we use the part of speech tagger described in [Church, 1988]. This program was developed at Bell Labora tories by Ken Church. The parser has been developed at Bell Communication Research by Steve Abney, Cuss stands for Cascaded Analysis of Syntactic Structure. I am much grateful to Steve Abney to help us use and customize Cuss for this work. 280 . ....

K. Church. Stochastic Parts Progra m and Noun Phrase Parser for Unrestricted Text. In Proceedings of the Second Conference on Applied Natural Language Processing, Austin, Texas, 1988.

....system. In contrast, the rules in rule based systems are usually difficult to construct and are typically not very robust. One area in which the statistical approach has done particularly well is automatic part of speech tagging, assigning each word in an input sentence its proper part of speech [Church 88; Cutting et al. 92; DeRose 88; Deroualt and Merialdo 86; Garside et al. 87; Jelinek 85; The author would like to thank Mitch Marcus and Rich Pito for valuable input. This work was supported by DARPA and AFOSR jointly under grant No. AFOSR 90 0066, and by ARO grant No. DAAL 03 89 C0031 PRI. ....

....our results with other published results. In [Meteer et al. 91] an error rate of 3 4 on one domain, Wall Street Journal articles and 5.6 on another domain, texts on terrorism in Latin American countries, is quoted. However, both the domains and the tag set are different from what we use. Church 88] reports an accuracy of 95 99 cor rect, depending on the definition of correct . We implemented a version of the algorithm described by Church. When trained and tested on the same samples used in our experiment, we found the error rate to be about 4.5 . DeRose 88] quotes a 4 error rate; ....

Church, K. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of the Second Conference on Applied Natural Language Processing, ACL, 136-143, 1988.

....to acquire or use inappropriate patterns. This problems is considered very itnportant when dealing with a corpus: it was the reason for the substantial human interven tion in the procedure of [Grishman et al. 1986] and it is the rcasou why other techniques use manually tagged corpora (e.g. [Church 1988]) lu practice, however, we have discovered that tile problem is not so crucial: senantically valid patterns have occurred many more times in syntactically unambiguons constructs than in ambiguous ones. Thns, they could be identified without the need of first disambiguating tile sentences. ....

Church, K. W., A stochastic parts program and noun phrase parser for unrestricted text, ACL Conf. on Applied NLP, 1988.

....frequencies based on a tagged corpus. The method utilizes a tagged corpus because (i) we don t have to deal with a lexical ambiguity (ii) tagged corpora in various domains are becoming readily available and (iii) simple and robust tagging techniques using such corpora recently have been developed ([Church, 1988], Brill, 1992] Brent reports a method for automatically acquiring subcat frames but without fre quency measurements ( Brent and Berwick, 1991] Brent, 1991] His approach is to count occurrences of those unambiguous verb phrases that contain no noun phrases other than pronouns or proper ....

K.W. Church. "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text". In Proceedings of the Second Conference on Applied Natural Language Processing, 1988.

....problem of incorporating the linguistic knowledge into the above statistical model. 1. Introduction The concept of baseNP is initially put forward by Church. In English, baseNP is defined as simple non recursive noun phrases , which means that there is no sub noun phrases contained in a baseNP[1]. But the definition can not meet the needs in Chinese information retrieval. The noun phrases such as ll(natural) J= anguage) t(process) Asian) t(finance) J[ crisis) and (political) system) reformation) process) are critical for information retrieval, but they are not ....

Church K., A stochastic parts program and noun phrase parser for unrestricted text, In: Proceedings of the Second Conference on Applied Natural Language Processing, 1988.

....of probabilities to determine the most likely tag for a word, such as HMMl based or cue based. Using probabilities in tagging is an obvious approach and has been utilised for many decades. First used by Stolz et al. 1965) various stochastic taggers include Marshall (1983) Garside (1987) and Church (1988). HMM taggers have to be trained on previously tagged data in order to calculate the probabilities for tag sequences. Also, it has been demonstrated that with the use of the Expectation Maximisation (EM) algorithm (Dempster et al. 1 977) that stochastic models can be trained on untagged data ....

K. W. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Second Conference on Applied Natural Language Processing, pp. 136-143. ACL. 1988.

....or more internal standard formats, and vice versa, will be essential. 3.2. Tools All MULTEXT tools will be developed according to the principles outlined above. Tile project will use only wellknown, state of the art methods in tool development, in order to ensure the project s feasibility (e.g. [Chur88], Cult921, Gale9 l ] Hirst93] lHirst91] The project will use these methods to produce a set of tools tbat is Ireely available, coherent, extensible, and language iudependent. The totDis will be implemented under UNIX, but will be developed according to principles that will facilitate ....

Church, K. W. (1988). A stochastic parts program and noun phrase parser for unrestricted texts. In Proceedings of the Second Conference on Applied Natural Language Processing. Austin, Texas, 136-143.

....to automatically extract case frames from corpus data, their accuracies do not seem completely satisfactory, and the problem still needs investigation. Manning (1992) for example, proposes extracting case frames by using a finite state parser. His method first uses a statistical tagger (cf. (Church, 1988; Kupiec, 1992; Charniak et al. 1993; Merialdo, 1994; Nagata, 1994; Schutze and Singer, 1994; Brill, 1995; Samuelsson, 1995; Ratnaparkhi, 1996; Haruno and Matsumoto, 1997) to assign a part of speech to each word in the sentences of a corpus. It then uses the finite state parser to parse the ....

Church, Kenneth. W. 1988. A stochastic parts program and noun phrase parser for unrestricted text. Proceedings of the 2nd Conference on Applied Natural Language Processing, pages 136--143.

....will discuss some of these techniques below. Statistical translation models originate in speech processing (see [12] for an overview) where they are used to estimate the probability of an utterance given its phonetic representation. They have been also successfully used in part of speech tagging [7], machine translation [3, 5] information retrieval [4, 20] transliteration [13] and text summarization [14] The reader can refer to [15] for a detailed description of statistical translation models in various applications. In statistical machine translation (SMT) there exist many techniques to ....

K. Church. A stochastic parts program and a noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, Austin, Texas, 1988.

....compression This section describes a probabilistic approach to the compression problem. In particular, we adopt the noisy channel framework that has been successful in a large number of other NLP applications, including speech recognition [14] machine translation [6] partof speech tagging [11], transliteration [17] and information retrieval [4] In this framework, we look at a long string and imagine that (1) it was originally a short string, and then (2) someone added some additional, optional text to it. Compression is a matter of identifying the original short string. It is not ....

K. Church, A stochastic parts program and noun phrase parser for unrestricted text, in: Proceedings of the Second Conference on Applied Natural Language Processing, Austin, TX, 1988, pp. 136--143.

....into supervised and unsupervised learning: Supervised learning is applied when the model is obtained from annotated corpora. Unsupervised learning is applied when the model is obtained from raw corpora training. The most noticeable examples of automatic tagging approaches are Markov chains [Church, 1989, Charniak et al. 1993, Jelinek, 1985, Merialdo, 1994, Garside et al. 1987, Cutting et al. 1992] neural networks [Schmid, 1994] decision trees IDaclemans et al. 1996, Mtrquez and Rodriguez, 1995] and transformation based error driven learning [Brill, 1994] The most widely used methods for ....

Church, K. (1989). A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of ICA$$P.

....with rules that perform aspectual classification directly from clausal constituents. Finally, we plan to compare genetic programming to other machine learning methods for this task. Similar baselines for comparison have been used for many classification problems [6] e.g. part ofspeech tagging [2, 1]. Acknowledgments This research is supported in part by the Columbia University Center for Advanced Technology in High Performance Computing and Communications in Health care (funded by the New York State Science and Technology Foundation) the Office of Naval Research under contract ....

K. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the 2nd Conference for Applied Natural Language Processing, pages 136--143, 1988.

....same phrase structure constraints are applied to speech recognition and natural language understanding. In text based natural language processing, shallow parsing approaches typically identify the syntactic constituents of a sentence. One example is the stochastic tagging procedure designed in [22], which can locate simple noun phrases according to syntactic noun phrase rules. Another example is the Fidditch parser presented in [43] which can be used to produce annotated syntactic phrase structure trees. However, in speech understanding systems, the grammars used can be semantic driven, or ....

K. Church, "A stochastic parts program and noun phrase parser fro unrestricted text," in Proceedings of the Second Conference on Applied Natural Language Processing, Austin, Texas, pp. 136--143, 1988.

....will discuss some of these techniques below. Statistical translation models originate in speech processing (see [12] for an overview) where they are used to estimate the probability of an utterance given its phonetic representation. They have been also successfully used in part of speech tagging [7], machine translation [3, 5] information retrieval [4, 20] transliteration [13] and text summarization [14] The reader can refer to [15] for a detailed description of statistical translation models in various applications. In statistical machine translation (SMT) there exist many techniques to ....

K. Church. A stochastic parts program and a noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, Austin, Texas, 1988.

No context found.

K. W. Church, "A stochastic parts program and noun phrase parser for unrestricted text," Proceedings of the Second Conference on Applied Natural Language Processing, vol. 136, 1988.

No context found.

CHURCH, KENNETH W. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Second Conference on Applied Natural Language Processing, 136--143, Austin, Texas.

No context found.

K. Church. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of Second Conference on Applied Natural Language Processing (ANLP'88), Austin, TX, 1988. 185

No context found.

Church, Kenneth Ward. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Second Conference on Applied Natural Language Processing, Austin, Texas.

No context found.

Church, Kenneth Ward. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Second Conference on Applied Natural Language Processing, pages 136#143, Austin, TX.

No context found.

Church, K. (1988). A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Annual Conference on Applied Natural Language Parsing ACL (pp. 136 --143), Austin, TX.

No context found.

Church, Kenneth Ward. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Second Conference on Applied Natural Language Processing, Austin, Texas.

No context found.

Church, K. "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text." Proceedings of the Second Conference on Applied Natural Language Processing. Austin, Texas, 1989.

No context found.

Church, K.W.: A stochastic parts program and noun phrase parser for unrestricted text. In: ANLP. (1988) 136--143

No context found.

Church, Kenneth. 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, pages 136--143.

No context found.

K. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing (ANLP-88), pages 136-143, Austin, Texas, February 1988. Association for Computational Linguistics.

No context found.

Church, K., 1988. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. Proceedings of the Second Conference on Applied Natural Language Processing. Texas.

No context found.

Church, K., 1988. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, pages 136-143, Austin, Texas.

No context found.

Church, K. (1988) A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of the Second ACL Conference on Applied Natural Language Processing (ANLP 1998), 136-143.

No context found.

K. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, pages 136--143. Association for Computational Linguistics, 1988.

No context found.

Church, K. W., A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Applied Natural Language Conference, pages 136-143, 1988.

No context found.

Church KW. A stochastic parts program and noun phrase parser for unrestricted text. In: Proceedings of the Second Conference on Applied Natural Language Processing; 1988. p. 136--43.

No context found.

K. Church. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of the Second Conference on Applied Natural Language Processing, pages 136--143, Morristown, NJ, 1988. Association for Computational Linguistics.

No context found.

K. W. Church. A stochastic parts program and a noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, Austin, Texas, 1988.

No context found.

Church, K. (1988) A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. Second Conference on Applied Natural Language Processing, ACL.

No context found.

Church, K., "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text," ACL Proc. 2nd Conf on Applied Natural Language Processing, pp. 136-143, Austin, Texas, USA, 9-12 Feb. 1988.

No context found.

Church, K. 1988. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text. In Proceedings of the Second Conference on Applied Natural Language Processing. Austin, Texas.

No context found.

Church, Ken W. (1988). "A stochastic Parts Program and Noun Phrase Parser for Unrestricted Text." In Proceedings of the 2nd Conference on Applied Natural Language Processing (ANLP-88), pp 136- 143, Austin, Texas, USA.

No context found.

Church, K.W., "A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text," in Proceedings of the Second Conference on Applied Natural Language Processing, AUL, 136-143, 1988.

No context found.

K. W. Church. A stochastic parts program and noun phrase parser for unrestricted text. In Proceedings of the Second Conference on Applied Natural Language Processing, pp. 136-143, 1988.

No context found.

Church, Kenneth W. 1988. A stochastic parts program and noun phrase parser for un- restricted text, Proceedings of the Second Conference on Applied Natural Language Pro- cessing, Austin, Texas.

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