Weischedel, Ralph, Marie Meteer, Richard Schwartz, Lance Ramshaw, and Jeff Palmucci. 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19(2):359--382, June.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....in an unsegmented corpus, even if it includes unknown words. This is achieved by introducing an explicit statistical model of unknown words, and by using an N best word segmentation algorithm (Nagata, 1994) as an approximation of the generalized ForwardBackward algorithm. In English taggers, (Weischedel et al. 1993) proposed a statistical model to estimate word out put probability p(w i]li) for an unknown word from spelling information such as infiectional endings, derivational endings, hyphenation, and capitalization. Our word model can be thought of a generalization of their statistical model. One ....

Ralph Weischedel, Marie Meteer, Richard Schwartz, Lance Ramshaw, and Jeff Palmucci. 1993. Coping with Ambiguity and Unknown Words through Probabilistic Models, in Computational Linguistics, Vol.19, No.2, pages 359-382. Computers are increasingly getting connected through data couunication such as satellites and

.... 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) and contextual probabilities (P(tagiltagi 1 . tagi n) Once trained, a sentence can be tagged by searching for ....

....tagi n) Once trained, a sentence can be tagged by searching for the tag sequence that mayAmizes the product of lexical and contextual probabilities. The most accurate stochastic taggers use estimates of lexical and contextual proba bilities extracted from large manually annotated corpora (e.g. [Weischedel et al. 1993; Charniak et al. 1993] It is possible to use unsupervised learning to train stochastic taggers without the need for a manually annotated corpus by using the Baum Welch al gorithm [Banm, 1972; Jelinek, 1985; Cutting et al. 1992; Kupiec, 1992; Elworthy, 1994; Merialdo, 1995] This algorithm ....

[Article contains additional citation context not shown here]

Weischedel, R.; Meteer, M.; Schwartz, R.; Ramshaw, L.; and Pal- mucci, J. 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics. 13

....of a pivot letter in a word, for instance the letter in excise. Choosing a fixed number of letters around the pivot might be a solution. Sequences of two letters (bigrams) or three letters (trigrams) are often chosen as the basis for learning methods (e.g. probabilistic part of speech tagging [4]) But it seems that often enough more context may be necessary; e.g. eme is generally accented as me at the end of a word (emphysme, quatrime) whereas it is accented as eme when followed by an n (arrachement, infarcissement) Besides, the relevant context around the pivot letter may extend both ....

Weischedel R, Meeter M, Schwartz R, Ramshaw L, and Palmucci J. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics 1993;19(2):359--82. Special Issue on Using Large Corpora: II.

....and semantic knowledge, yet there are surprisingly few resources available for lexical semantic information. In contrast, a variety of dictionaries and computational tools are available for acquiring syntactic information (e.g. Brill 1994; Church 1989; Marcus, Santorini, Marcinkiewicz 1993; Weischedel et al. 1993)) Ideally, one would like to have a semantic knowledge base that contains semantic representations of all words, phrases, and concepts in the language. Given the vast scope of human knowledge and the practical limitations of manual knowledge engineering, it is unrealistic to expect a complete ....

....predefined seed words. The only additional knowledge used by our system is a part of speech dictionary for syntactic segmentation. We used a hand crafted part of speech dictionary for these experiments, but statistical and corpus based taggers are widely available (e.g. Brill 1994; Church 1989; Weischedel et al. 1993)) One other relevant piece of related research is Roark and Charniak s work (Roark Charniak 1998) which improves upon preliminary results that we reported in (Riloff Shepherd 1997) Roark and Charniak confirmed our intuition that conjunctions, appositives, lists, and compound nouns can help ....

Weischedel, R.; Meteer, M.; Schwartz, R.; Ramshaw, L.; and Palmucci, J. 1993. Coping with Ambiguity and Unknown Words through Probabilistic Models. Computational Linguistics 19(2):359--382.

.... 1994, Magerman 1994, O Donoghue 1993, Schabes, Roth and Osborne 1993, Sekine and Grishman 1995) semantic analysis or word sense tagging (mapping word sequences onto semantic tags or meaning analyses) e.g. Demetriou 1993, Demetriou and Atwell 1994, 2001, Bod et al. 1996, Kuhn and de Mori 1994, Weischedel et al. 1993, Wilson and Rayson 1993, Wilson and Leech 1993, Jost and Atwell 1993) Machine Translation (mapping a source language word sequence onto a target language word sequence) e.g. Brown et al. 1990, Berger et al. 1994, Gale and Church 1993) speech to text recognition (mapping a speech signal onto ....

Weischedel R, Meteer M, Schwarz R, Ramshaw L, Palmucci J 1993 Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics 19(2): 359-382.

....applications including text based information retrieval, speech recognition, and text to speech synthesis. The POS tagging has been usually performed by statistical (or data corpus driven) approaches mainly using hidden markov model (HMM) Church, 1988, Cutting et al. 1992, 1 Kupiec, 1992, Weischedel et al. 1993] However, since statistical approaches only consider the neighboring tags within a limited window (usually two or three) sometimes the decision cannot cover all the linguistic rules necessary for the disambiguation. Also the approaches are inappropriate for the idiomatic expressions in which ....

R. Weischedel, R. Scewartz, J. Ralmucci, M. Meteer, and L. Rawshaw. Coping with ambiguity and unknown words through probabilistic model. Computational linguitics, 19(2):359--382, 1993. 10

.... never far above 97 (i.e. about 3 of error) with an average ambiguity level of around 16 , it means that almost 20 of the ambiguities were attributed a wrong tag We attempted to set a confidence threshold, so that for similarly weighted transitions, the system would keep the ambiguity, as in (Weischedel and al. 1993), but results were not satisfying. 2.2 Constraint based systems We also looked at more powerful principlebased parsers, and tests were conducted on 2 The first one using this expression was maybe M. Marcus, lately we can find a quite similar idea in Silberztein (1997) 111 Token Lemma Lexical ....

Weischedel, Ralph and M. Meeler and R. Shwartz and L. Ramshaw and J. Palmucci, 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19(2):359--382.

....PR (r i j r i 1 ; p; h; w h ) e.g. 5) PR (NP j BEGIN ;V P; V BD; caught) 3 The word feature is a vector of orthographic and morphological features of the word and is computed deterministically at run time. The inclusion of the word feature in the BBN model was due to the work described in (Weischedel et al. 1993), where word features helped reduce part of speech ambiguity for unknown words. 4 That is, p will denote the single nonterminal that forms the LHS of a rule (the parent constituent) h will denote the head nonterminal of the RHS of a rule and l i and r i will denote left and right modi er ....

R. Weischedel, M. Meteer, R. Schwartz, L. Ramshaw, and J. Palmucci. 1993. Coping with ambiguity and unknown words through probabilistic methods. Computational Linguistics, 19(2):359382.

....and sometimes difficult, though the payoffs are often significant. General purpose text annotations, such as part of speech tags and noun phrase bracketing, are costly to obtain but have wide applicability and have been used successfully to develop statistical NLP systems (e.g. Church, 1989; Weischedel et al. 1993 ] Domain specific text annotations, however, require a domain expert and have much narrower applicability. From a practical perspective, it is important to consider the human factor and to try to minimize the amount of time and effort required to build a training corpus. Domain specific text ....

Weischedel, R.; Meteer, M.; Schwartz, R.; Ramshaw, L.; and Palmucci, J. 1993. Coping with Ambiguity and Unknown Words through Probabilistic Models. Computational Linguistics 19(2):359--382.

....more templates, including templates like if one of the three previous tags is A . Brill s results demonstrate that this approach can outperform the Hidden Markov Model approaches that are frequently used for part of speech tagging (Jelinek, 1985; Church, 1988; DeRose, 1988; Cutting et al. 1992; Weischedel et al. 1993), as well as showing promise for other applications. The resulting model, encoded as a list of rules, is also typically more compact and for some purposes more easily interpretable than a table of HMM probabilities. An Incremental Algorithm It is worthwhile noting first that it is possible in ....

Weischedel, Ralph, Marie Meteer, Richard Schwartz, Lance Ramshaw, and Jeff Palmucci. 1993. Coping with ambiguity and unknown words through probabilistic methods. Computational Linguistics, 19(2):359--382.

No context found.

Weischedel, Ralph, Marie Meteer, Richard Schwartz, Lance Ramshaw, and Jeff Palmucci. 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19(2):359--382, June.

No context found.

Weischedel, Ralph, Marie Meteer, Richard Schwartz, Lance Ramshaw, and Je# Palmucci. 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19#2#:359#382, June.

No context found.

Ralph Weischedel, Richard Schwartz, Jeff Palmucci, Marie Meteer, and Lance Ramshaw. 1993. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, Special Issue on Using Large Corpora, 19(2):361--382, June.

No context found.

R. Weischedel, M. Meter, R. Schwartz, L. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19(2):359-382, 1993. 5

No context found.

R. Weischedel, M. Meteer, R. Schwartz, L. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown words through probabilistic models. Association for Computational Linguistics, 19(2):359--382, 1993.

No context found.

R. Weischedel, M. Meteer, R. Schwartz, L. A. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown word through probabilistic models. Computational Linguistics, 19(2):359--382, 1993.

No context found.

R. Weischedel, M. Meteer, R. Schwartz, L. A. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown word through probabilistic models. Computational Linguistics, 19(2):359--382, 1993.

No context found.

Weischedel R, Meteer M, Schwartz R, Ramshaw L, Palmucci J. Coping with ambiguity and unknown words through probabilistic models. Comput Linguist 1993;19(2):359--82.

No context found.

Weischedel, R., R. Schwartz, J. Palmucci, M. Meteer, and L. Ramshaw, 1993. Coping with Ambiguity and Unknown Words through Probabilistic Models. Computational Linguistics, 19(2). 36

No context found.

R. Weischedel, M. Meteer, R. Schwartz, L. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown words through probabilistic methods. Computational Linguistics, 19(2):359--382, 1993.

No context found.

Weischedel, R., Meteer, M., Schwartz, R., Ramshaw, L., and Palmucci, J. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics 19, 2 (1993), 359-382. 157

No context found.

Ralph Weischedel, Richard Schwartz, Jeff Palmucci, Marie Meteer, and Lance Ramshaw. Coping with Ambiguity and Unknown Words through Probabilistic Models. Computational Linguistics, 19(2):359 -- 382, 1993.

No context found.

Weischedel, R., Meteer, M., Schwartz, R., Ramshaw, L., and Palmucci, J. 1993. "Coping with Ambiguity and Unknown Words Through Probabilistic Models." ComputationM Linguistics, 19(2):359-382.

No context found.

R. Weischedel, M. Meteer, R. Schwartz, L. Ramshaw, and J. Palmucci. Coping with ambiguity and unknown words through probabilistic models. Computational Linguistics, 19(2):359--382, 1993.

No context found.

Ralph Weischedel, Marie Meteer, Richard Schwartz, Lance Ramshaw & Jeff Palmucci, "Coping with ambiguity and unknown words through probabilistic models," Computational Linguistics 19 (1993), 359--382.

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