By Bonnie Jean Dorr
This publication describes a singular, cross-linguistic method of computing device translation that solves convinced sessions of syntactic and lexical divergences through technique of a lexical conceptual constitution that may be composed and decomposed in language-specific methods. This strategy permits the translator to function uniformly throughout many languages, whereas nonetheless accounting for wisdom that's particular to every language.The translation version can be utilized to map a source-language sentence to a target-language sentence in a principled style. it's equipped at the foundation of a parametric technique, making it effortless to alter from one language to a different (by atmosphere syntactic switches for every language and delivering lexical descriptions for every one language) with no need to write down a complete new processor for every language.Dorr's strategy advances the sector of desktop translation in a couple of very important methods: it offers a uniform processor during which a similar syntactic and lexical-semantic processing modules are used for every language; it truly is interlingual, in a position to derive an underlying language-independent type of the resource language that permits any of the 3 goal languages - Spanish, English, or German - to be made from this type; and it describes a scientific mapping among the lexical-semantic point and the syntactic point that enables the perfect target-language phrases to be chosen and discovered, regardless of the potential of syntactic and lexical divergences.Bonnie Jean Dorr is Assistant Professor within the laptop technology division on the collage of Maryland.
Read or Download Machine translation : a view from the lexicon PDF
Best intelligence & semantics books
An Introduction to Computational Learning Theory
Emphasizing problems with computational potency, Michael Kearns and Umesh Vazirani introduce a few critical subject matters in computational studying idea for researchers and scholars in man made intelligence, neural networks, theoretical computing device technology, and data. Computational studying idea is a brand new and quickly increasing quarter of study that examines formal versions of induction with the pursuits of researching the typical tools underlying effective studying algorithms and making a choice on the computational impediments to studying.
Minimum Error Entropy Classification
This e-book explains the minimal errors entropy (MEE) proposal utilized to facts class machines. Theoretical effects at the internal workings of the MEE inspiration, in its program to fixing various category difficulties, are offered within the wider realm of chance functionals. Researchers and practitioners additionally locate within the e-book a close presentation of functional information classifiers utilizing MEE.
Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms
A very good development calls for a powerful beginning. This publication teaches easy synthetic Intelligence algorithms similar to dimensionality, distance metrics, clustering, errors calculation, hill mountain climbing, Nelder Mead, and linear regression. those aren't simply foundational algorithms for the remainder of the sequence, yet are very priceless of their personal correct.
Advances in Personalized Web-Based Education
This e-book goals to supply vital information regarding adaptivity in computer-based and/or web-based academic platforms. to be able to make the scholar modeling strategy transparent, a literature overview touching on pupil modeling recommendations and techniques in past times decade is gifted in a distinct bankruptcy.
- Elements of Quantum Computing: History, Theories and Engineering Applications
- Fuzzy Logic in Control
- Learning and Reinforcement
- Communicating Process Architectures 2011: WoTUG-33
Extra resources for Machine translation : a view from the lexicon
Example text
3 These rules are derived on the b asis of information associated with the LeS for the word put as described in chapt e r 4. The algorith m for parsing a source- langu age sentence is conceptually simple . Essentially, the words of the input, Wi ... Wn, are read left to right. As the Earley parser scans a word Wi, a set of word-level con straints are applied. An example of such a constraint is the subcatego rization test mentioned above. Similarly, as the Earley parser predicts ( i. , builds ) and completes (i.
16. Note that John is the highest left-most conceptual constituent in this representation, but the subject of the sentence is I . ST. ( - l O) � PHYS . (>- lO) Figure 1 . 1 5 The CD representation for Mary died indicates that Mary changed into a "very bad physical state" ( i. e . , dead ) . The CD representation for John killed Mary indicates that John caused this state to come about. John l¢=>LOC(M) fool n I pO SS -B Y Figure 1 . 1 6 The CD Representation / believe John is a fool indicates that the conceptualization John is a fool is located in the memory of / .
The current approach strives to fill what I truly believe to be a serious gap in many existing approaches to machine translation, namely that of 22 This remark was v irt u al ly the only positive comment given in t h e entire book review, and no elaboration was given on this point . Regarding the rest of the review, 1 may not be so quick to agree on his point that the framework has resulted in no serious computer program; 1 believe this to be a matter of opinion. (I i m agi ne that � an'y other r esea c;he s m i ght di s agr e e as well, e .