Search results
Jump to navigation
Jump to search
Page title matches
- 6 KB (838 words) - 17:47, 25 July 2012
- 5 KB (620 words) - 12:21, 27 July 2012
Page text matches
- ...mmatical and other transformations between the two languages involved, and lexical data for the part-of-speech tagger, which is in charge of the disambiguatio ...nd keep only the bilingual data (lexical selection, bilingual transfer and transfer rules) in the "pair" directory.50 KB (7,915 words) - 00:04, 10 March 2019
- Writing transfer rules seems to be tricky. People generally understand the basic concepts, b ...ion in the target language morphological generator. This means that if the transfer needs some information about the available forms of a particular word, e.g.28 KB (4,478 words) - 12:25, 17 March 2022
- analysis of Apertium) and in the transfer and generation, the transducers from The design is based on the classic transfer architecture of machine translation,58 KB (8,964 words) - 11:11, 14 May 2016
- ...is, the dictionary is used in the direction Left/right. 'surface form' -> 'lexical unit'. ...('lemma') and tags for all matches (lemma and tags together are called a 'lexical unit').29 KB (4,687 words) - 16:28, 5 June 2020
- ...the initial developer. It is another developer, full beginner for writing transfer rules who chose to do that. The examples given are the first rules written ...ool ''apertium-transfer''. Writing tags used for [[chunking]] in a 3-stage transfer is not approached there.58 KB (8,365 words) - 20:16, 26 June 2018
- ...s with [[lexical selection]], for more information on the topic, see the [[lexical selection|main page]].'' the question of lexical selection becomes significant, because there11 KB (1,814 words) - 03:22, 9 March 2019
- ...is, and show how basic (that is, single level) morphological and syntactic transfer rules can be made in Apertium. ...atures they share, and how they are distinguished. When working on shallow-transfer machine translation, we can consider for example, both morphological contra16 KB (2,303 words) - 08:22, 10 May 2013
- ...is, and show how basic (that is, single level) morphological and syntactic transfer rules can be made in Apertium. ...atures they share, and how they are distinguished. When working on shallow-transfer machine translation, we can consider for example, both morphological contra16 KB (2,303 words) - 10:57, 30 October 2015
- ...is, and show how basic (that is, single level) morphological and syntactic transfer rules can be made in Apertium. ...atures they share, and how they are distinguished. When working on shallow-transfer machine translation, we can consider for example, both morphological contra16 KB (2,302 words) - 12:00, 31 January 2012
- There are two main issues with transfer in this case, the first is re-ordering, from <code>OVS → SVO</code>, the ...hat like the chunking available in Apertium (see [[Chunking]]), however no transfer takes place, it just groups words into chunks. The grammar is quite familia26 KB (4,167 words) - 13:05, 11 May 2016
- [[A long introduction to transfer rules|In English]] == Transfert lexical et transfert de structure ==27 KB (4,440 words) - 14:51, 7 October 2014
- ...ransfer module is necessary. This session describes the Apertium 3+ level transfer system which was designed to allow easier treatment of longer patterns, and ===Chunking-based transfer===14 KB (1,969 words) - 12:00, 31 January 2012
- ...ransfer module is necessary. This session describes the Apertium 3+ level transfer system which was designed to allow easier treatment of longer patterns, and ===Chunking-based transfer===14 KB (1,975 words) - 08:36, 10 May 2013
- ...ransfer module is necessary. This session describes the Apertium 3+ level transfer system which was designed to allow easier treatment of longer patterns, and ===Chunking-based transfer===14 KB (1,975 words) - 10:58, 30 October 2015
- ==Lexical transfer== The first stage of transfer is lexical transfer. This is where we take the tree that we have just constructed, and we trans53 KB (8,811 words) - 04:05, 21 January 2017
- ...and lexical selection. The theory section will cover some details of why a transfer lexicon (or bilingual dictionary) cannot always be just correspondences bet ...the second is marking in the entries features which need to be inferred by transfer rules. For example, choosing the most frequent translation of the Chuvash w13 KB (2,056 words) - 10:56, 30 October 2015
- ...and lexical selection. The theory section will cover some details of why a transfer lexicon (or bilingual dictionary) cannot always be just correspondences bet ...the second is marking in the entries features which need to be inferred by transfer rules. For example, choosing the most frequent translation of the Chuvash w13 KB (2,053 words) - 12:00, 31 January 2012
- ...and lexical selection. The theory section will cover some details of why a transfer lexicon (or bilingual dictionary) cannot always be just correspondences bet ...the second is marking in the entries features which need to be inferred by transfer rules. For example, choosing the most frequent translation of the Chuvash w13 KB (2,056 words) - 08:20, 10 May 2013
- ...as dictionaries, bilingual dictionaries, grammars and rules and structural transfer files. RBMT systems consist of an engine (coding and decoding), data (lingu ...with possessives, proclitics, enclitics, ordinals, superlatives, etc.) and lexical selection. It would be better to spend more time on apertium cat>srd that i21 KB (3,171 words) - 14:34, 3 April 2017
- ...on and lexical selection, and [[lttoolbox]]/apertium modules for the rest. Transfer is four-stage [[chunking]]. The pipeline looks like this: pretransfer | lt-proc (lexical transfer) | cg-proc (lexical selection) |\16 KB (2,604 words) - 19:42, 17 April 2018
- ...n the dictionaries, introduce lexical selection rules and create some more transfer rules, a low WER can be reached. ...guese, but also for Italian) and the introduction of a few more structural transfer rules. In any case, I am totally open to suggestions and will be happy to t16 KB (2,285 words) - 06:46, 12 April 2019
- ===Transfer=== Transfer-based machine translation works by first converting the source language to12 KB (1,464 words) - 12:00, 31 January 2012
- ===Transfer=== Transfer-based machine translation works by first converting the source language to11 KB (1,519 words) - 06:51, 11 May 2013
- ===Transfer=== Transfer-based machine translation works by first converting the source language to11 KB (1,519 words) - 18:27, 16 October 2015
- ...do full syntactic parsing, the rules are typically operations on groups of lexical units, rather than operations on parse trees. ...ent of gender, number, etc. The rules can also be used to insert or delete lexical items, as will be described later. These files are:36 KB (5,933 words) - 16:14, 22 February 2021
- '''Lexical selection''' is the task of choosing, given several source-language (SL) tr This page has some links to pages about lexical selection in Apertium.4 KB (625 words) - 08:36, 29 April 2015
- | [[Lexical form]] | [[Lexical unit]]13 KB (1,601 words) - 23:31, 23 July 2021
- !colspan="2"| lexical transfer !colspan="2"| lexical selection6 KB (873 words) - 14:35, 28 July 2020
- ...he [[pipeline]]: In the '''Anaphora Resolution module''' and the in the '''Transfer''' stage. ...or in the Anaphora Resolution module and select the correct pronoun in the Transfer stage.20 KB (3,107 words) - 21:13, 24 June 2022
- ...age for [[Ideas_for_Google_Summer_of_Code/Weighted_transfer_rules|Weighted transfer rules project]] conducted by [[User:Nikita Medyankin|Nikita Medyankin]] at ...e takes exclusive precedence and blocks out all its ambiguous peers during transfer precompilation stage.9 KB (1,387 words) - 13:37, 23 August 2016
- '''apertium-lex-tools''' provides a module for compiling lexical selection rules and processing them in the pipeline. Rules can be manually ==Lexical transfer in the pipeline==19 KB (2,820 words) - 15:26, 11 April 2023
- * Write new transfer rules * Write constraint-based lexical selection8 KB (1,094 words) - 13:10, 14 April 2019
- | rationale = Apertium-separable is a newish module to process lexical items with discontinguous dependencies, an area where Apertium has traditio ...n two existing language modules, focusing on the dictionary and structural transfer23 KB (3,198 words) - 09:15, 4 March 2024
- ...it just expands an {{sc|sl}} dictionary, and runs each possibly analysed [[lexical form]] through all the translation stages to see that for each possible inp ...-quality language pair also needs testvoc on phrases consisting of several lexical units. Often one can find a lot of the errors by running a large corpus (wi9 KB (1,400 words) - 22:30, 18 January 2021
- ...formatting / superblanks interacts with word/chunk reordering in Apertium. Transfer rules can reorder words, but never look at the tags themselves, and have no ...in the input to a transfer rule are always output before the output that a transfer rule gives; so a <p> will never be moved around by a rule.8 KB (1,364 words) - 12:15, 14 May 2017
- ** write lexical selection to generate "yesh-" forms from "any-" forms in negatives or "bir" ***lexical selection for "anything" as "yeshnarse" for negative sentences and as "bir20 KB (2,856 words) - 06:26, 27 May 2021
- |title=expand coverage of Kyrgyz to English structural transfer ...bilingual dictionary is not fully (or correctly) parsed by the <tt>kir-eng-transfer</tt> Apertium mode. Determine what rule(s) need(s) to be added (or fixed)32 KB (4,862 words) - 06:23, 5 December 2019
- === Lexical Selection === ...xt level of problem, once you've chosen the correct morphological form, is lexical selection. The sort of problem this best solves is when you have one stem10 KB (1,615 words) - 07:43, 20 December 2015
- ...rules is detected in the source language text, Apertium will follow these transfer rules to create a grammatical translation in the target language. If this works, great! We move on to the next section: The addition of transfer rules.19 KB (3,164 words) - 20:58, 2 April 2021
- Missing or incorrect Disambiguation and Lexical Selection rules often cause the wrong word to be translated. Problems in d === Lexical Selection ===5 KB (903 words) - 11:57, 26 September 2016
- Missing or incorrect Disambiguation and Lexical Selection rules often cause the wrong word to be translated. Problems in d === Lexical Selection ===6 KB (900 words) - 19:45, 2 December 2013
- ...transfer rule to an existing language pair and test that it works. [[/Add transfer rule|Read more]]... || [[User:Mlforcada]] [[User:ilnar.salimzyan]] [[User: ...selection quality of a pair and test them to ensure that they work. [[/Add lexical-select rules|Read more]]... || [[User:Mlforcada]], [[User:Francis Tyers]]68 KB (10,323 words) - 15:37, 25 October 2014
- * Write documentation on the current status of transfer rules * Write documentation on the current status of transfer rules5 KB (506 words) - 14:56, 28 August 2017
- ...s with [[lexical selection]], for more information on the topic, see the [[lexical selection|main page]].'' ...anguage or a constraint grammar it is possible to do '''limited rule-based lexical selection'''.7 KB (1,057 words) - 21:07, 1 December 2013
- ...e ''cantábamos'' would be <code>cantar.vblex.pii.p1.pl</code> (''cantar'', lexical verb, imperfect indicative, 1st person, plural). ...ode>pl.n.kitabu</code>, ''natural'' meaning that in this way, morphemes in lexical forms would be in the same order as in surface forms, and one could use thi6 KB (935 words) - 13:49, 21 August 2018
- ...an="6"| [[Helsinki Apertium Workshop/Session 4|4: Lexical transfer]] || '''Practical''': Dictionary work .../p/apertium/svn/branches/courses/helsinki_2013/slides/session4.pdf Lexical transfer]8 KB (720 words) - 15:18, 20 March 2015
- ...khimova.pdf Study of the problem of creating structural transfer rules and lexical selection for the Kazakh-Russian machine translation system on Apertium pla ...ers/turklang2015-amirova.pdf Choosing the model for solving the problem of lexical selection for English-Kazakh language pair in the free/open-source platform33 KB (4,418 words) - 11:52, 29 December 2021
- Based on a system of transfer rules and dictionaries written in markup language, Apertium is a platform t ...ng as a spell protractor, provided us with a consistent base data from the lexical point of view in the LSC and a valid model for the creation and assignment7 KB (1,110 words) - 11:34, 23 August 2016
- '''Transfer rules (English to Catalan):''' 221 (T1X), 60 (T2X), 38 (T3X) '''Transfer rules (Catalan to English):''' 97 (T1X), 28 (T2X), 9 (T3X)7 KB (973 words) - 21:38, 9 May 2018
- ==Transfer== There are 51 structural transfer rules that take Crimean Tatar constructions and turn them into their Turkis4 KB (551 words) - 23:52, 28 August 2017
- ...por substantivoj. Transiraj regulaj dosieroj havas siajn proprajn DTD-on (transfer.dtd) kiujn oni povas trovi en la Apertium-a enpako. Se vi bezonas krei regu <transfer>34 KB (5,392 words) - 07:13, 16 February 2015
- ....af-en.t1x || Afrikaans—English first stage transfer file (transfer) |apertium-en-af.af-en.t2x || Afrikaans—English second stage transfer file (interchunk)5 KB (583 words) - 11:17, 18 November 2013
- #* <pre>after disambiguation and pre-transfer: ^coffee# with milk<n><sg>$</pre> #* <pre>after disambiguation and pre-transfer: ^coffee# with milk<n><pl>$</pre>21 KB (3,521 words) - 05:17, 10 December 2017
- For no er dette gjort med ein spesiell kategori ngen_time_meas i transfer; sidan regelen for ngen_time_meas kjem først i fila, prøver me ikkje meir ...practical problems come when trying to integrate this with disambiguation, transfer and generation in Apertium.13 KB (2,051 words) - 10:24, 22 September 2010
- * word-sense / lexical selection ambiguity ==Word-Sense / Lexical Selection ambiguity==4 KB (620 words) - 18:06, 26 September 2016
- ...s should only appear escaped in the input stream unless they are part of a lexical unit, chunk or superblank. ...e characters <code>^</code> and <code>$</code> are reserved for delimiting lexical units6 KB (797 words) - 07:12, 29 March 2022
- First a little overview of how 3-stage transfer normally works: * Transfer stage: Words are translated using the bidix and categorized and put into ch15 KB (2,237 words) - 12:41, 21 August 2015
- .../sub> → ^(lexical_unit)$ || Pops 'N' values from the stack, creates a lexical unit ^...$ with them and pushes the lu back onto the stack | lu-count || - || N/A || [empty] → number || Pushes the number of lexical units (words inside the chunk) in the rule onto the stack14 KB (2,020 words) - 13:58, 7 October 2014
- === [[sme-smn sátneválljen|Sátneválljen (Lexical selection)]] === === [[Errors in the North Saami transfer component|Transfer]] ===3 KB (557 words) - 12:11, 31 March 2017
- This page describes how to generate lexical selection rules without relying on a parallel corpus. *** <code>-multi</code> which is all the modules after lexical transfer (see apertium-mk-en/modes.xml)12 KB (1,634 words) - 18:26, 26 September 2016
- ...ds. For further information, you can consult the [[How to get started with lexical selection rules|getting started guide]]. || [[User:Francis Tyers|Francis Ty ...ies to a transfer lexicon of your choice. This will involve adding lexical transfer entries, which consist of a translation, and its corresponding grammatical14 KB (2,007 words) - 03:06, 27 October 2013
- .... Consider the following example: we can see that for each source language lexical form, there is a corresponding entry in the bilingual dictionary. ...ode>#</code> mark errors in the lexical transfer, and in the morphological transfer/generation respectively.18 KB (2,490 words) - 12:00, 31 January 2012
- .... Consider the following example: we can see that for each source language lexical form, there is a corresponding entry in the bilingual dictionary. ...ode>#</code> mark errors in the lexical transfer, and in the morphological transfer/generation respectively.18 KB (2,493 words) - 08:39, 10 May 2013
- .... Consider the following example: we can see that for each source language lexical form, there is a corresponding entry in the bilingual dictionary. ...ode>#</code> mark errors in the lexical transfer, and in the morphological transfer/generation respectively.18 KB (2,493 words) - 10:59, 30 October 2015
- ...uages. The project consisted mainly of building a bilingual bidix, writing transfer and disambiguation rules and enriching the Uyghur morphological analyzer. ==Transfer==5 KB (607 words) - 13:25, 12 August 2018
- ==Lexical transfer in the pipeline== ...to apply to input. Also, it will need to be able to handle the output of transfer. —[[User:Firespeaker|Firespeaker]] ([[User talk:Firespeaker|talk]]) 00:015 KB (2,420 words) - 18:54, 2 May 2024
- ...s (plural-ergative) so that no election is made until the word reaches the transfer module. But this would cause that the morphological analysis is not complet ...te forms unless a def-mult element is defined in the tagger with 2 or more lexical forms.11 KB (1,758 words) - 13:22, 10 December 2010
- ...uzkas evit an anvioù-kadarn. Restroù DTD eo ar restroù reolennoù treuzkas (transfer.dtd) a c'haller kaout e pakad Apertium. Mar fell deoc'h enplementañ ur reo <transfer>35 KB (5,602 words) - 07:14, 16 February 2015
- ...ags and words with different lexical meanings based on the grammatical and lexical context. CG rules work both for disambiguation within one part of speech an The rules of '''lexical selection''' are needed when one word has different meaning depending on it9 KB (1,370 words) - 13:58, 23 August 2016
- At the moment Apertium transfer rules are combinations of fixed-length patterns and actions. Conflicts are Transfer rules:5 KB (804 words) - 11:54, 9 March 2017
- ===Transfer rules=== ...fferent transfer stages, and the code is quite convoluted. Work related to transfer rules has focused on code updates to ensure everything is applied correctly5 KB (887 words) - 22:24, 31 August 2017
- .... A lint tester would help people write standard code for dictionaries and transfer files. ...ol should at least check [[lttoolbox]] (dix) dictionary data, perhaps also transfer rules. The [[Apertium New Language Pair HOWTO]] should introduce most of th5 KB (789 words) - 10:36, 31 May 2016
- This states that if a lexical unit has a target-language <code><mf></code> tag and a rule tries to replac ==== Literal Lexical Units ====32 KB (5,012 words) - 13:27, 6 September 2023
- ..."|Friday<br/>(6th October) || 10:00 — 12:00 || Lexical transfer | 14:00 — 18:00 || Lexical transfer3 KB (329 words) - 19:16, 13 November 2015
- ===Lexical selection rules=== The translator has 274 lexical selection rules. These are rules that choose between two or more possible t9 KB (1,306 words) - 15:56, 2 September 2017
- # fix tags of "be" in transfer # transfer rules to get tags from beAdjVerb to new be{{tag|v}}8 KB (741 words) - 03:41, 4 September 2017
- ...rchunk (see "advanced transfer" in the official documentation). Interchunk transfer uses 3 steps and cascaded interchunk uses more than 3. *Then, the chunks are formed by reading lexical forms left-to-right and building the longest-matching sequence that matches4 KB (669 words) - 14:12, 6 July 2012
- ...ach language pair. After that the focus was on tur-uig and uzb-tur. CG and transfer rules were written to improve the translation quality for these languages. ==Transfer==7 KB (798 words) - 18:30, 26 August 2019
- ===Lexical=== You can use some other system for lexical transfer (e.g. an Apertium bilingual dictionary), or you can do it directly in CG.3 KB (368 words) - 11:35, 26 August 2011
- * A couple easy lexical selection rules are still not written. # write ≥4 lexical selection rules8 KB (975 words) - 06:42, 23 September 2013
- ===Lexical Selection Errors（因词害义）=== ...". However, "干" is also colloquial slang for "f***". The translator's poor lexical selection resulted in a widely-circulated internet joke.12 KB (1,637 words) - 16:03, 21 January 2016
- * Do we try and find syntactic relations in the transfer, or do we pre-annotate (e.g. with CG) then use the tags from CG to constrai ...allow for >1 possible TL translation ? to allow 'lexical selection' inside transfer as well as outside ?5 KB (788 words) - 10:50, 9 February 2015
- ...lexical selection. Work on rudimentary transfer rules, as well as begin on transfer rules for verbs. | Continue work on transfer rules for verbs.4 KB (521 words) - 05:48, 5 June 2017
- ...face form can correspond to multiple lexical units. When this happens, the lexical units are connected with <code>+</code>. ...hin the same <code>^…$</code> in the output of the analyser), while during transfer they are considered separate (a single <code>+</code> will give two <code>^4 KB (654 words) - 08:31, 6 April 2021
- ...otrebna su nam pravila prevoda za imenice. Pravila prevoda imaju svoj DTD (transfer.dtd), koji se može naći u paketu Apertiuma. Ako treba da implementirate p <transfer>26 KB (4,259 words) - 07:00, 16 February 2015
- :* Transfer (syntactic + lexical) ...ule-based) and the ability to move around chunks (NP, V, etc.) rather than lexical units.3 KB (406 words) - 14:29, 13 April 2008
- ===Improvements in lexical-selection module=== * [[User:Fpetkovski/GSOC 2013 Application - Improving the lexical selection module]]2 KB (200 words) - 08:21, 13 January 2015
- * Execute transfer stages (all 3 of them) ...the C++ binaries for preparing/developing a language pair, i.a. to compile transfer files and train the tagger.9 KB (1,370 words) - 09:49, 7 April 2020
- * -lex runs up until lexical selection * -transfer runs up until (1-stage) transfer6 KB (824 words) - 22:30, 24 January 2022
- ...c compounding magic for generation – transfer should simply output several lexical units in a row with no spaces between them. We typically use a (non-hidden) Example: after transfer we might have <code>^krans<n><m><sg><ind><cmp>$^kake<n><f><sg><ind>$</code>16 KB (2,689 words) - 09:07, 6 April 2021
- ...ce is available. This section describes several (3) methods for estimating lexical selection rules using a parallel corpus. We start by describing the part of ...-tagger-output</code> and the [[Lexical selection module scripts reference|lexical selection scripts]]. (The program [[multitrans]] should be installed by ape14 KB (2,181 words) - 19:01, 17 August 2018
- I had to write the transfer rules from scratch, but this also went Apertium documentation; nn-nb uses only one-stage transfer since the12 KB (1,886 words) - 12:20, 20 June 2019
- ...oped the analysis dictionary, the bilingual dictonary, the three levels of transfer rules. ===Transfer rules===7 KB (830 words) - 21:33, 30 September 2013
- ...r during transfer) based on the dependency tree (this would not do lexical transfer, concordance or anything else, just LU reordering). The sister project [[Ma ...nvert <code>cg-proc</code> to output dependency information along with the lexical units. The second stage would be to write a module that builds a tree and d6 KB (804 words) - 08:44, 3 October 2013
- ...has an [http://apertium.svn.sourceforge.net/viewvc/apertium/trunk/apertium-transfer-tools/example/ example] directory in the source package, which should be th apertium-transfer:6 KB (1,022 words) - 08:15, 8 October 2014
- ...s from the analyser will have some match in the bidix, and all output from transfer will have some entry in the generator.<ref>Typically this goes for both tra ...certain nouns, and gender is not even present in the source language. The transfer rule expects to have this information; without it, not only will the noun b4 KB (679 words) - 16:06, 3 May 2020
- Lexical transfer: Lexical selection:6 KB (412 words) - 23:31, 31 January 2020
- | <code>vblex</code> || Standard ("lexical") verb || ''see also: vbser, vbhaver, vbmod, vaux, vbdo'' || VERB | <code><r></code> || Right side (lexical unit) || In <code><p></code>. Ex.: <code><r>beer<s n="noun"/>&38 KB (4,492 words) - 15:36, 9 May 2024
- Some ideas for (semi-)automatically extracting lexical resources from # Transfer rules6 KB (928 words) - 13:57, 3 April 2009
- | apertium-transfer -n '/home/shane/apertium/en-es/apertium-en-es/apertium-en-es.en-es.genitive | apertium-transfer -b '/home/shane/apertium/en-es/apertium-en-es/apertium-en-es.en-es.t1x' '/6 KB (992 words) - 17:25, 22 September 2016
