diff --git a/examples/phrasebook/GreetingsSpa.gf b/examples/phrasebook/GreetingsSpa.gf index 6008688f6..673bac85e 100644 --- a/examples/phrasebook/GreetingsSpa.gf +++ b/examples/phrasebook/GreetingsSpa.gf @@ -11,6 +11,9 @@ lin GDamn = ss "joder" ; GExcuse = ss "perdón" ; GExcusePol = ss "perdone" ; + GCongratulations = ss "felicitaciones" ; + GGoodLuck = ss "buena suerte" ; + GHappyBirthday = ss "feliz cumpleaños" ; GGoodMorning, GGoodDay = ss "buenos días" ; GGoodEvening = ss "buenas tardes" ; GGoodNight = ss "buenas noches" ; diff --git a/examples/phrasebook/Implementation.html b/examples/phrasebook/Implementation.html index 41bab9f70..ff2275979 100644 --- a/examples/phrasebook/Implementation.html +++ b/examples/phrasebook/Implementation.html @@ -106,8 +106,10 @@ gfdoc - a rudimentary GF document generator. Too property = mkAP too_AdA (mkAP property) ; PropQuality property = mkAP property ; - ThePlace kind = placeNP the_Det kind ; - APlace kind = placeNP a_Det kind ; + ThePlace kind = let dd = if_then_else Det kind.isPl thePl_Det theSg_Det + in placeNP dd kind ; + APlace kind = let dd = if_then_else Det kind.isPl thePl_Det theSg_Det + in placeNP dd kind ; IMale, IFemale = mkPerson i_Pron ; YouFamMale, YouFamFemale = mkPerson youSg_Pron ; @@ -130,7 +132,11 @@ gfdoc - a rudimentary GF document generator. NNumeral n = mkCard <lin Numeral n : Numeral> ; - AHave p obj = mkCl p.name have_V2 obj ; + SHave p obj = mkS (mkCl p.name have_V2 obj) ; + SHaveNo p k = mkS negativePol (mkCl p.name have_V2 (mkNP aPl_Det k)) ; + SHaveNoMass p m = mkS negativePol (mkCl p.name have_V2 (mkNP m)) ; + QDoHave p obj = mkQS (mkQCl (mkCl p.name have_V2 obj)) ; + AHaveCurr p curr = mkCl p.name have_V2 (mkNP aPl_Det curr) ; ACitizen p n = mkCl p.name n ; ABePlace p place = mkCl p.name place.at ; @@ -166,12 +172,20 @@ These are used in Words for each language. } ; NPPlace : Type = {name : NP ; at : Adv ; to : Adv} ; - CNPlace : Type = {name : CN ; at : Prep ; to : Prep} ; + CNPlace : Type = {name : CN ; at : Prep ; to : Prep; isPl : Bool} ; mkCNPlace : CN -> Prep -> Prep -> CNPlace = \p,i,t -> { name = p ; at = i ; - to = t + to = t ; + isPl = False + } ; + + mkCNPlacePl : CN -> Prep -> Prep -> CNPlace = \p,i,t -> { + name = p ; + at = i ; + to = t ; + isPl = True } ; placeNP : Det -> CNPlace -> NPPlace = \det,kind -> @@ -344,7 +358,7 @@ Means of transportation Actions: the predication patterns are very often language-dependent. 
-      AHasAge p num = mkCl p.name (mkNP (mkNP num L.year_N) (mkAdv "old"));
+      AHasAge p num = mkCl p.name (mkNP (mkNP num L.year_N) (ParadigmsEng.mkAdv "old"));
       AHasChildren p num = mkCl p.name have_V2 (mkNP num L.child_N) ;
       AHasRoom p num = mkCl p.name have_V2 
         (mkNP (mkNP a_Det (mkN "room")) (SyntaxEng.mkAdv for_Prep (mkNP num (mkN "person")))) ;
@@ -456,10 +470,10 @@ auxiliaries
         mkNPDay day (SyntaxEng.mkAdv on_Prep day) 
           (SyntaxEng.mkAdv on_Prep (mkNP a_Quant plNum (mkCN (mkN d)))) ;
   
-      mkCompoundPlace : Str -> Str -> Str -> {name : CN ; at : Prep ; to : Prep} = \comp, p, i ->
+      mkCompoundPlace : Str -> Str -> Str -> {name : CN ; at : Prep ; to : Prep; isPl : Bool} = \comp, p, i ->
        mkCNPlace (mkCN (P.mkN comp (mkN p))) (P.mkPrep i) to_Prep ;
   
-      mkPlace : Str -> Str -> {name : CN ; at : Prep ; to : Prep} = \p,i -> 
+      mkPlace : Str -> Str -> {name : CN ; at : Prep ; to : Prep; isPl : Bool} = \p,i -> 
         mkCNPlace (mkCN (mkN p)) (P.mkPrep i) to_Prep ;
   
       open_Adv = P.mkAdv "open" ;
diff --git a/examples/phrasebook/Makefile b/examples/phrasebook/Makefile
index f0dc1826d..4e36e2988 100644
--- a/examples/phrasebook/Makefile
+++ b/examples/phrasebook/Makefile
@@ -29,7 +29,7 @@ doc:
 	rm -f Ontology.gf
 	cat SentencesI.gf WordsEng.gf >Implementation.gf
 	gfdoc Implementation.gf
-	txt2tags -thtml phrasebook.txt
+	txt2tags -thtml --toc phrasebook.txt
 	rm -f Ontology.gf Implementation.gf
 
 upload:: Phrasebook.pgf
diff --git a/examples/phrasebook/Ontology.html b/examples/phrasebook/Ontology.html
index 0765ac4e0..48059049a 100644
--- a/examples/phrasebook/Ontology.html
+++ b/examples/phrasebook/Ontology.html
@@ -147,12 +147,16 @@ Determiners.
 Actions are typically language-dependent, not only lexically but also
 structurally. However, these ones are mostly functorial.
 
-      AHave     : Person -> Object      -> Action ;  -- you have pizzas
+      SHave       : Person -> Object      -> Sentence ;  -- you have beer
+      SHaveNo     : Person -> Kind        -> Sentence ;  -- you have no apples
+      SHaveNoMass : Person -> MassKind    -> Sentence ;  -- you have no beer
+      QDoHave     : Person -> Object      -> Question ;  -- do you have beer
+  
       AHaveCurr : Person -> Currency    -> Action ;  -- you have dollars
       ACitizen  : Person -> Citizenship -> Action ;  -- you are Swedish
       ABePlace  : Person -> Place       -> Action ;  -- you are in the bar
   
-      ByTransp : Transport -> ByTransport ;         -- by bus
+      ByTransp : Transport -> ByTransport ;          -- by bus
   
   }
 

diff --git a/examples/phrasebook/WordsFin.gf b/examples/phrasebook/WordsFin.gf
index 29494ccb2..0e4e7d14c 100644
--- a/examples/phrasebook/WordsFin.gf
+++ b/examples/phrasebook/WordsFin.gf
@@ -208,7 +208,9 @@ concrete WordsFin of Words = SentencesFin **
       mkQS (mkQCl (mkIP which_IDet trans.name) (mkVP (mkVP L.go_V) place.to)) ;
 
     IsTranspPlace trans place =
-      mkQS (mkQCl (E.AdvPredNP place.to L.go_V (E.PartCN (trans.name)))) ; 
+      mkQS (mkQCl (mkCl (mkVP (mkVP (mkVP (mkV "päästä")) trans.by) place.to))) ;
+      -- pääseekö keskustaan bussilla
+      -- mkQS (mkQCl (E.AdvPredNP place.to L.go_V (E.PartCN (trans.name)))) ; 
       -- meneekö keskustaan bussia
 
 -- modifiers of places
diff --git a/examples/phrasebook/missing.txt b/examples/phrasebook/missing.txt
index e05b4c3c2..88a998dfb 100644
--- a/examples/phrasebook/missing.txt
+++ b/examples/phrasebook/missing.txt
@@ -11,5 +11,5 @@ PhrasebookIta :
 PhrasebookNor :
 PhrasebookPol :
 PhrasebookRon :
-PhrasebookSpa : GCongratulations GGoodLuck GHappyBirthday
+PhrasebookSpa :
 PhrasebookSwe :
diff --git a/examples/phrasebook/phrasebook.html b/examples/phrasebook/phrasebook.html
index fae61468a..2d36e5fc0 100644
--- a/examples/phrasebook/phrasebook.html
+++ b/examples/phrasebook/phrasebook.html
@@ -2,6 +2,7 @@
 
 
 
+
 MOLTO Multilingual Phrasebook
 
 
MOLTO Multilingual Phrasebook

@@ -10,6 +11,25 @@
 Showcase for project FP7-ICT-247914, Deliverable D10.2.
 

 
+

+

+

+  
+
+

+

+

 

 

 
@@ -18,6 +38,8 @@ Showcase for project FP7-ICT-247914, Deliverable D10.2.
 History
 

 
 
-
Acknowledgements

+
+
Effort and cost

+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
LanguageGrammarian's language skillsGrammarian's GF skillsInformant used for developmentInformant used for testingUse of external toolsImpact of external toolsChanges on the resource grammarDevelopment time
Bulgarian######---?###
Catalan######---?##
Danish-###+++######
Dutch-###+++#####
English#####-+--_#
Finnish######---?###
French#####-+-?##
German####+++#######
Italian####---?####
Norwegian####+-+#####
Polish######+++####
Romanian######--+#######
Spanish###---?_##
Swedish#####-+-?-##

+
+

+Explanation on scores
+

+
+
+
+
+
+
+
+
+
+
+
+
+
+
Example-based grammar writing prototype

+

+The figure presents the process of creating a Phrasebook using an example-based 
+approach for the language X, where X = {Danish, Dutch, German, Norwegian}.
+

+

+
+

+
+
+

+The time needed for preparing the configuration files for a grammar will not be needed 
+in the future, since the files are reusable for other applications.
+The time for the second step can be saved if automatic tools, like Google translate 
+are used. This is only possible in languages with a simpler morphology and syntax 
+and large corpora available.
+Good results were obtained for German and Dutch with Google translate, but for 
+languages like Romanian or Polish, which are both complex and lack enough resources, 
+the results are discouraging. 
+

+

+If the statistical oracle works well, the only step where the presence of a human 
+translator is needed is the evaluation and feedback step. An average of 4 hours per 
+round and 2 rounds were needed in average for the languages for which we performed 
+the experiment. It is possible that more effort is needed for more complex languages.
+

+
+
Conclusions (tentative)

+

+The grammarian need not be a native speaker of the language.
+

+

+For many languages, the grammarian need not even know the language - native informants are
+enough.
+

+

+However, evaluation by native speakers is necessary.
+

+

+Correct and idiomatic translations are possible.
+

+

+A typical development time was 2-3 person working days per language.
+

+

+Google translate helps in bootstrapping grammars, but must be checked.
+

+
+
+

+Resource grammars should give some more support
+

+
+
+
+
Acknowledgements

 

 The Phrasebook has been built in the MOLTO project funded by the European Commission.
 

 

 The authors are grateful to their native speaker informants helping to bootstrap and evaluate
-the grammars: Richard Bubel, Grégoire Détrez, Michal Palka, Willard Rafnsson,...
+the grammars: 
+Richard Bubel, 
+Grégoire Détrez, 
+Karin Keijzer, 
+Michał Pałka,
+Willard Rafnsson,
+Nick Smallbone.
 

 
 
-
+
 
diff --git a/examples/phrasebook/phrasebook.txt b/examples/phrasebook/phrasebook.txt
index 7226ae1b1..d7bfa162d 100644
--- a/examples/phrasebook/phrasebook.txt
+++ b/examples/phrasebook/phrasebook.txt
@@ -3,6 +3,8 @@ Krasimir Angelov, Olga Caprotti, Ramona Enache, Thomas Hallgren, Inari Listenmaa
 Showcase for project FP7-ICT-247914, Deliverable D10.2.
 
 
+%!Encoding:utf-8
+
 %!postproc(html): #HR 

 %!postproc(html): #BSMALL 
 %!postproc(html): #ESMALL 
@@ -14,6 +16,8 @@ Showcase for project FP7-ICT-247914, Deliverable D10.2.
 #BSMALL
 
 History
+- 2 June. Version 1.0 released!
+- 29 May. Link to Google translate with the current language pair and phrase.
 - 27 May. Polish added.
 - 26 May. Version 0.9:
   Catalan added, mass/count noun distinction to reduce overgeneration, 
@@ -46,24 +50,24 @@ History
 =Purpose=
 
 This phrasebook is a program for translating touristic phrases 
-between the 15 European languages included in the 
+between 14 European languages included in the 
 [MOLTO http://www.molto-project.eu] project
 (Multilingual On-Line Translation):
 - Bulgarian, Catalan, Danish, Dutch, English,
   Finnish, French, German, Italian, Norwegian,
-  Polish, Romanian, Russian, Spanish, Swedish
+  Polish, Romanian, Spanish, Swedish
 
 
 It is implemented by using the GF programming language 
 ([Grammatical Framework http://grammaticalframework.org]).
-It is the first demo for the MOLTO project, released in the third month (by June 2010)
-but to be updated in the course of the project.
+It is the first demo for the MOLTO project, released in the third month (by June 2010).
+The first version is a very small system, but it will extended in the course of the project.
 
-The phrasebook has the following requirements:
+The phrasebook has the following requirement specification:
 - high quality: reliable translations to express yourself in any language
 - translation between all pairs of languages
 - runnable in web browsers
-- runnable on mobile phones (also off-line: forthcoming for Android phones)
+- runnable on mobile phones (forthcoming: Android phones)
 - easily extensible by new words (forthcoming: semi-automatic extensions by users)
 
 
@@ -72,30 +76,57 @@ The source code resides in
 [``code.haskell.org/gf/examples/phrasebook/`` http://code.haskell.org/gf/examples/phrasebook/]
 
 
-Current status (27 May 2010):
-- small but useful coverage in abstract syntax
-- reasonable implementations for all MOLTO languages except Russian
-- works on web browsers calling a server
-- web service not yet released, but preliminarily available in
-  http://www.grammaticalframework.org/demos/phrasebook/
-
-
 
 =Points illustrated=
 
-Interlingua-based translation.
+Interlingua-based translation
+- we translate meanings, rather than words
 
-Incremental parsing.
 
-The use of resource grammars and functors.
+Incremental parsing
+- the user is at every point guided by the list of possible next words
 
-Example-based grammar writing and grammar induction from statistical models (Google).
 
-Compile-time transfer: especially, in Action in Words.
+The use of resource grammars and functors
+- the translator was implemented on top of an earlier linguistic knowledge base,
+  the [GF Resource Grammar Library http://grammaticalframework.com/lib]
 
-Quasi-incremental translation: many basic types are also used as phrases.
 
-Disambiguation, esp. of politeness distinctions.
+Example-based grammar writing and grammar induction from statistical models 
+([Google translate http://translate.google.com])
+- many of the grammars were created semi-automatically by generalization from
+  examples
+
+
+Compile-time transfer: especially, in Action in Words
+- the structural differences between languages are treated at compile time,
+  for maximal run-time efficiency
+
+
+Quasi-incremental translation: many basic types are also used as phrases
+- one can translate both words and complete sentences, and get intermediate results
+
+
+Disambiguation, esp. of politeness distinctions
+- if a phrase has many translations, each of them is shown and given an explanation
+  (currently just in English, later in any source language)
+
+
+Fall-back to statistical translation
+- currently just a link to Google translate (forthcoming: tailor-made statistical models)
+
+
+Feed-back from users
+- you are welcome to send comments, bug reports, and better translation suggestions!
+
+
+The level of skills involved in grammar development
+- testing different configurations (see table below)
+
+
+Grammar testing
+- use of treebanks with guided random generation for initial evaluation and regression testing
+
 
 
 
@@ -146,25 +177,15 @@ Here is the module structure as produced in GF by
 
 =To Do=
 
-Improved translation interface
-- a nicer way to show disambiguation (maybe hidden by default)
-
-
-Complete the missing words and phrases
-
 Disambiguation grammars for other languages than English
 
 Extend the abstract lexicon in ``Words`` by hand or (semi)automatically for
 - food stuff
-- languages
 - places
+- actions
 
 
-Link to Google translate, for fall-back and for comparison
-
-Feedback facility in the UI
-
-Customizable distribution: make your own selection of the 2^15 language subsets
+Customizable phone distribution: make your own selection of the 2^15 language subsets
 when downloading the phrasebook to a phone
 
 
@@ -214,10 +235,151 @@ Here are the steps to follow for contributors:
 - Don't compromise quality to gain coverage: //non multa sed multum!// 
 
 
-==Acknowledgements==
+
+=Effort and cost=
+
+|| Language | Grammarian's language skills  | Grammarian's GF skills | Informant used for development | Informant used for testing | Use of external tools | Impact of external tools | Changes on the resource grammar | Development time || 
+| Bulgarian |   ###    |    ###  |    -  |  -  |   -   |   ?   |  #   |   ##  |
+| Catalan   |   ###    |    ###  |    -  |  -  |   -   |   ?   |  #   |   #   |
+| Danish    |   -      |    ###  |    +  |  +  |   +   |   ##  |  ##  |   ##  |
+| Dutch     |   -      |    ###  |    +  |  +  |   +   |   ##  |  #   |   ##  |
+| English   |   ##     |    ###  |    -  |  +  |   -   |   -   |  _   |   #   |
+| Finnish   |   ###    |    ###  |    -  |  -  |   -   |   ?   |  #   |   ##  |
+| French    |   ##     |    ###  |    -  |  +  |   -   |   ?   |  #   |   #   |
+| German    |   #      |    ###  |    +  |  +  |   +   |   ##  |  ##  |   ###  |
+| Italian   |   ###    |    #    |    -  |  -  |   -   |   ?   |  ##  |   ##  |
+| Norwegian |   #      |    ###  |    +  |  -  |   +   |   ##  |  #   |   ##  |
+| Polish    |   ###    |    ###  |    +  |  +  |   +   |   #   |  #   |   ##  |
+| Romanian  |   ###    |    ###  |    -  |  -  |   +   |   #   |  ###  |   ###  |
+| Spanish   |   ##     |    #    |    -  |  -  |   -   |   ?   |  _   |   ##   |
+| Swedish   |   ##     |    ###  |    -  |  +  |   -   |   ?   |  -   |   ##  |
+
+
+Explanation on scores
+
+- Grammarian's language skills  
+   - -   : no skills
+   - #   : passive knowledge
+   - ##  : fluent non-native
+   - ### : native speaker
+
+
+- Grammarian's GF skills  
+   - -   : no skills
+   - #   : basic skills (2-day GF tutorial)
+   - ##  : medium skills (previous experience of similar task)
+   - ### : advanced skills (resource grammar writer/substantial contributor)
+
+
+- Informant used for development/Informant needed for testing/Use of external tools 
+   - - : no
+   - + : yes
+
+
+- Impact of external tools 
+   - ? : not investigated
+   - - : no effect on the Phrasebook
+   - # : small impact (literal translation, simple idioms)
+   - ## : medium effect (translation of more forms of words, contextual preposition)
+   - ### : great effect (no extra work needed, translations are correct)
+
+
+- Changes on the resource grammars
+   - - : no changes
+   - # : 1-3 minor changes
+   - ## : 4-10 minor changes, 1-3 medium changes
+   - ### : >10 changes of any kind  
+
+
+- Overall effort (including extra work on resource grammars)
+   - # : less than 8 person hours
+   - ## : 8-24 person hours
+   - ### : >24 person hours
+ 
+
+=Example-based grammar writing prototype=
+
+The figure presents the process of creating a Phrasebook using an example-based 
+approach for the language X, where X = {Danish, Dutch, German, Norwegian}.
+
+[picpic.jpg]
+
+- the first step assumes an analysis of the resource grammar and extracts the necessary 
+  information that functions that build new lexical entries would need. 
+  A model is built so that the proper forms of the word can be rendered, 
+  and additional information, such as gender, can be inferred. The script applies 
+  these rules to each entry that we want to translate into the target language, and 
+  one obtains a set of constructions.
+- they are furthermore given to an external translator tool (Google translate) 
+  or a native speaker for translation. One needs the configuration file even if the 
+  translator is human, because formal knowledge of grammar is not assumed.
+- the translations into the target language are further more processed in order to 
+  build the linearizations of the categories first, decoding the information received. 
+  Furthermore, having the words in the lexicon, one can parse the translations of 
+  functions with the GF parser and generalize from that.
+- the resulting grammar is tested with the aid of a script that generates 
+  constructions covering all the functions and categories from the grammar, along 
+  with some other constructions that proved to be problematic in some language. 
+  The result of the script contains for each construction in the target language 
+  its English correspondent and the abstract syntax tree. A native speaker 
+  evaluates the results and if corrections are needed, the algorithm runs again 
+  with the new examples. Depending on the language skills of the grammar writer, 
+  the changes can be made directly into the GF files, and the correct examples 
+  given by the native informant are just kept for validating the results. 
+  The algorithm is repeated as long as corrections are needed.
+
+
+The time needed for preparing the configuration files for a grammar will not be needed 
+in the future, since the files are reusable for other applications.
+The time for the second step can be saved if automatic tools, like Google translate 
+are used. This is only possible in languages with a simpler morphology and syntax 
+and large corpora available.
+Good results were obtained for German and Dutch with Google translate, but for 
+languages like Romanian or Polish, which are both complex and lack enough resources, 
+the results are discouraging. 
+
+If the statistical oracle works well, the only step where the presence of a human 
+translator is needed is the evaluation and feedback step. An average of 4 hours per 
+round and 2 rounds were needed in average for the languages for which we performed 
+the experiment. It is possible that more effort is needed for more complex languages.
+
+
+=Conclusions (tentative)=
+
+The grammarian need not be a native speaker of the language.
+
+For many languages, the grammarian need not even know the language - native informants are
+enough.
+
+However, evaluation by native speakers is necessary.
+
+Correct and idiomatic translations are possible.
+
+A typical development time was 2-3 person working days per language.
+
+Google translate helps in bootstrapping grammars, but must be checked.
+- in particular, unreliable for morphologically rich languages
+
+
+Resource grammars should give some more support
+- higher-level access to constructions like negative expressions
+- large-scale morphological lexica
+
+
+
+
+
+
+=Acknowledgements=
 
 The Phrasebook has been built in the MOLTO project funded by the European Commission.
 
 The authors are grateful to their native speaker informants helping to bootstrap and evaluate
-the grammars: Richard Bubel, Grégoire Détrez, Michal Palka, Willard Rafnsson,...
+the grammars: 
+Richard Bubel, 
+Grégoire Détrez, 
+Karin Keijzer, 
+Michał Pałka,
+Willard Rafnsson,
+Nick Smallbone.
 
diff --git a/examples/phrasebook/picpic.jpg b/examples/phrasebook/picpic.jpg
new file mode 100644
index 000000000..aac20b611
Binary files /dev/null and b/examples/phrasebook/picpic.jpg differ