 kr.angelov
|
667c3aa174
|
decrease the heuristic factor for parsing to 0.80 from 0.95. Otherwise we get the wrong result for compound verbs like "look after", "look forward", etc.
|
2013-09-20 12:07:47 +00:00 |
|
|
kr.angelov
|
aa4c55a3c1
|
ProgrVP in English should add the verb particle if there is any
|
2013-09-20 12:07:12 +00:00 |
|
|
kr.angelov
|
dd8b65e355
|
added PossNP, PartNP and CountNP in the Bulgarian RGL
|
2013-09-20 12:05:39 +00:00 |
|
|
kr.angelov
|
f76a57c8d2
|
added a version of compoundN which combines adjective and noun into a new noun
|
2013-09-20 12:04:37 +00:00 |
|
|
kr.angelov
|
519049496f
|
added a number of interjections and greetings in DictEng and DictEngBul
|
2013-09-19 12:02:44 +00:00 |
|
|
kr.angelov
|
d40118971a
|
fixes in DictEng & DictEngBul
|
2013-09-17 12:01:05 +00:00 |
|
|
kr.angelov
|
3ccb56cf4d
|
added UttInterj in PhraseBul
|
2013-09-17 11:59:59 +00:00 |
|
|
kr.angelov
|
a81c396ed6
|
fixes in DictEngBul
|
2013-09-13 09:49:31 +00:00 |
|
|
kr.angelov
|
1a7258040c
|
added for_sure_Adv in DictEng. renamed ourself -> ourselves & themself -> themselves
|
2013-09-04 07:11:56 +00:00 |
|
|
kr.angelov
|
3a2f05066b
|
added ExtAdvNP and ExtAdvVP in the resource grammar
|
2013-09-03 08:59:47 +00:00 |
|
|
kr.angelov
|
420ef54132
|
more changes in DictEng/DictEngBul
|
2013-09-03 08:57:18 +00:00 |
|
|
kr.angelov
|
f6d187b244
|
"that" in ComplVS and SlashV2S is now optional
|
2013-09-03 08:12:07 +00:00 |
|
|
kr.angelov
|
a7ff24ec23
|
PredVPovs now puts comma before the verb
|
2013-09-03 08:11:01 +00:00 |
|
|
kr.angelov
|
92878e5b0b
|
exposed ComplSlashPartLast in the parse grammar
|
2013-09-03 08:08:57 +00:00 |
|
|
kr.angelov
|
e75a059c6a
|
a couple of changes in DictEng/DictEngBul. Added infVV in ParadigmsEng which allows the definition of VVs that take a bare infinitive
|
2013-09-03 08:06:44 +00:00 |
|
|
kr.angelov
|
92c6ac9c2f
|
RelNP and ApposNP should put a final comma after the inserted phrase.
|
2013-09-03 08:00:59 +00:00 |
|
|
kr.angelov
|
9736b50ab2
|
fix the placement of AdV in PassVPSlash for English
|
2013-09-02 08:14:31 +00:00 |
|
|
kr.angelov
|
ca3c3d7acc
|
fix in the spelling of Hong Kong in DictEng
|
2013-09-02 08:13:52 +00:00 |
|
|
kr.angelov
|
2756fef545
|
fix the compilation of LangTur
|
2013-09-01 11:48:02 +00:00 |
|
|
kr.angelov
|
2a23f441a0
|
PassVPSlash must add the preposition
|
2013-08-27 14:32:12 +00:00 |
|
|
kr.angelov
|
51f9f2a966
|
laugh_at_V2 in DictEng(Abs,Eng,Bul)
|
2013-08-27 14:31:12 +00:00 |
|
|
kr.angelov
|
e7e242b911
|
added silly_A to DictEngBul
|
2013-08-27 14:03:00 +00:00 |
|
|
kr.angelov
|
f933f07842
|
fix PresPartRS for phrasal verbs
|
2013-08-27 12:02:57 +00:00 |
|
|
kr.angelov
|
3a34c87c3a
|
fix make_V2V
|
2013-08-27 12:02:29 +00:00 |
|
|
kr.angelov
|
ce7a29bb06
|
conjunction of AdV
|
2013-08-27 12:00:38 +00:00 |
|
|
kr.angelov
|
0d2c4a5307
|
fix in DictEng.gf
|
2013-08-27 08:08:41 +00:00 |
|
|
kr.angelov
|
3bb862b5a7
|
a few words in DictEngBul.gf
|
2013-08-26 07:00:39 +00:00 |
|
|
kr.angelov
|
f5fe5ce1d4
|
bugfix in the Hindi parse grammar
|
2013-08-25 12:48:11 +00:00 |
|
|
kr.angelov
|
62afa58663
|
nonExist now does the expected thing
|
2013-08-23 13:17:45 +00:00 |
|
|
kr.angelov
|
bb13a6b9ba
|
a bunch of words in DictEngBul
|
2013-08-20 20:54:20 +00:00 |
|
|
kr.angelov
|
200e13f7e5
|
fixes in DictEngBul
|
2013-08-16 12:37:38 +00:00 |
|
|
kr.angelov
|
8ffdc12a03
|
extensions in DictEngBul.gf
|
2013-06-22 15:41:52 +00:00 |
|
|
kr.angelov
|
f42061837b
|
substantive and relative nouns in the Bulgarian library
|
2013-05-23 10:15:10 +00:00 |
|
|
kr.angelov
|
abf9f13f3c
|
a bunch of changes in DictEng and DictEngBul
|
2013-05-23 09:29:59 +00:00 |
|
|
kr.angelov
|
e625d50492
|
remove DiffBul.gf which is now obsolete
|
2013-05-23 08:59:36 +00:00 |
|
|
kr.angelov
|
ec06e9d1e4
|
remove /lib/src/english/ParseEngAbs3.probs since now it is moved to /treebanks/PennTreebank/ParseEngAbs3.probs
|
2013-05-03 21:25:31 +00:00 |
|
|
kr.angelov
|
fe12224a7f
|
added a few more multiword expressions in DictEng and a few words in the abstract syntax are not tagged with their senses. There is a new statistical model too
|
2013-03-27 20:46:42 +00:00 |
|
|
kr.angelov
|
f9b67676e1
|
a long list of prepositions from Wikipedia is now imported in DictEng in addition there are a number of small other changes in the dictionary. The statistical model is updated and is now moved to treebanks/PennTreebank/ParseEngAbs.probs
|
2013-03-25 10:24:24 +00:00 |
|
|
kr.angelov
|
b73a6af45f
|
fix in ParseHin which made it impossible to load the grammar with the C runtime
|
2013-03-20 10:34:37 +00:00 |
|
|
kr.angelov
|
c51918f65e
|
the ParseFin grammar now excludes ComplVV from VerbFin since this function has a more general type in the parsing grammar
|
2013-03-19 10:49:13 +00:00 |
|
|
kr.angelov
|
87a1d29d7e
|
filterout all adjectives and adverbs which could be derived morphologically
|
2013-03-18 17:31:20 +00:00 |
|
|
kr.angelov
|
5c078f9393
|
some of the newly added nouns in DictEng were actually variations of already existing lexical entries. Those are removed now.
|
2013-03-15 23:23:06 +00:00 |
|
|
kr.angelov
|
cf6ec163ce
|
massive extensions in DictEng and DictEngBul. This includes all new nouns imported from WordNet by Shafqat, phrasal verbs that I collected from internet and the PennTreebank, plus various other small additions.
|
2013-03-15 20:18:22 +00:00 |
|
|
kr.angelov
|
1606ea463a
|
a bunch of changes in DictEng and DictEngBul plus an updated statistical model
|
2013-02-27 09:21:29 +00:00 |
|
|
kr.angelov
|
e5b0d757bf
|
fixes and extensions in DictEng and DictBul
|
2013-02-22 09:53:54 +00:00 |
|
|
kr.angelov
|
6005445757
|
now the beam size for the statistical parser can be configured by using the flag beam_size in the top-level concrete module
|
2013-02-12 10:53:13 +00:00 |
|
|
kr.angelov
|
eb612177c3
|
a bunch of new words and fixes in DictEng and DictEngBul
|
2013-02-10 22:27:18 +00:00 |
|
|
kr.angelov
|
bd47f06df6
|
in NumeralAmh: UTF8 -> utf8. The former is not recognized on Windows
|
2013-01-31 15:08:13 +00:00 |
|
|
kr.angelov
|
f784d35ba0
|
a few fixes in DictEng
|
2013-01-30 09:58:39 +00:00 |
|
|
kr.angelov
|
67e141850f
|
more words in DictEngBul.gf
|
2013-01-30 09:57:39 +00:00 |
|
|
kr.angelov
|
39bd3e08c0
|
switch from CP1251 to UTF8 in DictBul
|
2013-01-17 15:52:04 +00:00 |
|
|
kr.angelov
|
c073e2ed71
|
a few more words in DictEngBul.gf
|
2013-01-17 08:23:13 +00:00 |
|
|
kr.angelov
|
b51444af30
|
a few fixes in DictEngBul
|
2013-01-15 13:24:04 +00:00 |
|
|
kr.angelov
|
08a982242d
|
about 3000 new words in DictEngBul.gf. The words are imported from the Universal WordNet but are not manually checked yet.
|
2013-01-15 11:17:59 +00:00 |
|
|
kr.angelov
|
bc5d0e1cea
|
updated statistical model
|
2012-12-17 10:31:04 +00:00 |
|
|
kr.angelov
|
47baaae4dc
|
some fixes in DictEng
|
2012-12-17 10:24:46 +00:00 |
|
|
kr.angelov
|
e3288db894
|
a bugfix for building questions in the Bulgarian resource grammar
|
2012-12-13 15:52:55 +00:00 |
|
|
kr.angelov
|
a15e0ec6a4
|
updated statistical model
|
2012-11-28 12:44:20 +00:00 |
|
|
kr.angelov
|
77874dd9bf
|
Pakistani is now properly capitalized in the English dictionary
|
2012-11-28 12:43:45 +00:00 |
|
|
kr.angelov
|
21b3e0fdc4
|
translations for several words in the Bulgarian dictionary
|
2012-11-28 12:42:23 +00:00 |
|
|
kr.angelov
|
b8f95bfd6b
|
added familiar_A2 in DictEng, DictEngBul and DictEngGer
|
2012-11-28 12:40:20 +00:00 |
|
|
kr.angelov
|
448a4a77fc
|
bugfix for composite adjectivial phrases in Bulgarian
|
2012-11-28 12:37:24 +00:00 |
|
|
kr.angelov
|
2ad45a05a2
|
a bunch of additions in the parsing grammars and dictionaries plus an updated statistical model
|
2012-11-26 16:43:09 +00:00 |
|
|
kr.angelov
|
fc5199fc51
|
fix in ParseEngAbs3.probs
|
2012-11-19 14:14:08 +00:00 |
|
|
kr.angelov
|
c0e6c1bdd1
|
a statistical model for robustness in lib/src/english
|
2012-11-19 12:24:11 +00:00 |
|
|
kr.angelov
|
9498b86834
|
updated ParseEngAbs.probs with the latest statistics
|
2012-11-19 12:15:25 +00:00 |
|
|
kr.angelov
|
2114122e20
|
a couple of fixes and new words in DictEng and DictEngBul
|
2012-11-16 09:56:20 +00:00 |
|
|
kr.angelov
|
055b0658fd
|
Added as_Subj and UttAdV in the parsing grammars. Replaced plus_Prep with plus_Conj
|
2012-10-01 08:47:52 +00:00 |
|
|
kr.angelov
|
9e65cf21d5
|
added AdvVPSlash and AdVVPSlash to VerbGer and an extended version of PPartNP which uses VPSlash in ParseEngGer. I guess the definitions so they might not be quite correct
|
2012-09-27 11:44:25 +00:00 |
|
|
kr.angelov
|
8b54233ca1
|
added ParseEngGer.gf
|
2012-09-27 09:54:13 +00:00 |
|
|
kr.angelov
|
b3eb1bc0aa
|
add ApposNP and UncNeg to the Bulgarian parsing grammar
|
2012-09-27 09:31:37 +00:00 |
|
|
kr.angelov
|
9b959b93c9
|
use CNNumNP in the parsing grammars
|
2012-09-27 09:31:04 +00:00 |
|
|
kr.angelov
|
88bb473ca7
|
remove no_RP from the parsing grammars and use EmptyRelSlash instead
|
2012-09-27 09:29:59 +00:00 |
|
|
kr.angelov
|
18b06fea67
|
added EmptyRelSlash in ExtraBul and ExtraGer. For Bulgarian and German the function simply inserts the default relative pronoun
|
2012-09-27 09:28:31 +00:00 |
|
|
kr.angelov
|
b24530d970
|
added according_to_Prep and ofter_AdA in DictEng, DictEngBul and DictEngGer
|
2012-09-27 09:11:04 +00:00 |
|
|
kr.angelov
|
308339e0ab
|
a few more words in DictEngBul
|
2012-09-27 09:09:49 +00:00 |
|
|
kr.angelov
|
6f2723485c
|
now in the parsing grammar ComplVV gets as additional arguments the polarity and the anteriority
|
2012-09-27 09:05:47 +00:00 |
|
|
kr.angelov
|
2c11a50c0a
|
an optimization in the German grammar for the dative/genitive variants
|
2012-09-26 11:11:42 +00:00 |
|
|
kr.angelov
|
9d3632d1c3
|
a bit of reordering in DictEngGer.gf
|
2012-09-26 09:16:17 +00:00 |
|
|
kr.angelov
|
2894ae6fb4
|
fixes in DictEngGer.gf
|
2012-09-26 08:52:18 +00:00 |
|
|
kr.angelov
|
7c9c2cabb1
|
260 new words in DictEngGer which are taken from the lexicon for patents
|
2012-09-26 08:26:39 +00:00 |
|
|
kr.angelov
|
fe44298623
|
fixes in the German parsing grammar and cleanup in DictEngGer.gf
|
2012-09-25 20:12:38 +00:00 |
|
|
kr.angelov
|
819b3337dd
|
fixes in the Bulgarian resource grammar. extensions in DictEng and DictEngBul
|
2012-09-24 09:41:14 +00:00 |
|
|
kr.angelov
|
704a1b9e2c
|
a few changes in DictEng
|
2012-09-18 09:25:22 +00:00 |
|
|
kr.angelov
|
2506fb3ebc
|
updates to ParseEng and ParseEngBul
|
2012-09-06 13:27:08 +00:00 |
|
|
kr.angelov
|
3c7baa68f9
|
update the statistical model for ParseEng
|
2012-09-06 13:26:16 +00:00 |
|
|
kr.angelov
|
30ec87b57e
|
extensions to the English and the Bulgarian grammars. Infinitives with polarity and anteriority
|
2012-08-31 09:31:36 +00:00 |
|
|
kr.angelov
|
6f9715fc32
|
a few fixes in DictEng, DictEngBul and ParseEng
|
2012-08-29 11:46:58 +00:00 |
|
|
kr.angelov
|
7088d735e4
|
fixes in DictEng and extensions in DictEngBul
|
2012-08-09 12:09:21 +00:00 |
|
|
kr.angelov
|
4d89287a9e
|
DictEngBul is extended to 5000 words and there are few more functions in ParseEngBul
|
2012-06-29 09:57:02 +00:00 |
|
|
kr.angelov
|
8d49ef42c9
|
added VPI category and AdvVPSlash to the Bulgarian RGL
|
2012-06-26 09:54:06 +00:00 |
|
|
kr.angelov
|
eccb2f93d2
|
bugfix in GenRP in ExtraEng
|
2012-06-21 09:00:46 +00:00 |
|
|
kr.angelov
|
00e0ca26da
|
added few missing functions in the Bulgarian RGL
|
2012-06-21 09:00:21 +00:00 |
|
|
kr.angelov
|
acdf232cc9
|
various extensions to DictEngBul
|
2012-06-21 08:59:37 +00:00 |
|
|
kr.angelov
|
3b3f335857
|
extensions to DictEng and addition of parallel DictEngBul which is partly imported from Apertium
|
2012-06-20 09:06:59 +00:00 |
|
|
kr.angelov
|
e27893fd31
|
fix UncNeg in ParseEng
|
2012-06-13 06:10:51 +00:00 |
|
|
kr.angelov
|
b632671704
|
fix the path in DictEngGer.gf
|
2012-06-12 10:04:15 +00:00 |
|
|
kr.angelov
|
727133bc38
|
more in DictEng
|
2012-06-12 09:58:01 +00:00 |
|
|
kr.angelov
|
49c75f5d69
|
several updates to DictEng and ParseEng
|
2012-05-25 07:33:40 +00:00 |
|
|
kr.angelov
|
5bb13c4631
|
a bunch of new things in DictEng and ParseEng a simple fix for the VPI category in ExtraEng
|
2012-05-21 15:06:41 +00:00 |
|