Parsing Sanskrit Texts: Some relation specific issues
Transcript of Parsing Sanskrit Texts: Some relation specific issues
![Page 1: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/1.jpg)
. . . . . .
.
.. ..
.
.
Parsing Sanskrit Texts: Some relation specificissues
Amba Kulkarni1 and K V Ramakrishnamacharyulu2
Department of Sanskrit Studies,University of Hyderabad,
Hyderabad
Department of Vyakarana,Rashtriya Sanskrit Vidyapeetha,
Tirupati
1 / 39
![Page 2: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/2.jpg)
. . . . . .
.. Sentence Level Analysis
Parsing: a linear string of words – > a structure showing therelations between words.
Structure: Constituency / Dependency
2 / 39
![Page 3: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/3.jpg)
. . . . . .
.. Constituency Structure: Eng Sentence
For positional languages such as English, constituency structuremore or less leads to the dependency relations.
Figure: Constituency Parse of an English Sentence
3 / 39
![Page 4: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/4.jpg)
. . . . . .
.. Constituency Structure: Sanskrit CompoundIn case of Sanskrit compounds, such a constitutional structure isvery useful in determining the parse.
Figure: Constituency Structure of a Sanskrit Compound
4 / 39
![Page 5: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/5.jpg)
. . . . . .
.. Structure of a Sanskrit Sentence
Sanskrit:Morphologically richFree word order to a large extent
Dependency structure makes more sense than the constituencystructure.
5 / 39
![Page 6: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/6.jpg)
. . . . . .
.. Dependency Structure: Sanskrit Sentence
Dependency Parse: rājā viprāya gām dadāti
6 / 39
![Page 7: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/7.jpg)
. . . . . .
.. Sentence Level Analysis
Traditional Approaches:Daṇdānvyayaḥ [Anvyayamukhī]Khaṇdānvyayaḥ [Kathambhūtinī]
7 / 39
![Page 8: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/8.jpg)
. . . . . .
.. Sentence Level Analysis ...
Modern TimesDependency Parsing: credited to Tesniére [1959]
8 / 39
![Page 9: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/9.jpg)
. . . . . .
.. Tagset
Dependency Relations:Compilation of all relations: 90 [KVRK, 2009]Proposed a tagset
9 / 39
![Page 10: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/10.jpg)
. . . . . .
.. Tagset ...
Is this tagset suitable?
For Manual AnnotationFor Statistical ParsingFor Rule Based Parsing
10 / 39
![Page 11: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/11.jpg)
. . . . . .
.. Tagset ...
Is this tagset suitable?For Manual AnnotationFor Statistical ParsingFor Rule Based Parsing
10 / 39
![Page 12: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/12.jpg)
. . . . . .
.. Tagset ...
Concerns related to Manual Annotation / design of a StatisticalParser
The inter annotator agreementThe grey / fussy boundaries between semantics of tags lead toerrors in annotation.
Concerns related to a design of a Rule based ParserWhether the relations can be decided purely on the basis ofmorphological and syntactic information?
11 / 39
![Page 13: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/13.jpg)
. . . . . .
.. Annotation Convention
1 rAmaH kartA,32 vanam karma,33 gacchati
12 / 39
![Page 14: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/14.jpg)
. . . . . .
.. Clues for extracting the relations
Abhihitatva (property of being expressed)VibhaktiIndeclinables (avyaya)Sāmānādhikaraṇya (being in g-n-p agreement)Nitya sambandhaḥ
13 / 39
![Page 15: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/15.jpg)
. . . . . .
.. Clues: Abhitatva
tiṅrāmaḥ vanam gacchati.marks the kartā relationrāmeṇa vanam gamyate.marks the karma relation
kṛtdhāvan aśvaḥ.marks the kartā.
taddhitaḥsamāsaḥ
14 / 39
![Page 16: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/16.jpg)
. . . . . .
.. Clues: Vibhakti
kāraka vibhaktiMarks noun-verb relations.e.g. kartā, karma, etc.upapada vibhaktiMarks noun-noun relations through the upapadas.More of a morphological requirement.E.g. rāmeṇa saha sītā vanam gacchati.special vibhakti
kriyā-viśeṣaṇamvegena dhāvatiaṅgavikāraḥakṣṇā kāṇaḥnirdhāraṇanareṣu śreṣṭaḥ
15 / 39
![Page 17: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/17.jpg)
. . . . . .
.. Clues: Indeclinables
negationrāmaḥ gṛham na gacchati.emphasisrāmaḥ eva tatra upaviṣati.
16 / 39
![Page 18: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/18.jpg)
. . . . . .
.. Clues: sāmānādhikaraṇya
śvetaḥ aśvaḥ dhāvati.aśvaḥ śvetaḥ asti.
17 / 39
![Page 19: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/19.jpg)
. . . . . .
.. Clues: Nitya Sambandhaḥ
Relation between yat-tat pairyadā - tadāyatra - tatra
18 / 39
![Page 20: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/20.jpg)
. . . . . .
.. Choice of the relations
Should the inflectional suffixes and derivational suffixes betreated at par?How to treat the function words? Should they be treated as anode in a tree or an edge?How to represent the inter sentential relations?Should anaphoric resolution be part of this annotation?
19 / 39
![Page 21: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/21.jpg)
. . . . . .
.. Basic Principles
...1 Preserve one-one mapping between the nodes of a tree andthe words in a sentence.
...2 In case of derived nouns, consider only the inflectional suffixfor establishing the relations.
...3 In case of derived indeclinables, use the derived suffix to markthe relations.
...4 A suffix or a word can represent one and only one relation.
20 / 39
![Page 22: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/22.jpg)
. . . . . .
.. Which relation to mark?
Example: dhāvantam aśvam paśya.
21 / 39
![Page 23: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/23.jpg)
. . . . . .
.. Which relation to mark? Contd...
Example: dhāvantam aśvam paśya.
A loop destroys the nice tree structure of a parse. Hence mark onlyrelations indicated through the inflectional suffixes and not theones indicated through the derivational suffixes.
22 / 39
![Page 24: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/24.jpg)
. . . . . .
.. Which relation? .. contd
What about the faithfulness?
Information is available through the kṛt suffix, which is availablefor marking the relation of kartā at a later stage.
23 / 39
![Page 25: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/25.jpg)
. . . . . .
.. Treating indeclinables:
(1) kṛdanta avyayas:rāmaḥ dugdham pītvā śālām gacchati.
24 / 39
![Page 26: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/26.jpg)
. . . . . .
.. Treating indeclinables:
(1) kṛdanta avyayas:rāmaḥ dugdham pītvā śālām gacchati.
25 / 39
![Page 27: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/27.jpg)
. . . . . .
.. Treating indeclinables:Content / function ?
(2) upapada avyayassītā rāmeṇa saha vanam gacchati.
26 / 39
![Page 28: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/28.jpg)
. . . . . .
.. Treating indeclinables:Content / function ?
(3) Rest of the avyayaseva – avadhāraṇāna – niṣedhya
Number of relations explode.
27 / 39
![Page 29: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/29.jpg)
. . . . . .
.. Treating indeclinables:Content / function ?
(3) Rest of the avyayaseva – avadhāraṇāna – niṣedhya
Number of relations explode.
28 / 39
![Page 30: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/30.jpg)
. . . . . .
.. Inter Sentential Connectivesyadi tvam icchasi tarhi aham bhavataḥ gṛham āgacchāmi.
29 / 39
![Page 31: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/31.jpg)
. . . . . .
.. Treatment of Anaphoras
yatra nāryaḥ pūjyante ramante tatra devatāḥ
30 / 39
![Page 32: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/32.jpg)
. . . . . .
31 / 39
![Page 33: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/33.jpg)
. . . . . .
.. Treatment of Conjunction and Disjunctionrāmaḥ sītā lakṣmaṇaḥ ca vanam gacchanti
32 / 39
![Page 34: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/34.jpg)
. . . . . .
.. GranularityCriterion for Granularity:If one can tell one relation from the other purely on the basis ofsyntax or morphology, then the two relations may be treated asdistinctTradition clasifies kartā into the following subcategories.
anubhavī kartāEx: ghaṭo naśyatiamūrtaḥ kartāEx: krodhaḥ āgacchatiprayojaka kartāEx: devadattaḥ viṣṇumitreṇa pācayati.prayojya kartāEx: devadattaḥ viṣṇumitreṇa pācayati.madhyastha kartāEx: devadattaḥ yajñadattena viṣṇumitreṇa pācayati.abhipreraka / utpreraka kartāEx: modakaḥ rocate.
33 / 39
![Page 35: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/35.jpg)
. . . . . .
.. Granularity ...
karma-kartṛEx: kāṣṭhaḥ svayameva bhidyate.karaṇa-kartṛEx: asiḥ chinatti.ṣaṣṭhī kartāEx: ācāryasya anuśāsanam
34 / 39
![Page 36: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/36.jpg)
. . . . . .
Necessary conditions forprayojaka kartāprayojya kartāṣaṣṭhī kartā
areMorphologySyntax
devadattena annam pācayati. (prayojya kartā)devadattaḥ agninā annam pācayati. (karaṇa)
35 / 39
![Page 37: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/37.jpg)
. . . . . .
asiḥ chinattiHere asiḥ is karaṇakartṛ of chinn only because it is a karaṇa forchinn.
Semantics is involved in the decision.
31 relations: Necessary information for deciding the possibilityinvolves only morphology and Syntactic information.
36 / 39
![Page 38: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/38.jpg)
. . . . . .
.. Set of Relations
kartā prayojyakartāprayojakakartā karmakaraṇam sampradānamapādānam ṣaṣṭhīsambandhaḥadhikaraṇam sambodhanasūcakamsambodhyaḥhetuḥ prayojanamtādarthya niṣedhyaḥkriyāviśeṣaṇam viśeṣaṇamnirdhāraṇam upapadasambandhaḥpratiyogī anuyogīsamuccitam anyataraḥkartṛsamānādhikaraṇam karmasamānādhikaraṇamsamānakālaḥ anantarakālaḥpūrvakālaḥ vīpsāśeṣasambandhaḥ sambandhaḥ
37 / 39
![Page 39: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/39.jpg)
. . . . . .
.. Towards a more useful parse
Treat upapadas as function words rather than content wordsShow the co-indexing for anaphora resolutionShow the sharing of kārakas
38 / 39
![Page 40: Parsing Sanskrit Texts: Some relation specific issues](https://reader030.fdocuments.in/reader030/viewer/2022032501/62343342bf9e0e1b78110c9c/html5/thumbnails/40.jpg)
. . . . . .
DEMO
39 / 39