Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Pavankumar Satuluri"'
Publikováno v:
Computational Linguistics, Vol 46, Iss 4, Pp 785-845 (2021)
AbstractWe propose a framework using energy-based models for multiple structured prediction tasks in Sanskrit. Ours is an arc-factored model, similar to the graph-based parsing approaches, and we consider the tasks of word segmentation, morphological
Externí odkaz:
https://doaj.org/article/35de6616e60043589aae3d5a815841b3
Publikováno v:
Computational Linguistics. 46:785-845
We propose a framework using energy-based models for multiple structured prediction tasks in Sanskrit. Ours is an arc-factored model, similar to the graph-based parsing approaches, and we consider the tasks of word segmentation, morphological parsing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5dfed8f619520c9e16d3980c4530c52d
https://doi.org/10.1162/coli_a_00390
https://doi.org/10.1162/coli_a_00390
Publikováno v:
EMNLP (1)
Morphologically rich languages seem to benefit from joint processing of morphology and syntax, as compared to pipeline architectures. We propose a graph-based model for joint morphological parsing and dependency parsing in Sanskrit. Here, we extend t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0e0756fcbdf32bafb7466c570a7dc29
https://doi.org/10.18653/v1/2020.emnlp-main.388
https://doi.org/10.18653/v1/2020.emnlp-main.388
Autor:
Bishal Santra, Aishik Chakraborty, Amrith Krishna, Pavankumar Satuluri, Pawan Goyal, Vishnu Dutt Sharma
Publikováno v:
ACL (1)
The word ordering in a Sanskrit verse is often not aligned with its corresponding prose order. Conversion of the verse to its corresponding prose helps in better comprehension of the construction. Owing to the resource constraints, we formulate this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86ea2ff8e4d5ba02b45c42b2636fb9c7
https://doi.org/10.18653/v1/p19-1111
https://doi.org/10.18653/v1/p19-1111
Autor:
Amrith Krishna, Vishnu Dutt Sharma, Bishal Santra, Pavankumar Satuluri, Pawan Goyal, Sasi Prasanth Bandaru, Gaurav Sahu
Publikováno v:
EMNLP
The configurational information in sentences of a free word order language such as Sanskrit is of limited use. Thus, the context of the entire sentence will be desirable even for basic processing tasks such as word segmentation. We propose a structur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f0bd8575d404060da1ee7260293eebf7
Autor:
Gulab Arora, Amrith Krishna, Muneeb Ahmed, Kaustubh Hiware, Pavankumar Satuluri, Harshavardhan Ponnada, Pawan Goyal
Publikováno v:
TextGraphs@ACL
The work is accepted at TextGraphs - 17 colocated with ACL 2017 (http://acl2017.org/) Derivational nouns are widely used in Sanskrit corpora and is a prevalent means of productivity in the language. Currently, there exists no analyser that identifies
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7b54f1b884d7f16dbd754c7e25a5d3b
https://doi.org/10.18653/v1/w17-2409
https://doi.org/10.18653/v1/w17-2409
Publikováno v:
LaTeCH@ACL
The last decade saw a surge in digitisation efforts for ancient manuscripts in Sanskrit. Due to various linguistic peculiarities inherent to the language, even the preliminary tasks such as word segmentation are non-trivial in Sanskrit. Elegant model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abb77d443e2c0863035caaccc7333e90
https://doi.org/10.18653/v1/w17-2214
https://doi.org/10.18653/v1/w17-2214