Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit

Krishna, Amrith; Gupta, Ashim; Garasangi, Deepak; Satuluri, Pavankumar; Goyal, Pawan

doi:10.18653/v1/2020.emnlp-main.388

Cited by 6 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ Results: Clearly, the proposed ensembled system outperforms the state of the art purely data-driven system (BiAFF) by 2.8/3.9 points (UAS/LAS) absolute gain. 7 Interestingly, it also supersedes the performance of the hybrid state of the art system [Krishna et al 2020b, MG-EBM] by 1.2 points (UAS) absolute gain and shows comparable performance for LAS metric. We observe that performance of transition-based systems (YAP/L2S) is significantly low compared to graph-based counterparts (BiAFF/Ours).…”

Section: Methodsmentioning

confidence: 88%

See 1 more Smart Citation

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing

Sandhan¹,

Behera²,

Goyal³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Existing state of the art approaches for Sanskrit Dependency Parsing (SDP), are hybrid in nature, and rely on a lexicon-driven shallow parser for linguistically motivated feature engineering. However, these methods fail to handle out of vocabulary (OOV) words, which limits their applicability in realistic scenarios. On the other hand, purely data-driven approaches do not match the performance of hybrid approaches due to the labelled data sparsity. Thus, in this work, we investigate the following question: How far can we push a purely data-driven approach using recently proposed strategies for low-resource settings? We experiment with five strategies, namely, data augmentation, sequential transfer learning, cross-lingual/mono-lingual pretraining, multi-task learning and self-training. Our proposed ensembled system outperforms the purely data-driven state of the art system by 2.8/3.9 points (Unlabelled Attachment Score (UAS)/Labelled Attachment Score (LAS)) absolute gain. Interestingly, it also supersedes the performance of the state of the art hybrid system by 1.2 points (UAS) absolute gain and shows comparable performance in terms of LAS. 1 CCS Concepts: • Computing methodologies → Natural language processing, neural networks.

show abstract

Section: Methodsmentioning

confidence: 88%

“…[BiAFF] is a graph-based approach with BiAFFINE attention mechanism. Krishna et al [2020b][MG-EBM] extends Krishna et al [2020c][Tree-EBM-F] using multi-graph formulation. We report their standalone numbers for fair comparison.…”

Section: Methodsmentioning

confidence: 99%

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing

Sandhan¹,

Behera²,

Goyal³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, the largest freely available repository of translations are for The Bhagavadgita (Prabhakar et al, 2000) and The Rāmāyana (Geervani et al, 1989). However, labeled datasets for other tasks, like the ones proposed in (Kulkarni, 2013;Bhardwaj et al, 2018; have resulted in parsers (Krishna et al, 2020(Krishna et al, , 2021 and sandhi splitters (Aralikatte et al, 2018; which are pre-cursors to modular translation systems. Though there have been attempts at building Sanskrit translation tools (Bharati and Kulkarni, 2009), they are mostly rule-based and rely on manual intervention.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 8th Workshop on Asian Translation (WAT2021)

Nakazawa¹,

Goto²

2021

View full text Add to dashboard Cite

Many Asian countries are rapidly growing these days and the importance of communicating and exchanging the information with these countries has intensified. To satisfy the demand for communication among these countries, machine translation technology is essential.Machine translation technology has rapidly evolved recently and it is seeing practical use especially between European languages. However, the translation quality of Asian languages is not that high compared to that of European languages, and machine translation technology for these languages has not reached a stage of proliferation yet. This is not only due to the lack of the language resources for Asian languages but also due to the lack of techniques to correctly transfer the meaning of sentences from/to Asian languages. Consequently, a place for gathering and sharing the resources and knowledge about Asian language translation is necessary to enhance machine translation research for Asian languages.

show abstract

Section: Related Workmentioning

confidence: 99%

Itihasa: A large-scale corpus for Sanskrit to English translation

Aralikatte¹,

Lhoneux²,

Kunchukuttan³

et al. 2021

Preprint

View full text Add to dashboard Cite

This work introduces Itihāsa, a large-scale translation dataset containing 93,000 pairs of Sanskrit shlokas and their English translations. The shlokas are extracted from two Indian epics viz., The Rāmāyana and The Mahābhārata. We first describe the motivation behind the curation of such a dataset and follow up with empirical analysis to bring out its nuances. We then benchmark the performance of standard translation models on this corpus and show that even state-of-the-art transformer architectures perform poorly, emphasizing the complexity of the dataset. 1

show abstract

Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit

Cited by 6 publications

References 20 publications

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing

Proceedings of the 8th Workshop on Asian Translation (WAT2021)

Itihasa: A large-scale corpus for Sanskrit to English translation

Contact Info

Product

Resources

About