Views
No views yet
git clone https://github.com/ashishgupta2598/SaCTI.git1conda create --name sactienv python=3.9
2conda activate sactienvpip3 install -r requirements.txt1/save_models_english
2/save_models_marathi
3/save_models_saCTIbase_coarse
4/save_models_saCTIbase_fine
5/save_models_saCTIlarge_coarse
6/save_models_saCTIlarge_fine
7bert model, posdep model and an xlm-roberta-base modelpython3 main.py --model_path='<path to downloaded model>' --experiment='<exp-name>' --training= Falseenglish, marathi, sacti-base_coarse, sacti-base_fine, sacti-large_coarse, sacti-large_finebatch size = 75 and epochs = 70.├── LICENSE
├── README.md
├── save_models_english/
│ ├── bert/
│ │ └── model.pth
│ ├── posdep/
│ │ └── model.pth
│ └── xlm-roberta-base/
│ └── customized-mwt-ner/
│ ├── customized-mwt-ner.tagger.mdl
│ └── customized-mwt-ner.vocabs.json
├── save_models_marathi/
│ └── ... (same structure as above)
├── save_models_saCTIbase_coarse/
│ └── ... (same structure as above)
├── save_models_saCTIbase_fine/
│ └── ... (same structure as above)
├── save_models_saCTIlarge_coarse/
│ └── ... (same structure as above)
└── save_models_saCTIlarge_fine/
└── ... (same structure as above)bert/model.pthposdep/model.pthxlm-roberta-base/customized-mwt-ner/
customized-mwt-ner.tagger.mdl
customized-mwt-ner.vocabs.json
1@inproceedings{sandhan-etal-2022-novel,
2 title = "A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in {S}anskrit",
3 author = "Sandhan, Jivnesh and Gupta, Ashish and Terdalkar, Hrishikesh and Sandhan, Tushar and Samanta, Suvendu and Behera, Laxmidhar and Goyal, Pawan",
4 booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
5 month = oct,
6 year = "2022",
7 address = "Gyeongju, Republic of Korea",
8 publisher = "International Committee on Computational Linguistics",
9 url = "https://aclanthology.org/2022.coling-1.358",
10 pages = "4071--4083",
11 abstract = "The phenomenon of compounding is ubiquitous in Sanskrit. It serves for achieving brevity in expressing thoughts, while simultaneously enriching the lexical and structural formation of the language. In this work, we focus on the Sanskrit Compound Type Identification (SaCTI) task, where we consider the problem of identifying semantic relations between the components of a compound word. Earlier approaches solely rely on the lexical information obtained from the components and ignore the most crucial contextual and syntactic information useful for SaCTI. However, the SaCTI task is challenging primarily due to the implicitly encoded context-sensitive semantic relation between the compound components. Thus, we propose a novel multi-task learning architecture which incorporates the contextual information and enriches the complementary syntactic information using morphological tagging and dependency parsing as two auxiliary tasks. Experiments on the benchmark datasets for SaCTI show 6.1 points (Accuracy) and 7.7 points (F1-score) absolute gain compared to the state-of-the-art system. Further, our multi-lingual experiments demonstrate the efficacy of the proposed architecture in English and Marathi languages.",
12}Apache license 2.0.