A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit

August 22, 2022 ยท Entered Twilight ยท ๐Ÿ› International Conference on Computational Linguistics

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: LICENSE.md, README.md, Trakit_macro_UAS_LAS.py, __init__.py, __main__.py, __pycache__, adapter_transformers, attention_weights, combine.pks.conll, config.py, data, data_config.py, eval_matrix.txt, generate_report.py, iterators, layers, main.py, models, pipeline.py, requirements.txt, saCTI-base coarseeval_matrix.txt, saCTI-base fineeval_matrix.txt, tests, tpipeline.py, utils

Authors Jivnesh Sandhan, Ashish Gupta, Hrishikesh Terdalkar, Tushar Sandhan, Suvendu Samanta, Laxmidhar Behera, Pawan Goyal arXiv ID 2208.10310 Category cs.CL: Computation & Language Citations 7 Venue International Conference on Computational Linguistics Repository https://github.com/ashishgupta2598/SaCTI โญ 3 Last Checked 1 month ago
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.The code and datasets are publicly available at https://github.com/ashishgupta2598/SaCTI
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 8 years ago