HLDC: Hindi Legal Documents Corpus

Findings of the Association for Computational Linguistics: ACL 2022, pages 3521 - 3536 May 22-27, 2022 c⃝2022 Association for Computational Linguistics HLDC: Hindi Legal Documents Corpus Arnav Kapoor†, Mudit Dhawan‡, Anmol Goel†, T.H. Arjun†, Akshala Bhatnagar‡, Vibhu Agrawal‡, Amul Agrawal†, Arnab Bhattacharya¶, Ponnurangam Kumaraguru†, Ashutosh Modi¶∗ †IIIT Hyderabad, ‡IIIT Delhi, ¶IIT Kanpur {arnav.kapoor,anmol.goel,arjun.thekoot}@research.iiit.ac.in {mudit18159,akshala18012,vibhu18116}@iiitd.ac.in, amul.agrawal@students.iiit.ac.in, arnabb@cse.iitk.ac.in, pk.guru@iiit.ac.in, ashutoshm@cse.iitk.ac.in Abstract Many populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment legal practitioners can mitigate this. However, there is a dearth of high-quality corpora that is needed to develop such data-driven systems. The problem gets even more pronounced in the case of low resource languages such as Hindi. In this resource paper, we introduce the Hindi Legal Documents Corpus (HLDC), a corpus of more than 900K legal documents in Hindi. Documents are cleaned and structured to en- able the development of downstream applica- tions. Further, as a use-case for the corpus, we introduce the task of bail prediction. We ex- periment with a battery of models and propose a Multi-Task Learning (MTL) based model for the same. MTL models use summarization as an auxiliary task along with bail prediction as the main task. Experiments with different models are indicative of the need for further research in this area. 1 Introduction In recent times, the legal system in many populous countries (e.g., India) has been inundated with a large number of legal documents and pending cases (Katju, 2019). There is an imminent need for automated systems to process legal documents and help augment the legal procedures. For example, if a system could readily extract the required in- formation from a legal document for a legal prac- titioner, then it would help expedite the legal pro- cess. However, the processing of legal documents is challenging and is quite different from conven- tional text processing tasks. For example, legal documents are typically quite long (tens of pages), highly unstructured and noisy (spelling and gram- mar mistakes since these are typed), use domain- specific language and jargon; consequently, pre- ∗Corresponding Author trained language models do not perform well on these (Malik et al., 2021b). Thus, to develop legal text processing systems and address the challenges associated with the legal domain, there is a need for creating specialized legal domain corpora. In recent times, there have been efforts to de- velop such corpora. For example, Chalkidis et al. (2019) have developed an English corpus of Eu- ropean Court of Justice documents, while Ma- lik et al. (2021b) have developed an English cor- pus of Indian Supreme Court documents. Xiao et al. (2018) have developed Chinese Legal Docu- ment corpus. However, to the best of our knowl- edge, there does not exist any legal document cor- pus for the Hindi language (a language belonging to the Indo-European family and pre-dominantly spoken in India). Hindi uses Devanagari script (Wikipedia contributors, 2021) for the writing sys- tem. Hindi is spoken by approximately 567 mil- lion …

Content truncated to 500 words