Search Results for author: Amrith Krishna

Found 24 papers, 10 papers with code

A Graph-Based Framework for Structured Prediction Tasks in Sanskrit

no code implementations CL (ACL) 2020 Amrith Krishna, Bishal Santra, Ashim Gupta, Pavankumar Satuluri, Pawan Goyal

Ours is a search-based structured prediction framework, which expects a graph as input, where relevant linguistic information is encoded in the nodes, and the edges are then used to indicate the association between these nodes.

Dependency Parsing Structured Prediction

A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs

no code implementations25 Jun 2024 Vaibhav Singh, Amrith Krishna, Karthika NJ, Ganesh Ramakrishnan

Low-resource languages, by its very definition, tend to be under represented in the pre-training corpora of Large Language Models.

Cross-Lingual Transfer In-Context Learning

Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems

no code implementations31 May 2023 Ashim Gupta, Amrith Krishna

Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling function.

Data Poisoning text-classification +1

Sāmayik: A Benchmark and Dataset for English-Sanskrit Translation

1 code implementation23 May 2023 Ayush Maheshwari, Ashim Gupta, Amrith Krishna, Atul Kumar Singh, Ganesh Ramakrishnan, G. Anil Kumar, Jitin Singla

Translation models trained on our dataset demonstrate statistically significant improvements when translating out-of-domain contemporary corpora, outperforming models trained on older classical-era poetry datasets.

Machine Translation Translation

A Benchmark and Dataset for Post-OCR text correction in Sanskrit

1 code implementation15 Nov 2022 Ayush Maheshwari, Nikhil Singh, Amrith Krishna, Ganesh Ramakrishnan

Keeping this in mind, we release a multi-domain dataset, from areas as diverse as astronomy, medicine and mathematics, with some of them as old as 18 centuries.

Astronomy Optical Character Recognition (OCR)

ProoFVer: Natural Logic Theorem Proving for Fact Verification

1 code implementation25 Aug 2021 Amrith Krishna, Sebastian Riedel, Andreas Vlachos

Fact verification systems typically rely on neural network classifiers for veracity prediction which lack explainability.

Automated Theorem Proving counterfactual +3

Evaluating Neural Morphological Taggers for Sanskrit

1 code implementation WS 2020 Ashim Gupta, Amrith Krishna, Pawan Goyal, Oliver Hellwig

Neural sequence labelling approaches have achieved state of the art results in morphological tagging.

Morphological Tagging

SHR++: An Interface for Morpho-syntactic Annotation of Sanskrit Corpora

1 code implementation LREC 2020 Amrith Krishna, Shiv Vidhyut, Dilpreet Chawla, Sruti Sambhavi, Pawan Goyal

It incorporates analyses and predictions from various tools designed for processing texts in Sanskrit, and utilise them to ease the cognitive load of the human annotators.

Decision Making Segmentation +1

Neural Approaches for Data Driven Dependency Parsing in Sanskrit

no code implementations17 Apr 2020 Amrith Krishna, Ashim Gupta, Deepak Garasangi, Jivnesh Sandhan, Pavankumar Satuluri, Pawan Goyal

We compare the performance of each of the models in a low-resource setting, with 1, 500 sentences for training.

Dependency Parsing

Compound Type Identification in Sanskrit: What Roles do the Corpus and Grammar Play?

no code implementations WS 2016 Amrith Krishna, Pavankumar Satuluri, Shubham Sharma, Apurv Kumar, Pawan Goyal

We construct an elaborate features space for our system by combining conditional rules from the grammar \textit{Adṣṭ{\=a}dhy{\=a}y{\=\i}}, semantic relations between the compound components from a lexical database \textit{Amarakoṣa} and linguistic structures from the data using Adaptor Grammars.

Classification General Classification +2

Towards automating the generation of derivative nouns in Sanskrit by simulating Panini

no code implementations17 Dec 2015 Amrith Krishna, Pawan Goyal

We also present cases where we have checked the applicability of the system with the rules which are not specifically applicable to derivation of derivative nouns, in order to see the effectiveness of the proposed schema as a generic system for modeling Astadhyayi.

Cannot find the paper you are looking for? You can Submit a new open access paper.