Rahul's webpage

Rahul Aralikatte

I am a Postdoctoral Researcher at Mila - Quebec AI Institute working with Prof. Jackie Cheung, currently visiting Google Research. I also closely collaborate with AI4Bharat and build tools for Indic NLP. I finished my Ph.D. at the CoAStaL NLP lab at the University of Copenhagen under the supervision of Prof. Anders Søgaard. I do a bit of everything NLP, but currently focussed on text summarization and low-resource learning.

Recent News

Dec 2023	Helped organize the 1st Shared Task on Multi-lingual Multi-task Information Retrieval (findings)
Dec 2023	Our model submission was placed third in the BabyLM shared task at EMNLP 2023.
Oct 2023	"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization" accepted in CONLL 2023.
May 2023	Two papers accepted in ACL 2023 (IndicXTREME and Vārta).
May 2023	New preprint: Vārta: A Large-Scale Headline-Generation Dataset for Indic Languages
Dec 2022	IndicXTREME and IndicBERT v2 released. You can read the preprint here.
Nov 2022	Started as a visiting researcher at Google.
Aug 2022	Joined MILA as a postdoctoral researcher.

Publications

2023

McGill BabyLM Shared Task Submission: The Effects of Data Formatting and Structural Biases. EMNLP 2023
Ziling Cheng, Rahul Aralikatte, Ian Porada, Cesare Spinoso-Di Piano, Jackie CK Cheung
Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization. CONLL 2023
Ondrej Skopek, Rahul Aralikatte, Sian Gooding, Victor Carbune
Vārta: A Large-Scale Headline-Generation Dataset for Indic Languages. Findings of ACL 2023
Rahul Aralikatte*, Ziling Cheng*, Sumanth Doddapaneni, Jackie Chi Kit Cheung
Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages. ACL 2023
Sumanth Doddapaneni, Rahul Aralikatte, Gowtham Ramesh, Shreya Goyal, Mitesh M. Khapra, Anoop Kunchukuttan, Pratyush Kumar

2022

Compositional Generalization in Multilingual Semantic Parsing over Wikidata. Transactions of ACL 2022
Ruixiang Cui, Rahul Aralikatte, Heather Lent, Daniel Hershcovich

2021

Itihāsa: A large-scale corpus for Sanskrit to English translation. WAT at ACL 2021
Rahul Aralikatte, Miryam de Lhoneux, Anoop Kunchukuttan, Anders Søgaard
How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task. WAT at ACL 2021
Rahul Aralikatte, Héctor Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, Anders Søgaard
Focus Attention: Promoting Faithfulness and Diversity in Summarization. ACL 2021.
Rahul Aralikatte, Shashi Narayan, Joshua Maynez, Sascha Rothe, Ryan T. McDonald
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages. Findings of ACL 2021.
Edoardo Maria Ponti*, Rahul Aralikatte*, Disha Shrivastava, Siva Reddy, Anders Søgaard
Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task. NLP for Indigenous Languages of the Americas at NAACL 2021
Marcel Bollmann, Rahul Aralikatte, Héctor Murrieta Bello, Daniel Hershcovich, Miryam de Lhoneux, Anders Søgaard
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards. AAAI 2021.
Rahul Aralikatte, Mostafa Abdou, Heather C. Lent, Daniel Hershcovich, Anders Søgaard
Ellipsis Resolution as Question Answering: An Evaluation. EACL 2021.
Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard

2020

Rahul Aralikatte, Anders Søgaard

2019

Rewarding Coreference Resolvers for Being Consistent with World Knowledge. EMNLP-IJCNLP 2019.
Rahul Aralikatte, Heather C. Lent, Ana Valeria González-Garduño, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
Compositional Generalization in Image Captioning. CONLL 2019.
Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte, Desmond Elliott
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension. DeepLo at EMNLP-IJCNLP 2019.
Mostafa Abdou, Cezar Sas, Rahul Aralikatte, Isabelle Augenstein, Anders Søgaard
Adversarial Black-Box Attacks for Automatic Speech Recognition Systems Using Multi-Objective Genetic Optimization. Interspeech 2019.
Shreya Khare, Rahul Aralikatte, Senthil Mani
DeepTriage: Exploring the Effectiveness of Deep Learning for Bug Triaging. COMAD/CODS 2019.
Senthil Mani, Anush Sankaran, Rahul Aralikatte
A Visual Programming Paradigm for Abstract Deep Learning Model Development. India HCI 2019.
Srikanth Tamilselvam, Naveen Panwar, Shreya Khare, Rahul Aralikatte, Anush Sankaran, Senthil Mani

2018

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension. ACL 2018.
Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan
Sanskrit Sandhi Splitting using seq2(seq)2. EMNLP 2018.
Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani
Hi, How Can I Help You?: Automating Enterprise IT Support Help Desks. IAAI 2018.
Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan
Agent Assist: Automating Enterprise IT Support Help Desks. AAAI 2018.
Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan
Democratization of Deep Learning Using DARVIZ. AAAI 2018.
Anush Sankaran, Naveen Panwar, Shreya Khare, Senthil Mani, Akshay Sethi, Rahul Aralikatte, Neelamadhav Gantayat
Fault in your stars: An Analysis of Android App Reviews. COMAD/CODS 2018.
Rahul Aralikatte, Giriprasad Sridhara, Neelamadhav Gantayat, Senthil Mani

2017

DARVIZ: Deep Abstract Representation, Visualization, and Verification of Deep Learning Models. ICSE NIER 2017.
Anush Sankaran, Rahul Aralikatte, Senthil Mani, Shreya Khare, Naveen Panwar, Neelamadhav Gantayat
mAnI: Movie Amalgamation using Neural Imitation. ML4Creativity workshop at KDD 2017.
Naveen Panwar, Shreya Khare, Neelamadhav Gantayat, Rahul Aralikatte, Senthil Mani, Anush Sankaran

2015

Phoenix: A Self-Optimizing Chess Engine. CICN 2015.
Rahul Aralikatte, G Srinivasaraghavan

Patents

Debugging deep neural networks
Rahul Aralikatte, Srikanth Govindaraj Tamilselvam, Shreya Khare, Naveen Panwar, Anush Sankaran, Senthil Kumar Kumarasamy Mani
Multi-Modal Construction of Deep Learning Networks
Rahul Aralikatte, Neelamadhav Gantayat, Shreya Khare, Senthil Kumar Kumarasamy Mani, Naveen Panwar, Anush Sankaran
Suggestion and Completion of Deep Learning Models from a Catalog
Anush Sankaran, Naveen Panwar, Srikanth Govindaraj Tamilselvam, Shreya Khare, Rahul Aralikatte, Senthil Kumar Kumarasamy Mani
Deep-learning model catalog creation
Shreya Khare, Srikanth Govindaraj Tamilselvam, Anush Sankaran, Naveen Panwar, Rahul Aralikatte, Senthil Kumar Kumarasamy Mani
Collaborative deep learning model authoring tool
Anush Sankaran, Rahul Aralikatte, Shreya Khare, Naveen Panwar, Senthil Kumar Kumarasamy Mani, Srikanth Govindaraj Tamilselvam
Application recommendation based on permissions
Rahul Aralikatte, Vijay Ekambaram, Senthil Kumar Kumarasamy Mani, Giriprasad Sridhara
Mobile application update manager
Giriprasad Sridhara, Rahul Aralikatte, Senthil Kumar Kumarasamy Mani, Vijay Ekambaram

Past Industry Experience

Internship at Google Research (2020)
Research Engineer at IBM Research (2015-2018)
Software Engineer at Cisco Systems (2014-2015)

Service

Reviewer

AAAI (2020-2022)
AACL (2020-2022)
ACL (2019-2022)
COLING (2020-2022)
EACL (2021-2022)
EMNLP (2019-2022)
ICLR (2020-2022)
NAACL (2021-2022)
NeurIPS (2021-2022)

Misc.

Mila hiring committe member (2022)