no code implementations • NAACL (AmericasNLP) 2021 • Marcel Bollmann, Rahul Aralikatte, Héctor Murrieta Bello, Daniel Hershcovich, Miryam de Lhoneux, Anders Søgaard
We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios.
no code implementations • ACL (WAT) 2021 • Rahul Aralikatte, Héctor Ricardo Murrieta Bello, Miryam de Lhoneux, Daniel Hershcovich, Marcel Bollmann, Anders Søgaard
This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization.
no code implementations • 19 Mar 2024 • Victor Carbune, Hassan Mansoor, Fangyu Liu, Rahul Aralikatte, Gilles Baechler, Jindong Chen, Abhanshu Sharma
We propose a technique to transfer capabilities from LLMs to VLMs.
Ranked #1 on Chart Question Answering on ChartQA (using extra training data)
Chart Question Answering Optical Character Recognition (OCR)
no code implementations • 12 Oct 2023 • Ondrej Skopek, Rahul Aralikatte, Sian Gooding, Victor Carbune
Despite recent advances, evaluating how well large language models (LLMs) follow user instructions remains an open problem.
1 code implementation • 10 May 2023 • Rahul Aralikatte, Ziling Cheng, Sumanth Doddapaneni, Jackie Chi Kit Cheung
We present V\=arta, a large-scale multilingual dataset for headline generation in Indic languages.
1 code implementation • 11 Dec 2022 • Sumanth Doddapaneni, Rahul Aralikatte, Gowtham Ramesh, Shreya Goyal, Mitesh M. Khapra, Anoop Kunchukuttan, Pratyush Kumar
Across languages and tasks, IndicXTREME contains a total of 105 evaluation sets, of which 52 are new contributions to the literature.
1 code implementation • 7 Aug 2021 • Ruixiang Cui, Rahul Aralikatte, Heather Lent, Daniel Hershcovich
We introduce such a dataset, which we call Multilingual Compositional Wikidata Questions (MCWQ), and use it to analyze the compositional generalization of semantic parsers in Hebrew, Kannada, Chinese and English.
no code implementations • ACL (WAT) 2021 • Rahul Aralikatte, Miryam de Lhoneux, Anoop Kunchukuttan, Anders Søgaard
This work introduces Itihasa, a large-scale translation dataset containing 93, 000 pairs of Sanskrit shlokas and their English translations.
Ranked #1 on Machine Translation on Itihasa
1 code implementation • 2 Jun 2021 • Edoardo Maria Ponti, Rahul Aralikatte, Disha Shrivastava, Siva Reddy, Anders Søgaard
In fact, under a decision-theoretic framework, MAML can be interpreted as minimising the expected risk across training languages (with a uniform prior), which is known as Bayes criterion.
no code implementations • ACL 2021 • Rahul Aralikatte, Shashi Narayan, Joshua Maynez, Sascha Rothe, Ryan Mcdonald
Professional summaries are written with document-level information, such as the theme of the document, in mind.
1 code implementation • 12 Oct 2020 • Rahul Aralikatte, Mostafa Abdou, Heather Lent, Daniel Hershcovich, Anders Søgaard
Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, and what semantic roles expressions serve in the sentence.
1 code implementation • CONLL 2019 • Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte, Desmond Elliott
Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts.
1 code implementation • IJCNLP 2019 • Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
Unresolved coreference is a bottleneck for relation extraction, and high-quality coreference resolvers may produce an output that makes it a lot easier to extract knowledge triples.
1 code implementation • EACL 2021 • Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard
Most, if not all forms of ellipsis (e. g., so does Mary) are similar to reading comprehension questions (what does Mary do), in that in order to resolve them, we need to identify an appropriate text span in the preceding discourse.
1 code implementation • WS 2019 • Mostafa Abdou, Cezar Sas, Rahul Aralikatte, Isabelle Augenstein, Anders Søgaard
Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in different languages.
1 code implementation • LREC 2020 • Rahul Aralikatte, Anders Søgaard
Humans do not make inferences over texts, but over models of what texts are about.
no code implementations • 7 May 2019 • Srikanth Tamilselvam, Naveen Panwar, Shreya Khare, Rahul Aralikatte, Anush Sankaran, Senthil Mani
Deep learning is one of the fastest growing technologies in computer science with a plethora of applications.
no code implementations • 4 Nov 2018 • Shreya Khare, Rahul Aralikatte, Senthil Mani
Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • EMNLP 2018 • Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi.
1 code implementation • ACL 2018 • Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan
We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.
no code implementations • 4 Jan 2018 • Senthil Mani, Anush Sankaran, Rahul Aralikatte
Using an attention mechanism enables the model to learn the context representation over a long word sequence, as in a bug report.
no code implementations • 1 Jan 2018 • Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, Senthil Mani
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi.
no code implementations • 2 Nov 2017 • Senthil Mani, Neelamadhav Gantayat, Rahul Aralikatte, Monika Gupta, Sampath Dechu, Anush Sankaran, Shreya Khare, Barry Mitchell, Hemamalini Subramanian, Hema Venkatarangan
Question answering is one of the primary challenges of natural language understanding.
no code implementations • 16 Aug 2017 • Rahul Aralikatte, Giriprasad Sridhara, Neelamadhav Gantayat, Senthil Mani
Further, we developed three systems; two of which were based on traditional machine learning and one on deep learning to automatically identify reviews whose rating did not match with the opinion expressed in the review.
no code implementations • 16 Aug 2017 • Naveen Panwar, Shreya Khare, Neelamadhav Gantayat, Rahul Aralikatte, Senthil Mani, Anush Sankaran
Cross-modal data retrieval has been the basis of various creative tasks performed by Artificial Intelligence (AI).
no code implementations • 30 Mar 2016 • Rahul Aralikatte, G. Srinivasaraghavan
With the advent of deep learning, chess playing agents can surpass human ability with relative ease.