Search Results - "Aralikatte, Rahul"

Compositional Generalization in Multilingual Semantic Parsing over Wikidata by Cui, Ruixiang, Aralikatte, Rahul, Lent, Heather, Hershcovich, Daniel

“…Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on…”
Get full text

Model-based annotation of coreference by Aralikatte, Rahul, Søgaard, Anders

“…Humans do not make inferences over texts, but over models of what texts are about. When annotators are asked to annotate coreferent spans of text, it is…”
Get full text

Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization by Skopek, Ondrej, Aralikatte, Rahul, Gooding, Sian, Carbune, Victor

“…Despite recent advances, evaluating how well large language models (LLMs) follow user instructions remains an open problem. While evaluation methods of…”
Get full text

V\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages by Aralikatte, Rahul, Cheng, Ziling, Doddapaneni, Sumanth, Cheung, Jackie Chi Kit

“…We present V\=arta, a large-scale multilingual dataset for headline generation in Indic languages. This dataset includes 41.8 million news articles in 14…”
Get full text

Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs by Carbune, Victor, Mansoor, Hassan, Liu, Fangyu, Aralikatte, Rahul, Baechler, Gilles, Chen, Jindong, Sharma, Abhanshu

“…Vision-language models (VLMs) are achieving increasingly strong performance on multimodal tasks. However, reasoning capabilities remain limited particularly…”
Get full text

Compositional Generalization in Multilingual Semantic Parsing over Wikidata by Cui, Ruixiang, Aralikatte, Rahul, Lent, Heather, Hershcovich, Daniel

“…Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on…”
Get full text

Itihasa: A large-scale corpus for Sanskrit to English translation by Aralikatte, Rahul, de Lhoneux, Miryam, Kunchukuttan, Anoop, Søgaard, Anders

“…This work introduces Itihasa, a large-scale translation dataset containing 93,000 pairs of Sanskrit shlokas and their English translations. The shlokas are…”
Get full text

Focus Attention: Promoting Faithfulness and Diversity in Summarization by Aralikatte, Rahul, Narayan, Shashi, Maynez, Joshua, Rothe, Sascha, McDonald, Ryan

“…Professional summaries are written with document-level information, such as the theme of the document, in mind. This is in contrast with most seq2seq decoders…”
Get full text

Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages by Doddapaneni, Sumanth, Aralikatte, Rahul, Ramesh, Gowtham, Goyal, Shreya, Khapra, Mitesh M, Kunchukuttan, Anoop, Kumar, Pratyush

“…Building Natural Language Understanding (NLU) capabilities for Indic languages, which have a collective speaker base of more than one billion speakers is…”
Get full text

Phoenix: A Self-Optimizing Chess Engine by Aralikatte, Rahul, Srinivasaraghavan, G

“…Since the advent of computers, many tasks which required humans to spend a lot of time and energy have been trivialized by the computers' ability to perform…”
Get full text

Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards by Aralikatte, Rahul, Abdou, Mostafa, Lent, Heather, Hershcovich, Daniel, Søgaard, Anders

“…Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer…”
Get full text

Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization by Khare, Shreya, Aralikatte, Rahul, Mani, Senthil

“…Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both…”
Get full text

Minimax and Neyman-Pearson Meta-Learning for Outlier Languages by Ponti, Edoardo Maria, Aralikatte, Rahul, Shrivastava, Disha, Reddy, Siva, Søgaard, Anders

“…Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the…”
Get full text

DeepTriage: Exploring the Effectiveness of Deep Learning for Bug Triaging by Mani, Senthil, Sankaran, Anush, Aralikatte, Rahul

“…For a given software bug report, identifying an appropriate developer who could potentially fix the bug is the primary task of a bug triaging process. A bug…”
Get full text

Ellipsis Resolution as Question Answering: An Evaluation by Aralikatte, Rahul, Lamm, Matthew, Hardt, Daniel, Søgaard, Anders

“…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,…”
Get full text

X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension by Abdou, Mostafa, Sas, Cezar, Aralikatte, Rahul, Augenstein, Isabelle, Søgaard, Anders

“…Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in different languages…”
Get full text

Fault in your stars: An Analysis of Android App Reviews by Aralikatte, Rahul, Sridhara, Giriprasad, Gantayat, Neelamadhav, Mani, Senthil

“…Mobile app distribution platforms such as Google Play Store allow users to share their feedback about downloaded apps in the form of a review comment and a…”
Get full text

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension by Saha, Amrita, Aralikatte, Rahul, Khapra, Mitesh M, Sankaranarayanan, Karthik

“…We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond…”
Get full text

Sanskrit Sandhi Splitting using seq2(seq)^2 by Aralikatte, Rahul, Gantayat, Neelamadhav, Panwar, Naveen, Sankaran, Anush, Mani, Senthil

“…In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a…”
Get full text

Compositional Generalization in Image Captioning by Nikolaus, Mitja, Abdou, Mostafa, Lamm, Matthew, Aralikatte, Rahul, Elliott, Desmond

“…Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pp. 87--98, ACL, 2019 Image captioning models are usually evaluated on…”
Get full text