activity
20182022
most citedA Tweet-based Dataset for Company-Level Stock Return Prediction

4 citations · 17 across the 12 of their papers we have counts for

collaborators

25 papers

cs.NE20222 cited

Exploring the Long-Term Generalization of Counting Behavior in RNNs

Nadine El-Naggar, Pranava Madhyastha, Tillman Weyde

In this study, we investigate the generalization of LSTM, ReLU and GRU models on counting tasks over long sequences. Previous theoretical work has established that RNNs with ReLU a…

cs.CV20222 cited

Belief Revision based Caption Re-ranker with Visual Semantic Information

Ahmed Sabir, Francesc Moreno-Noguer, Pranava Madhyastha +1

In this work, we focus on improving the captions generated by image-caption generation systems. We propose a novel re-ranking approach that leverages visual-semantic measures to id…

cs.CL2021

Numerical reasoning in machine reading comprehension tasks: are we there yet?

Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo

Numerical reasoning based machine reading comprehension is a task that involves reading comprehension along with using arithmetic operations such as addition, subtraction, sorting,…

cs.CL2021

BERTGEN: Multi-task Generation through BERT

Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha +1

We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is a…

cs.LG20211 cited

A call for better unit testing for invariant risk minimisation

Chunyang Xiao, Pranava Madhyastha

In this paper we present a controlled study on the linearized IRM framework (IRMv1) introduced in Arjovsky et al. (2020). We show that IRMv1 (and its variants) framework can be pot…

cs.CL2021

Discrete Reasoning Templates for Natural Language Understanding

Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo

Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that r…