Author name cluster

Rahul Goel

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2024 Conference Paper

GSN: Generalisable Segmentation in Neural Radiance Field

Vinayak Gupta
Rahul Goel
Sirikonda Dhawal
P. J. Narayanan

Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/

PDF Details DOI

ECAI Conference 2024 Conference Paper

Translation and Transliteration Based Data Augmentation for Multilingual Semantic Parsing

Sarthak Jauhari
Massimo Nicosia
Ankush Chatterjee
Rahul Goel

Multilingual semantic parsing is one of the natural language understanding tasks powering modern virtual assistants. Annotating training data for supporting all languages is expensive and methods that rely on machine translation and label projection are used to perform language adaptation. In this paper, we revisit the assumption that a separate label projection step is necessary, with the goal of saving compute and reducing the complexity of the data augmentation pipeline. We create synthetic training examples by applying translation and transliteration directly at the slot level. We show that without a dedicated and expensive label projection component, we are able to achieve 97% of state-of-the-art data augmentation performance on multilingual semantic parsing, and obtain the same performance of the best systems for code mixed and code switched semantic parsing.

Details

AAAI Conference 2019 Conference Paper

Online Embedding Compression for Text Classification Using Low Rank Matrix Factorization

Anish Acharya
Rahul Goel
Angeliki Metallinou
Inderjit Dhillon

Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during training, to compress the word embedding layer which represents the size bottleneck for most NLP models. Our models are trained, compressed and then further re-trained on the downstream task to recover accuracy while maintaining the reduced size. Empirically, we show that the proposed method can achieve 90% compression with minimal impact in accuracy for sentence classification tasks, and outperforms alternative methods like fixed-point quantization or offline word embedding compression. We also analyze the inference time and storage space for our method through FLOP calculations, showing that we can compress DNN models by a configurable ratio and regain accuracy loss without introducing additional latency compared to fixed point quantization. Finally, we introduce a novel learning rate schedule, the Cyclically Annealed Learning Rate (CALR), which we empirically demonstrate to outperform other popular adaptive learning rate algorithms on a sentence classification benchmark.

PDF Details

AAAI Conference 2018 Conference Paper

Context Aware Conversational Understanding for Intelligent Agents With a Screen

Vishal Naik
Angeliki Metallinou
Rahul Goel

We describe an intelligent context-aware conversational system that incorporates screen context information to service multimodal user requests. Screen content is used for disambiguation of utterances that refer to screen objects and for enabling the user to act upon screen objects using voice commands. We propose a deep learning architecture that jointly models the user utterance and the screen and incorporates detailed screen content features. Our model is trained to optimize end to end semantic accuracy across contextual and non-contextual functionality, therefore learns the desired behavior directly from the data. We show that this approach outperforms a rule-based alternative, and can be extended in a straightforward manner to new contextual use cases. We perform detailed evaluation of contextual and non-contextual use cases and show that our system displays accurate contextual behavior without degrading the performance of noncontextual user requests.

PDF Details