activity
20182022
most citedImproving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering

10 citations · 16 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CL2022★ 10 cited

Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering

Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen +3

Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledg…

cs.IR2021★ 4 cited

Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering

Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen +1

In this paper, we illustrate how to fine-tune the entire Retrieval Augment Generation (RAG) architecture in an end-to-end manner. We highlighted the main engineering challenges tha…

eess.AS2020★ 2 cited

Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Shamane Siriwardhana, Andrew Reis, Rivindu Weerasekera +1

Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled…

cs.LG2019

VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation

Shamane Siriwardhana, Rivindu Weerasakera, Denys J. C. Matthies +1

In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulato…

cs.AI2018

Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations

Shamane Siriwardhana, Rivindu Weerasekera, Suranga Nanayakkara

Being able to navigate to a target with minimal supervision and prior knowledge is critical to creating human-like assistive agents. Prior work on map-based and map-less approaches…