English
Related papers

Related papers: Improving QA Efficiency with DistilBERT: Fine-Tuni…

200 papers

The remarkable success of large transformer-based models such as BERT, RoBERTa and XLNet in many NLP tasks comes with a large increase in monetary and environmental cost due to their high computational load and energy consumption. In order…

Computation and Language · Computer Science 2022-04-14 Jonathan Mamou , Oren Pereg , Moshe Wasserblat , Roy Schwartz

Question-answering (QA) models have advanced significantly in machine reading comprehension but often exhibit biases that hinder their performance, particularly with complex queries in adversarial conditions. This study evaluates the…

Computation and Language · Computer Science 2026-01-21 Yuefeng Wang , ChangJae Lee

We present a highly parameter efficient approach for Question Answering that significantly reduces the need for extended BERT fine-tuning. Our method uses information from the hidden state activations of each BERT transformer layer, which…

Computation and Language · Computer Science 2022-02-25 Siduo Jiang , Cristopher Benge , William Casey King

As machine learning gets deployed more and more widely, and model sizes continue to grow, improving computational efficiency during model inference has become a key challenge. In many commonly used model architectures, including…

Machine Learning · Computer Science 2024-12-03 Sai Kiran Narayanaswami , Gopalakrishnan Srinivasan , Balaraman Ravindran

Motivated by the emerging demand in the financial industry for the automatic analysis of unstructured and structured data at scale, Question Answering (QA) systems can provide lucrative and competitive advantages to companies by…

Computation and Language · Computer Science 2025-05-05 Bithiah Yuan

Question answering (QA) models are well-known to exploit data bias, e.g., the language prior in visual QA and the position bias in reading comprehension. Recent debiasing methods achieve good out-of-distribution (OOD) generalizability with…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Yulei Niu , Hanwang Zhang

This paper presents the design of a hardware accelerator for Transformers, optimized for on-device time-series forecasting in AIoT systems. It integrates integer-only quantization and Quantization-Aware Training with optimized hardware…

Machine Learning · Computer Science 2026-04-22 Tianheng Ling , Chao Qian , Gregor Schiele

Recently, large pre-trained models have significantly improved the performance of various Natural LanguageProcessing (NLP) tasks but they are expensive to serve due to long serving latency and large memory usage. To compress these models,…

Machine Learning · Computer Science 2022-01-24 Xiaofan Zhang , Zongwei Zhou , Deming Chen , Yu Emma Wang

This work focuses on the efficiency of the knowledge distillation approach in generating a lightweight yet powerful BERT based model for natural language processing applications. After the model creation, we applied the resulting model,…

Computation and Language · Computer Science 2024-11-04 Ahmed Akib Jawad Karim , Kazi Hafiz Md. Asad , Md. Golam Rabiul Alam

Understanding the deep meanings of the Qur'an and bridging the language gap between modern standard Arabic and classical Arabic is essential to improve the question-and-answer system for the Holy Qur'an. The Qur'an QA 2023 shared task…

Computation and Language · Computer Science 2024-12-17 Mohamed Basem , Islam Oshallah , Baraa Hikal , Ali Hamdi , Ammar Mohamed

In this work, we describe our experiments and participating systems in the BioASQ Task 9b Phase B challenge of biomedical question answering. We have focused on finding the ideal answers and investigated multi-task fine-tuning and gradual…

Computation and Language · Computer Science 2021-09-16 Urvashi Khanna , Diego Mollá

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-02-28 Daniele Paliotta , Junxiong Wang , Matteo Pagliardini , Kevin Y. Li , Aviv Bick , J. Zico Kolter , Albert Gu , François Fleuret , Tri Dao

Question-answering (QA) on hybrid scientific tabular and textual data deals with scientific information, and relies on complex numerical reasoning. In recent years, while tabular QA has seen rapid progress, understanding their robustness on…

Computation and Language · Computer Science 2024-04-02 Akash Ghosh , B Venkata Sahith , Niloy Ganguly , Pawan Goyal , Mayank Singh

It is challenging to automatically evaluate the answer of a QA model at inference time. Although many models provide confidence scores, and simple heuristics can go a long way towards indicating answer correctness, such measures are heavily…

Computation and Language · Computer Science 2020-10-08 Lukas Muttenthaler , Isabelle Augenstein , Johannes Bjerva

High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel optimized deep learning…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Jiong Gong , Haihao Shen , Guoming Zhang , Xiaoli Liu , Shane Li , Ge Jin , Niharika Maheshwari , Evarist Fomenko , Eden Segal

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 David E. Hernandez , Jose Chang , Torbjörn E. M. Nordling

This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…

Machine Learning · Computer Science 2026-03-31 Soutrik Mukherjee , Sangwhan Cha

State-of-the-art extractive question-answering models achieve superhuman performances on the SQuAD benchmark. Yet, they are unreasonably heavy and need expensive GPU computing to answer questions in a reasonable time. Thus, they cannot be…

Computation and Language · Computer Science 2025-03-11 Sofian Chaybouti , Achraf Saghe , Aymen Shabou

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-01 Xiangchen Li , Saeid Ghafouri , Bo Ji , Hans Vandierendonck , Deepu John , Dimitrios S. Nikolopoulos

Question Answering (QA) is a task in natural language processing that has seen considerable growth after the advent of transformers. There has been a surge in QA datasets that have been proposed to challenge natural language processing…

Computation and Language · Computer Science 2021-10-08 Kate Pearce , Tiffany Zhan , Aneesh Komanduri , Justin Zhan