Search Results for author:
Found 23 papers, 9 papers with code
SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References
Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions.
Learning Answer Generation using Supervision from Automatic Question Answering Evaluators
Recent studies show that sentence-level extractive QA, i. e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval-augmented generation style).
Context-Aware Transformer Pre-Training for Answer Sentence Selection
Answer Sentence Selection (AS2) is a core component for building an accurate Question Answering pipeline.
Ranked #4 on
Question Answering
on TrecQA
(using extra training data)
Structured Pruning for Multi-Task Deep Neural Networks
Numerous structured pruning methods are already developed that can readily achieve speedups in single-task models, but the pruning of multi-task networks has not yet been extensively studied.
Knowledge Transfer from Answer Ranking to Answer Generation
In this paper, we propose to train a GenQA model by transferring knowledge from a trained AS2 model, to overcome the aforementioned issue.
SeRP: Self-Supervised Representation Learning Using Perturbed Point Clouds
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds.
Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection
An important task for designing QA systems is answer sentence selection (AS2): selecting the sentence containing (or constituting) the answer to a question from a set of retrieved relevant documents.
Ranked #1 on
Answer Selection
on ASNQ
Paragraph-based Transformer Pre-training for Multi-Sentence Inference
Our evaluation on three AS2 and one fact verification datasets demonstrates the superiority of our pre-training technique over the traditional ones for transformers used as joint models for multi-candidate inference tasks, as well as when used as cross-encoders for sentence-pair formulations of these tasks.
Ranked #3 on
Fact Verification
on FEVER
Self-Labeling Refinement for Robust Representation Learning with Bootstrap Your Own Latent
Using the proposed loss functions, we are able to surpass the performance of Vanilla BYOL (71. 04%) by training the BYOL framework using CCSL loss (76. 87%) on the STL10 dataset.
A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones
With the combination of our novel approach and the architecture, we present state-of-the-art results on detecting the image tilt angle on mobile devices as compared to the MobileNetV3 model.
Attentive Walk-Aggregating Graph Neural Networks
Our experiments demonstrate the strong performance of AWARE in graph-level prediction tasks in the standard setting in the domains of molecular property prediction and social networks.
Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering
In this paper we propose a novel approach towards improving the efficiency of Question Answering (QA) systems by filtering out questions that will not be answered by them.
Towards Robustness to Label Noise in Text Classification via Noise Modeling
Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures.
Functional Regularization for Representation Learning: A Unified Theoretical Perspective
Unsupervised and self-supervised learning approaches have become a crucial tool to learn representations for downstream prediction tasks.
Can Adversarial Weight Perturbations Inject Neural Backdoors?
We introduce adversarial perturbations in the model weights using a composite loss on the predictions of the original model and the desired trigger through projected gradient descent.
Advances in Quantum Deep Learning: An Overview
The last few decades have seen significant breakthroughs in the fields of deep learning and quantum computing.
Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer
In this paper we show that concatenating the embeddings from the pre-trained model with those from a simple sentence embedding model trained only on the target data, can improve over the performance of FT for few-sample tasks.
BAE: BERT-based Adversarial Examples for Text Classification
Modern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model.
Cross-Shape Attention for Part Segmentation of 3D Point Clouds
The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation.
Ranked #1 on
3D Semantic Segmentation
on PartNet
TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection
Additionally, we show that the transfer step of TANDA makes the adaptation step more robust to noise.
Ranked #2 on
Question Answering
on TrecQA
(using extra training data)
Stochastic Bandits with Delayed Composite Anonymous Feedback
The complexity of this problem stems from the anonymous feedback to the player and the stochastic generation of the reward.
Data Ordering Patterns for Neural Machine Translation: An Empirical Study
Recent works show that ordering of the training data affects the model performance for Neural Machine Translation.
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning
In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning.
