Search Results for author:
Found 7 papers, 0 papers with code
Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently
We propose a simple yet effective Multi-Layer RAndom Perturbation Training algorithm (RAPT) to enhance model robustness and generalization.
Towards a Language Model for Temporal Commonsense Reasoning
Temporal commonsense reasoning is a challenging task as it requires temporal knowledge usually not explicit in text.
Dialogue over Context and Structured Knowledge using a Neural Network Model with External Memories
The Differentiable Neural Computer (DNC), a neural network model with an addressable external memory, can solve algorithmic and question answering tasks.
Attention-Focused Adversarial Training for Robust Temporal Reasoning
Adding the perturbation to the attention representations performed best in our experiments.
AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data.
OCHADAI at SemEval-2022 Task 2: Adversarial Training for Multilingual Idiomaticity Detection
We propose a multilingual adversarial training model for determining whether a sentence contains an idiomatic expression.
OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction
We propose an ensemble model for predicting the lexical complexity of words and multiword expressions (MWEs).
