Search Results for author:
Found 17 papers, 7 papers with code
Value Retrieval with Arbitrary Queries for Form-like Documents
Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the layout and semantics of a form.
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
To enlarge the set of base classes, we propose a method to automatically generate pseudo bounding-box annotations of diverse objects from large-scale image-caption pairs.
Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting
However, given the limited size of the gender-neutral data and its potential distributional mismatch with the original pre-training data, catastrophic forgetting would occur during the second-phase pre-training.
Taking Notes on the Fly Helps Language Pre-Training
In this paper, we focus on improving the efficiency of language pre-training methods through providing better data utilization.
Learning from Mistakes: Using Mis-predictions as Harm Alerts in Language Pre-Training
According to recent studies and our empirical observations, one possible reason is that some easy-to-fit patterns in the training data, such as frequently co-occurring word combinations, dominate and harm pre-training, making it hard for the model to fit more complex information.
Taking Notes on the Fly Helps BERT Pre-training
In this paper, we focus on improving the efficiency of language pre-training methods through providing better data utilization.
On Layer Normalization in the Transformer Architecture
This motivates us to remove the warm-up stage for the training of Pre-LN Transformers.
Distance-Based Learning from Errors for Confidence Calibration
To circumvent this by inferring the distance for every test sample, we propose to train a confidence model jointly with the classification model.
A Walk with SGD: How SGD Explores Regions of Deep Network Loss?
The non-convex nature of the loss landscape of deep neural networks (DNN) lends them the intuition that over the course of training, stochastic optimization algorithms explore different regions of the loss surface by entering and escaping many local minima due to the noise induced by mini-batches.
Adaptive Cross-Modal Few-Shot Learning
Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested.
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
A Walk with SGD
Based on this and other metrics, we deduce that for most of the training update steps, SGD moves in valley like regions of the loss surface by jumping from one valley wall to another at a height above the valley floor.
A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
The task requires matching a response candidate with a conversation context, whose challenges include how to recognize important parts of the context, and how to model the relationships among utterances in the context.
Hierarchical Recurrent Attention Network for Response Generation
With the word level attention, hidden vectors of a word level encoder are synthesized as utterance vectors and fed to an utterance level encoder to construct hidden representations of the context.
Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information.
Ranked #7 on
Conversational Response Selection
on RRS
Detecting Context Dependent Messages in a Conversational Environment
While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process.
Topic Aware Neural Response Generation
We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots.
