Search Results for author:
Found 7 papers, 3 papers with code
Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction
Our experiments demonstrate that (1) KGs with different characteristics require different augmenting strategies, and (2) augmenting the language model's input with textual data improves task performance significantly.
Mitigating Bias for Question Answering Models by Tracking Bias Influence
Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance by observing its influence on another instance.
Dual-Awareness Attention for Few-Shot Object Detection
While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems.
Ranked #11 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Analysis of E-commerce Ranking Signals via Signal Temporal Logic
The timed position of documents retrieved by learning to rank models can be seen as signals.
Choosing Transfer Languages for Cross-Lingual Learning
Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance of natural language processing (NLP) on low-resource languages.
Towards a General-Purpose Linguistic Annotation Backend
In this extended abstract, we describe the beginnings of a new project that will attempt to ease this language documentation process through the use of natural language processing (NLP) technology.
Distributed Newton Methods for Deep Neural Networks
First, to reduce the communication cost, we propose a diagonalization method such that an approximate Newton direction can be obtained without communication between machines.
