Search Results for author:
Found 19 papers, 14 papers with code
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
Mitigating social biases typically requires identifying the social groups associated with each data sample.
Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection
In this work, we propose Iterative Gradient-Based Projection (IGBP), a novel method for removing non-linear encoded concepts from neural representations.
tBDFS: Temporal Graph Neural Network Leveraging DFS
A common approach employed by most previous works is to apply a layer that aggregates information from the historical neighbors of a node.
What If: Generating Code to Answer Simulation Questions
The dataset is composed of process texts, simulation questions, and their corresponding computer codes represented by the DSL. We propose a neural program synthesis approach based on reinforcement learning with a novel state-transition semantic reward.
Temporal Attention for Language Models
We leverage these representations for the task of semantic change detection; we apply our proposed mechanism to BERT and experiment on three datasets in different languages (English, German, and Latin) that also vary in time, size, and genre.
Time Masking for Temporal Language Models
Our world is constantly evolving, and so is the content on the web.
EqGNN: Equalized Node Opportunity in Graphs
To the best of our knowledge, we are the first to optimize GNNs for the equalized odds criteria.
Event-Driven Query Expansion
A significant number of event-related queries are issued in Web search.
SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification
Generating training examples for supervised tasks is a long sought after goal in AI.
Cross-Cultural Transfer Learning for Text Classification
In this work, we show that cross-cultural differences can be harnessed for natural language text classification.
Generating Timelines by Modeling Semantic Change
Though languages can evolve slowly, they can also react strongly to dramatic world events.
Explorations and Lessons Learned in Building an Autonomous Formula SAE Car from Simulations
This paper describes the exploration and learnings during the process of developing a self-driving algorithm in simulation, followed by deployment on a real car.
Robotics
Node Embedding over Temporal Graphs
In this work, we present a method for node embedding in temporal graphs.
Latent Entities Extraction: How to Extract Entities that Do Not Appear in the Text?
The dataset contains text descriptions of biological processes, and for each process, all of the involved entities in the process are labeled, including implicitly mentioned ones.
Learning to Focus when Ranking Answers
One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm.
Accelerating Prototype-Based Drug Discovery using Conditional Diversity Networks
In this work, we develop an algorithmic unsupervised-approach that automatically generates potential drug molecules given a prototype drug.
Learning Word Relatedness over Time
Search systems are often focused on providing relevant results for the "now", assuming both corpora and user needs that focus on the present.
Named Entity Disambiguation for Noisy Text
We address the task of Named Entity Disambiguation (NED) for noisy text.
Learning to Predict from Textual Data
Our Pundit algorithm generalizes examples of causality pairs to infer a causality predictor.
