Di Jin

Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition

2019

We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER). Specifically, two variants of DATNet, i.e., DATNet-F and DATNet-P, are investigated to explore effective feature …

Network-Specific Variational Auto-Encoder for Embedding in Attribute Networks

2019

Network embedding (NE) maps a network into a low-dimensional space while preserving intrinsic features of the network. Variational Auto-Encoder (VAE) has been actively studied for NE. These VAE-based methods typically utilize both network topologies and …

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

2019 · arXiv (Cornell University)

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these …

MMM: Multi-Stage Multi-Task Learning for Multi-Choice Reading Comprehension

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language. Multiple-Choice …

PRAG: Paninian Retrieval-Augmented Generation for Safety-Critical Medical Question Answering

2020 · arXiv (Cornell University)

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical …

What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

2021 · Preprints.org

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical …

Amer: A New Attribute-Missing Network Embedding Approach

2022 · IEEE Transactions on Cybernetics

Network embedding which aims to learn a low dimensional representation of nodes is a powerful technique for network analysis. While network embedding for networks with complete attributes has been widely investigated, in many real-world applications …

Using In-Context Learning to Improve Dialogue Safety

2023 · arXiv (Cornell University)

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which often perpetuates social …

MERCY: Multiple Response Ranking Concurrently in Realistic Open-Domain Conversational Systems

2023

Automatic Evaluation (AE) and Response Selection (RS) models assign quality scores to various candidate responses and rank them in conversational setups. Prior response ranking research compares various models’ performance on synthetically generated test sets. In …

Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language

2023 · arXiv (Cornell University)

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form …

Publicly Available Clinical BERT Embeddings

2019 · arXiv (Cornell University)

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have …

Heterogeneous Graph Neural Network via Attribute Completion

2021

Heterogeneous information networks (HINs), also called heterogeneous graphs, are composed of multiple types of nodes and edges, and contain comprehensive information and rich semantics. Graph neural networks (GNNs), as powerful tools for graph data, have …