Carsten Eickhoff

research

∙ 05/30/2023

Stable Anisotropic Regularization

Given the success of Large Language Models (LLMs), there has been consid...

0 William Rudman, et al. ∙

research

∙ 05/25/2023

Language Models Implement Simple Word2Vec-style Vector Arithmetic

A primary criticism towards language models (LMs) is their inscrutabilit...

0 Jack Merullo, et al. ∙

research

∙ 05/25/2023

Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors

Sparse annotation poses persistent challenges to training dense retrieva...

0 George Zerveas, et al. ∙

research

∙ 05/24/2023

Neural Summarization of Electronic Health Records

Hospital discharge documentation is among the most essential, yet time-c...

0 Koyena Pal, et al. ∙

research

∙ 03/07/2023

CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization

Cross-lingual summarization (CLS) has attracted increasing interest in r...

0 Ruochen Zhang, et al. ∙

research

∙ 02/13/2023

Parameter-efficient Modularised Bias Mitigation via AdapterFusion

Large pre-trained language models contain societal biases and carry alon...

0 Deepak Kumar, et al. ∙

research

∙ 01/03/2023

Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG

Epilepsy is one of the most common neurological disorders, typically obs...

0 İlkay Yıldız Potter, et al. ∙

research

∙ 09/30/2022

Linearly Mapping from Image to Text Space

The extent to which text-only language models (LMs) learn to represent t...

0 Jack Merullo, et al. ∙

research

∙ 07/05/2022

Pretraining on Interactions for Learning Grounded Affordance Representations

Lexical semantics and cognitive science point to affordances (i.e. the a...

2 Jack Merullo, et al. ∙

research

∙ 06/17/2022

Multimodal Attention-based Deep Learning for Alzheimer's Disease Diagnosis

Alzheimer's Disease (AD) is the most common neurodegenerative disorder w...

0 Michal Golovanevsky, et al. ∙

research

∙ 05/31/2022

NEWTS: A Corpus for News Topic-Focused Summarization

Text summarization models are approaching human levels of fidelity. Exis...

0 Seyed Ali Bahrainian, et al. ∙

research

∙ 05/24/2022

Garden-Path Traversal within GPT-2

In recent years, massive language models consisting exclusively of trans...

2 William Jurayj, et al. ∙

research

∙ 05/04/2022

Wasserstein Adversarial Learning based Temporal Knowledge Graph Embedding

Research on knowledge graph embedding (KGE) has emerged as an active fie...

0 Yuanfei Dai, et al. ∙

research

∙ 12/16/2021

CODER: An efficient framework for improving retrieval through COntextualized Document Embedding Reranking

We present a framework for improving the performance of a wide class of ...

2 George Zerveas, et al. ∙

research

∙ 11/20/2021

Image-Like Graph Representations for Improved Molecular Property Prediction

Research into deep learning models for molecular property prediction has...

0 Toni Sagayaraj, et al. ∙

research

∙ 11/10/2021

A Novel Corpus of Discourse Structure in Humans and Computers

We present a novel corpus of 445 human- and computer-generated documents...

0 Babak Hemmatian, et al. ∙

research

∙ 08/16/2021

IsoScore: Measuring the Uniformity of Vector Space Utilization

The recent success of distributed word representations has led to an inc...

0 William Rudman, et al. ∙

research

∙ 08/08/2021

PoolRank: Max/Min Pooling-based Ranking Loss for Listwise Learning Ranking Balance

Numerous neural retrieval models have been proposed in recent years. The...

0 Zhizhong Chen, et al. ∙

research

∙ 07/29/2021

ExpertRank: A Multi-level Coarse-grained Expert-based Listwise Ranking Loss

The goal of information retrieval is to recommend a list of document can...

0 Zhizhong Chen, et al. ∙

research

∙ 07/29/2021

The Cross-Lingual Arabic Information REtrieval (CLAIRE) System

Despite advances in neural machine translation, cross-lingual retrieval ...

0 Zhizhong Chen, et al. ∙

research

∙ 06/25/2021

A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models

Existing neural ranking models follow the text matching paradigm, where ...

0 Oleg Lesota, et al. ∙

research

∙ 06/03/2021

SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain

In the pursuit of natural language understanding, there has been a long ...

4 Ruochen Zhang, et al. ∙

research

∙ 05/10/2021

Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models

In any ranking system, the retrieval model outputs a single score for a ...

0 Daniel Cohen, et al. ∙

research

∙ 03/25/2021

Benchmarking Modern Named Entity Recognition Techniques for Free-text Health Record De-identification

Electronic Health Records (EHRs) have become the primary form of medical...

0 Abdullah Ahmed, et al. ∙

research

∙ 03/14/2021

TripClick: The Log Files of a Large Health Web Search Engine

Click logs are valuable resources for a variety of information retrieval...

0 Navid Rekabsaz, et al. ∙

research

∙ 10/12/2020

Extracting Angina Symptoms from Clinical Notes Using Pre-Trained Transformer Architectures

Anginal symptoms can connote increased cardiac risk and a need for chang...

0 Aaron S. Eisman, et al. ∙

research

∙ 10/06/2020

Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces

In politics, neologisms are frequently invented for partisan objectives....

0 Albert Webson, et al. ∙

research

∙ 10/06/2020

A Transformer-based Framework for Multivariate Time Series Representation Learning

In this work we propose for the first time a transformer-based framework...

24 George Zerveas, et al. ∙

research

∙ 09/08/2020

Brown University at TREC Deep Learning 2019

This paper describes Brown University's submission to the TREC 2019 Deep...

0 George Zerveas, et al. ∙

research

∙ 06/24/2020

Diagnosis Prevalence vs. Efficacy in Machine-learning Based Diagnostic Decision Support

Many recent studies use machine learning to predict a small number of IC...

0 Gil Alon, et al. ∙

research

∙ 06/24/2020

Mining Misdiagnosis Patterns from Biomedical Literature

Diagnostic errors can pose a serious threat to patient safety, leading t...

0 Cindy Li, et al. ∙

research

∙ 04/15/2020

Wasserstein Adversarial Autoencoders for Knowledge Graph Embedding based Drug-Drug Interaction Prediction

Interaction between pharmacological agents can trigger unexpected advers...

7 Yuanfei Dai, et al. ∙

research

∙ 08/22/2019

DC3 – A Diagnostic Case Challenge Collection for Clinical Decision Support

In clinical care, obtaining a correct diagnosis is the first step toward...

0 Carsten Eickhoff, et al. ∙

research

∙ 11/13/2018

Embedding Electronic Health Records for Clinical Information Retrieval

Neural network representation learning frameworks have recently shown to...

0 Xing Wei, et al. ∙

research

∙ 01/09/2018

Biomedical Question Answering via Weighted Neural Network Passage Retrieval

The amount of publicly available biomedical literature has been growing ...

0 Ferenc Galkó, et al. ∙

research

∙ 01/08/2018

Web2Text: Deep Structured Boilerplate Removal

Web pages are a valuable source of information for many natural language...

0 Thijs Vogels, et al. ∙

research

∙ 07/31/2017

Evaluating Music Recommender Systems for Groups

Recommendation to groups of users is a challenging and currently only pa...

0 Zsolt Mezei, et al. ∙

research

∙ 12/01/2016

Neural Document Embeddings for Intensive Care Patient Mortality Prediction

We present an automatic mortality prediction scheme based on the unstruc...

0 Paulina Grnarova, et al. ∙

research

∙ 06/24/2016

Efficient Parallel Learning of Word2Vec

Since its introduction, Word2Vec and its variants are widely used to lea...

0 Jeroen B. P. Vuurens, et al. ∙

research

∙ 05/24/2016

Computing Web-scale Topic Models using an Asynchronous Parameter Server

Topic models such as Latent Dirichlet Allocation (LDA) have been widely ...

0 Rolf Jagerman, et al. ∙

research

∙ 09/08/2015

Probabilistic Bag-Of-Hyperlinks Model for Entity Linking

Many fundamental problems in natural language processing rely on determi...

0 Octavian-Eugen Ganea, et al. ∙

Carsten Eickhoff

Featured Co-authors