Search Results for author:
Found 52 papers, 29 papers with code
Self-Supervised Neural Topic Modeling
Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text.
Do ``Undocumented Workers'' == ``Illegal Aliens''? Differentiating Denotation and Connotation in Vector Spaces
In politics, neologisms are frequently invented for partisan objectives.
Controllable Topic-Focused Abstractive Summarization
We show that our model sets a new state of the art on the NEWTS dataset in terms of topic-focused abstractive summarization as well as a topic-prevalence score.
Outlier Dimensions Encode Task-Specific Knowledge
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance.
Circuit Component Reuse Across Tasks in Transformer Language Models
that it is mostly reused to solve a seemingly different task: Colored Objects (Ippolito & Callison-Burch, 2023).
Predictive Uncertainty-based Bias Mitigation in Ranking
Prior work on bias mitigation often assumes that ranking scores, which correspond to the utility that a document holds for a user, can be accurately determined.
One-Versus-Others Attention: Scalable Multimodal Integration for Clinical Data
Multimodal learning models have become increasingly important as they surpass single-modality approaches on diverse tasks ranging from question-answering to autonomous driving.
SSE: A Metric for Evaluating Search System Explainability
Explainable Information Retrieval (XIR) is a growing research area focused on enhancing transparency and trustworthiness of the complex decision-making processes taking place in modern information retrieval systems.
Stable Anisotropic Regularization
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations.
Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors
Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning.
Language Models Implement Simple Word2Vec-style Vector Arithmetic
A primary criticism towards language models (LMs) is their inscrutability.
Neural Summarization of Electronic Health Records
Using nursing notes and discharge summaries from the MIMIC-III dataset, we studied the viability of the automatic generation of various sections of a discharge summary using four state-of-the-art neural network summarization models (BART, T5, Longformer and FLAN-T5).
CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization
Cross-lingual summarization (CLS) has attracted increasing interest in recent years due to the availability of large-scale web-mined datasets and the advancements of multilingual language models.
Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG
Epileptic seizures are commonly monitored through electroencephalogram (EEG) recordings due to their routine and low expense collection.
Evaluating Search Explainability with Psychometrics and Crowdsourcing
Information retrieval (IR) systems have become an integral part of our everyday lives.
Linearly Mapping from Image to Text Space
Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are optimized to encode images in the language space.
When BERT Fails -- The Limits of EHR Classification
Transformers are powerful text representation learners, useful for all kinds of clinical decision support tasks.
Pretraining on Interactions for Learning Grounded Affordance Representations
Lexical semantics and cognitive science point to affordances (i. e. the actions that objects support) as critical for understanding and representing nouns and verbs.
Multimodal Attention-based Deep Learning for Alzheimer's Disease Diagnosis
The objective of this study was to develop a novel multimodal deep learning framework to aid medical professionals in AD diagnosis.
NEWTS: A Corpus for News Topic-Focused Summarization
Text summarization models are approaching human levels of fidelity.
Garden-Path Traversal in GPT-2
In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular.
Wasserstein Adversarial Learning based Temporal Knowledge Graph Embedding
In order to deal with this issue, several temporal knowledge graph embedding (TKGE) approaches have been proposed to integrate temporal and structural information in recent years.
CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking
Contrastive learning has been the dominant approach to training dense retrieval models.
Image-Like Graph Representations for Improved Molecular Property Prediction
Research into deep learning models for molecular property prediction has primarily focused on the development of better Graph Neural Network (GNN) architectures.
A Novel Corpus of Discourse Structure in Humans and Computers
We present a novel corpus of 445 human- and computer-generated documents, comprising about 27, 000 clauses, annotated for semantic clause types and coherence relations that allow for nuanced comparison of artificial and natural discourse modes.
IsoScore: Measuring the Uniformity of Embedding Space Utilization
We propose IsoScore: a novel tool that quantifies the degree to which a point cloud uniformly utilizes the ambient vector space.
PoolRank: Max/Min Pooling-based Ranking Loss for Listwise Learning & Ranking Balance
These models learn to compute a ranking score between the given query and document.
The Cross-Lingual Arabic Information REtrieval (CLAIRE) System
Despite advances in neural machine translation, cross-lingual retrieval tasks in which queries and documents live in different natural language spaces remain challenging.
ExpertRank: A Multi-level Coarse-grained Expert-based Listwise Ranking Loss
Existing listwise ranking losses treat the candidate document list as a whole unit without further inspection.
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models
In contrast to the matching paradigm, the probabilistic nature of generative rankers readily offers a fine-grained measure of uncertainty.
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 standing interest in tracking state changes throughout narratives.
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 document based on its belief on how relevant it is to a given search query.
Benchmarking Modern Named Entity Recognition Techniques for Free-text Health Record De-identification
Electronic Health Records (EHRs) have become the primary form of medical data-keeping across the United States.
TripClick: The Log Files of a Large Health Web Search Engine
As such, the collection is one of the few datasets offering the necessary data richness and scale to train neural IR models with a large amount of parameters, and notably the first in the health domain.
Extracting Angina Symptoms from Clinical Notes Using Pre-Trained Transformer Architectures
Anginal symptoms can connote increased cardiac risk and a need for change in cardiovascular management.
Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
In politics, neologisms are frequently invented for partisan objectives.
A Transformer-based Framework for Multivariate Time Series Representation Learning
In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series.
Ranked #2 on
Time Series Classification
on Insectwingbeat
Brown University at TREC Deep Learning 2019
This paper describes Brown University's submission to the TREC 2019 Deep Learning track.
Mining Misdiagnosis Patterns from Biomedical Literature
Diagnostic errors can pose a serious threat to patient safety, leading to serious harm and even death.
Diagnosis Prevalence vs. Efficacy in Machine-learning Based Diagnostic Decision Support
Scores fell from 0. 28 for the 50 most prevalent ICD-9-CM codes to 0. 03 for the 1000 most prevalent ICD-9-CM codes.
Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
Recently, several knowledge graph embedding approaches have received increasing attention in the DDI domain due to their capability of projecting drugs and interactions into a low-dimensional feature space for predicting links and classifying triplets.
DC3 -- A Diagnostic Case Challenge Collection for Clinical Decision Support
In clinical care, obtaining a correct diagnosis is the first step towards successful treatment and, ultimately, recovery.
On the Effect of Low-Frequency Terms on Neural-IR Models
Low-frequency terms are a recurring challenge for information retrieval models, especially neural IR frameworks struggle with adequately capturing infrequently observed words.
Embedding Electronic Health Records for Clinical Information Retrieval
Neural network representation learning frameworks have recently shown to be highly effective at a wide range of tasks ranging from radiography interpretation via data-driven diagnostics to clinical decision support.
Biomedical Question Answering via Weighted Neural Network Passage Retrieval
The amount of publicly available biomedical literature has been growing rapidly in recent years, yet question answering systems still struggle to exploit the full potential of this source of data.
Evaluating Music Recommender Systems for Groups
Recommendation to groups of users is a challenging and currently only passingly studied task.
Neural Document Embeddings for Intensive Care Patient Mortality Prediction
We present an automatic mortality prediction scheme based on the unstructured textual content of clinical notes.
Efficient Parallel Learning of Word2Vec
Since its introduction, Word2Vec and its variants are widely used to learn semantics-preserving representations of words or entities in an embedding space, which can be used to produce state-of-art results for various Natural Language Processing tasks.
Computing Web-scale Topic Models using an Asynchronous Parameter Server
Topic models such as Latent Dirichlet Allocation (LDA) have been widely used in information retrieval for tasks ranging from smoothing and feedback methods to tools for exploratory search and discovery.
Probabilistic Bag-Of-Hyperlinks Model for Entity Linking
We demonstrate the accuracy of our approach on a wide range of benchmark datasets, showing that it matches, and in many cases outperforms, existing state-of-the-art methods.
The BladeMistress Corpus: From Talk to Action in Virtual Worlds
Thirdly, a joined analysis of both the language and the actions would empower us to build effective modes of the users and their behavior.
