no code implementations • EMNLP 2020 • Albert Webson, Zhizhong Chen, Carsten Eickhoff, Ellie Pavlick
In politics, neologisms are frequently invented for partisan objectives.
1 code implementation • Findings (EMNLP) 2021 • Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff
Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text.
no code implementations • 7 Feb 2025 • Meng Lu, Catherine Chen, Carsten Eickhoff
Neural Ranking Models (NRMs) have rapidly advanced state-of-the-art performance on information retrieval tasks.
no code implementations • 17 Jan 2025 • Andrew Parry, Catherine Chen, Carsten Eickhoff, Sean MacAvaney
Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains.
1 code implementation • 13 Jan 2025 • Siran Li, Linus Stenzel, Carsten Eickhoff, Seyed Ali Bahrainian
Retrieval-Augmented Generation (RAG) systems have recently shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses.
no code implementations • 11 Oct 2024 • Ruochen Zhang, Qinan Yu, Matianyu Zang, Carsten Eickhoff, Ellie Pavlick
In particular, we ask (1) when two languages employ the same morphosyntactic processes, do LLMs handle them using shared internal circuitry?
no code implementations • 7 Sep 2024 • Florian Hellmeier, Kay Brosien, Carsten Eickhoff, Alexander Meyer
Prognostic and diagnostic AI-based medical devices hold immense promise for advancing healthcare, yet their rapid development has outpaced the establishment of appropriate validation methods.
1 code implementation • 24 Jun 2024 • Michal Golovanevsky, William Rudman, Vedant Palit, Ritambhara Singh, Carsten Eickhoff
To address this, we introduce NOTICE, the first Noise-free Text-Image Corruption and Evaluation pipeline for mechanistic interpretability in VLMs.
1 code implementation • 21 Jun 2024 • Tassallah Abdullahi, Ritambhara Singh, Carsten Eickhoff
A simple approach often relies on comparing embeddings of query (text) to those of potential classes.
no code implementations • 13 Jun 2024 • Jack Merullo, Carsten Eickhoff, Ellie Pavlick
Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model.
1 code implementation • 3 May 2024 • Catherine Chen, Jack Merullo, Carsten Eickhoff
Neural models have demonstrated remarkable performance across diverse ranking tasks.
no code implementations • 12 Nov 2023 • Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff
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.
1 code implementation • 26 Oct 2023 • William Rudman, Catherine Chen, Carsten Eickhoff
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance.
1 code implementation • 12 Oct 2023 • Jack Merullo, Carsten Eickhoff, Ellie Pavlick
that it is mostly reused to solve a seemingly different task: Colored Objects (Ippolito & Callison-Burch, 2023).
1 code implementation • 18 Sep 2023 • Maria Heuss, Daniel Cohen, Masoud Mansoury, Maarten de Rijke, Carsten Eickhoff
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.
1 code implementation • 11 Jul 2023 • Michal Golovanevsky, Eva Schiller, Akira Nair, Eric Han, Ritambhara Singh, Carsten Eickhoff
Multimodal learning models have become increasingly important as they surpass single-modality approaches on diverse tasks ranging from question-answering to autonomous driving.
no code implementations • 16 Jun 2023 • Catherine Chen, Carsten Eickhoff
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.
1 code implementation • 30 May 2023 • William Rudman, Carsten Eickhoff
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations.
1 code implementation • 25 May 2023 • Jack Merullo, Carsten Eickhoff, Ellie Pavlick
A primary criticism towards language models (LMs) is their inscrutability.
1 code implementation • 25 May 2023 • George Zerveas, Navid Rekabsaz, Carsten Eickhoff
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.
no code implementations • 24 May 2023 • Koyena Pal, Seyed Ali Bahrainian, Laura Mercurio, Carsten Eickhoff
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).
1 code implementation • 7 Mar 2023 • Ruochen Zhang, Carsten Eickhoff
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.
1 code implementation • 13 Feb 2023 • Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, Navid Rekabsaz
Large pre-trained language models contain societal biases and carry along these biases to downstream tasks.
1 code implementation • 3 Jan 2023 • İlkay Yıldız Potter, George Zerveas, Carsten Eickhoff, Dominique Duncan
Epileptic seizures are commonly monitored through electroencephalogram (EEG) recordings due to their routine and low expense collection.
no code implementations • 17 Oct 2022 • Catherine Chen, Carsten Eickhoff
In this paper, we use psychometrics and crowdsourcing to identify human-centered factors of explainability in Web search systems and introduce SSE (Search System Explainability), an evaluation metric for explainable IR (XIR) search systems.
2 code implementations • 30 Sep 2022 • Jack Merullo, Louis Castricato, Carsten Eickhoff, Ellie Pavlick
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.
no code implementations • 26 Jul 2022 • Augusto Garcia-Agundez, Carsten Eickhoff
Transformers are powerful text representation learners, useful for all kinds of clinical decision support tasks.
1 code implementation • *SEM (NAACL) 2022 • Jack Merullo, Dylan Ebert, Carsten Eickhoff, Ellie Pavlick
Lexical semantics and cognitive science point to affordances (i. e. the actions that objects support) as critical for understanding and representing nouns and verbs.
1 code implementation • 17 Jun 2022 • Michal Golovanevsky, Carsten Eickhoff, Ritambhara Singh
The objective of this study was to develop a novel multimodal deep learning framework to aid medical professionals in AD diagnosis.
no code implementations • Findings (ACL) 2022 • Seyed Ali Bahrainian, Sheridan Feucht, Carsten Eickhoff
Text summarization models are approaching human levels of fidelity.
1 code implementation • 24 May 2022 • William Jurayj, William Rudman, Carsten Eickhoff
In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular.
no code implementations • 4 May 2022 • Yuanfei Dai, Wenzhong Guo, Carsten Eickhoff
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.
1 code implementation • 16 Dec 2021 • George Zerveas, Navid Rekabsaz, Daniel Cohen, Carsten Eickhoff
Contrastive learning has been the dominant approach to training dense retrieval models.
no code implementations • 20 Nov 2021 • Toni Sagayaraj, Carsten Eickhoff
Research into deep learning models for molecular property prediction has primarily focused on the development of better Graph Neural Network (GNN) architectures.
1 code implementation • 10 Nov 2021 • Babak Hemmatian, Sheridan Feucht, Rachel Avram, Alexander Wey, Muskaan Garg, Kate Spitalnic, Carsten Eickhoff, Ellie Pavlick, Bjorn Sandstede, Steven Sloman
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.
1 code implementation • Findings (ACL) 2022 • William Rudman, Nate Gillman, Taylor Rayne, Carsten Eickhoff
We propose IsoScore: a novel tool that quantifies the degree to which a point cloud uniformly utilizes the ambient vector space.
no code implementations • 8 Aug 2021 • Zhizhong Chen, Carsten Eickhoff
These models learn to compute a ranking score between the given query and document.
no code implementations • 29 Jul 2021 • Zhizhong Chen, Carsten Eickhoff
Despite advances in neural machine translation, cross-lingual retrieval tasks in which queries and documents live in different natural language spaces remain challenging.
no code implementations • 29 Jul 2021 • Zhizhong Chen, Carsten Eickhoff
Existing listwise ranking losses treat the candidate document list as a whole unit without further inspection.
1 code implementation • 25 Jun 2021 • Oleg Lesota, Navid Rekabsaz, Daniel Cohen, Klaus Antonius Grasserbauer, Carsten Eickhoff, Markus Schedl
In contrast to the matching paradigm, the probabilistic nature of generative rankers readily offers a fine-grained measure of uncertainty.
no code implementations • NAACL 2021 • Ruochen Zhang, Carsten Eickhoff
In the pursuit of natural language understanding, there has been a long standing interest in tracking state changes throughout narratives.
1 code implementation • 10 May 2021 • Daniel Cohen, Bhaskar Mitra, Oleg Lesota, Navid Rekabsaz, Carsten Eickhoff
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.
no code implementations • 25 Mar 2021 • Abdullah Ahmed, Adeel Abbasi, Carsten Eickhoff
Electronic Health Records (EHRs) have become the primary form of medical data-keeping across the United States.
1 code implementation • 14 Mar 2021 • Navid Rekabsaz, Oleg Lesota, Markus Schedl, Jon Brassey, Carsten Eickhoff
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.
no code implementations • 12 Oct 2020 • Aaron S. Eisman, Nishant R. Shah, Carsten Eickhoff, George Zerveas, Elizabeth S. Chen, Wen-Chih Wu, Indra Neil Sarkar
Anginal symptoms can connote increased cardiac risk and a need for change in cardiovascular management.
6 code implementations • 6 Oct 2020 • George Zerveas, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty, Carsten Eickhoff
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
1 code implementation • 6 Oct 2020 • Albert Webson, Zhizhong Chen, Carsten Eickhoff, Ellie Pavlick
In politics, neologisms are frequently invented for partisan objectives.
no code implementations • 8 Sep 2020 • George Zerveas, Ruochen Zhang, Leila Kim, Carsten Eickhoff
This paper describes Brown University's submission to the TREC 2019 Deep Learning track.
1 code implementation • 24 Jun 2020 • Cindy Li, Elizabeth Chen, Guergana Savova, Hamish Fraser, Carsten Eickhoff
Diagnostic errors can pose a serious threat to patient safety, leading to serious harm and even death.
no code implementations • 24 Jun 2020 • Gil Alon, Elizabeth Chen, Guergana Savova, Carsten Eickhoff
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.
no code implementations • 15 Apr 2020 • Yuanfei Dai, Chenhao Guo, Wenzhong Guo, Carsten Eickhoff
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.
1 code implementation • 22 Aug 2019 • Carsten Eickhoff, Floran Gmehlin, Anu V. Patel, Jocelyn Boullier, Hamish Fraser
In clinical care, obtaining a correct diagnosis is the first step towards successful treatment and, ultimately, recovery.
1 code implementation • 29 Apr 2019 • Sebastian Hofstätter, Navid Rekabsaz, Carsten Eickhoff, Allan Hanbury
Low-frequency terms are a recurring challenge for information retrieval models, especially neural IR frameworks struggle with adequately capturing infrequently observed words.
no code implementations • 13 Nov 2018 • Xing Wei, Carsten Eickhoff
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.
no code implementations • 9 Jan 2018 • Ferenc Galkó, Carsten Eickhoff
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.
no code implementations • 31 Jul 2017 • Zsolt Mezei, Carsten Eickhoff
Recommendation to groups of users is a challenging and currently only passingly studied task.
1 code implementation • 1 Dec 2016 • Paulina Grnarova, Florian Schmidt, Stephanie L. Hyland, Carsten Eickhoff
We present an automatic mortality prediction scheme based on the unstructured textual content of clinical notes.
no code implementations • 24 Jun 2016 • Jeroen B. P. Vuurens, Carsten Eickhoff, Arjen P. de Vries
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.
1 code implementation • 24 May 2016 • Rolf Jagerman, Carsten Eickhoff, Maarten de Rijke
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.
1 code implementation • 8 Sep 2015 • Octavian-Eugen Ganea, Marina Ganea, Aurelien Lucchi, Carsten Eickhoff, Thomas Hofmann
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.
no code implementations • LREC 2012 • Anton Leuski, Carsten Eickhoff, James Ganis, Victor Lavrenko
Thirdly, a joined analysis of both the language and the actions would empower us to build effective modes of the users and their behavior.