Search

Your search keyword '"Hoffart A"' showing total 3,210 results
Start Over Author "Hoffart A"
3,210 results on '"Hoffart A"'

1. PORTAL: Scalable Tabular Foundation Models via Content-Specific Tokenization

Author

Spinaci, Marco, Polewczyk, Marek, Hoffart, Johannes, Kohler, Markus C., Thelin, Sam, and Klein, Tassilo

Subjects
Computer Science - Machine Learning
Abstract

Self-supervised learning on tabular data seeks to apply advances from natural language and image domains to the diverse domain of tables. However, current techniques often struggle with integrating multi-domain data and require data cleaning or specific structural requirements, limiting the scalability of pre-training datasets. We introduce PORTAL (Pretraining One-Row-at-a-Time for All tabLes), a framework that handles various data modalities without the need for cleaning or preprocessing. This simple yet powerful approach can be effectively pre-trained on online-collected datasets and fine-tuned to match state-of-the-art methods on complex classification and regression tasks. This work offers a practical advancement in self-supervised learning for large-scale tabular data., Comment: Accepted at Table Representation Learning Workshop at NeurIPS 2024

Published
2024

3. Large Process Models: Business Process Management in the Age of Generative AI

Author

Kampik, Timotheus, Warmuth, Christian, Rebmann, Adrian, Agam, Ron, Egger, Lukas N. P., Gerber, Andreas, Hoffart, Johannes, Kolk, Jonas, Herzig, Philipp, Decker, Gero, van der Aa, Han, Polyvyanyy, Artem, Rinderle-Ma, Stefanie, Weber, Ingo, and Weidlich, Matthias

Subjects
Computer Science - Software Engineering, Computer Science - Artificial Intelligence
Abstract

The continued success of Large Language Models (LLMs) and other generative artificial intelligence approaches highlights the advantages that large information corpora can have over rigidly defined symbolic models, but also serves as a proof-point of the challenges that purely statistics-based approaches have in terms of safety and trustworthiness. As a framework for contextualizing the potential, as well as the limitations of LLMs and other foundation model-based technologies, we propose the concept of a Large Process Model (LPM) that combines the correlation power of LLMs with the analytical precision and reliability of knowledge-based systems and automated reasoning approaches. LPMs are envisioned to directly utilize the wealth of process management experience that experts have accumulated, as well as process performance data of organizations with diverse characteristics, e.g., regarding size, region, or industry. In this vision, the proposed LPM would allow organizations to receive context-specific (tailored) process and other business models, analytical deep-dives, and improvement recommendations. As such, they would allow to substantially decrease the time and effort required for business transformation, while also allowing for deeper, more impactful, and more actionable insights than previously possible. We argue that implementing an LPM is feasible, but also highlight limitations and research challenges that need to be solved to implement particular aspects of the LPM vision.

Published
2023

4. Mental illness and COVID-19 vaccination: a multinational investigation of observational & register-based data

Author

Mary M. Barker, Kadri Kõiv, Ingibjörg Magnúsdóttir, Hannah Milbourn, Bin Wang, Xinkai Du, Gillian Murphy, Eva Herweijer, Elísabet U. Gísladóttir, Huiqi Li, Anikó Lovik, Anna K. Kähler, Archie Campbell, Maria Feychting, Arna Hauksdóttir, Emily E. Joyce, Edda Bjork Thordardottir, Emma M. Frans, Asle Hoffart, Reedik Mägi, Gunnar Tómasson, Kristjana Ásbjörnsdóttir, Jóhanna Jakobsdóttir, Ole A. Andreassen, Patrick F. Sullivan, Sverre Urnes Johnson, Thor Aspelund, Ragnhild Eek Brandlistuen, Helga Ask, Daniel L. McCartney, Omid V. Ebrahimi, Kelli Lehto, Unnur A. Valdimarsdóttir, Fredrik Nyberg, and Fang Fang

Subjects
Science
Abstract

Abstract Individuals with mental illness are at higher risk of severe COVID-19 outcomes. However, previous studies on the uptake of COVID-19 vaccination in this population have reported conflicting results. Using data from seven cohort studies (N = 325,298) included in the multinational COVIDMENT consortium, and the Swedish registers (N = 8,080,234), this study investigates the association between mental illness (defined using self-report measures, clinical diagnosis and prescription data) and COVID-19 vaccination uptake. Results from the COVIDMENT cohort studies were pooled using meta-analyses, the majority of which showed no significant association between mental illness and vaccination uptake. In the Swedish register study population, we observed a very small reduction in the uptake of both the first and second dose of a COVID-19 vaccine among individuals with vs. without mental illness; the reduction was however greater among those not using psychiatric medication. Here we show that uptake of the COVID-19 vaccine is generally high among individuals both with and without mental illness, however the lower levels of vaccination uptake observed among subgroups of individuals with unmedicated mental illness warrants further attention.

Published
2024
Full Text
View/download PDF

5. Mental illness and COVID-19 vaccination: a multinational investigation of observational & register-based data

Author

Barker, Mary M., Kõiv, Kadri, Magnúsdóttir, Ingibjörg, Milbourn, Hannah, Wang, Bin, Du, Xinkai, Murphy, Gillian, Herweijer, Eva, Gísladóttir, Elísabet U., Li, Huiqi, Lovik, Anikó, Kähler, Anna K., Campbell, Archie, Feychting, Maria, Hauksdóttir, Arna, Joyce, Emily E., Thordardottir, Edda Bjork, Frans, Emma M., Hoffart, Asle, Mägi, Reedik, Tómasson, Gunnar, Ásbjörnsdóttir, Kristjana, Jakobsdóttir, Jóhanna, Andreassen, Ole A., Sullivan, Patrick F., Johnson, Sverre Urnes, Aspelund, Thor, Brandlistuen, Ragnhild Eek, Ask, Helga, McCartney, Daniel L., Ebrahimi, Omid V., Lehto, Kelli, Valdimarsdóttir, Unnur A., Nyberg, Fredrik, and Fang, Fang

Published
2024
Full Text
View/download PDF

8. Longitudinal qualitative perspectives of adolescents in an intensive interdisciplinary pain program

Author

Kristin Stegenga, William R. Black, Jennifer Christofferson, Dustin P. Wallace, and Cara M. Hoffart

Subjects
Adolescents, Qualitative, Structured interviews, Chronic pain, Rehabilitation, Psychology, BF1-990
Abstract

Abstract Objectives Chronic pain in children and adolescents is often associated with functional, physical, and psychosocial challenges. Intensive interdisciplinary pain treatment (IIPT) programs are effective at helping these youth regain functioning, but little is known about their perspectives prior to and during IIPT participation. This study sought to better understand how children and adolescents experience the process from evaluation to completion of the IIPT program. Methods Individual interviews (n = 7) were conducted at three time-points; (1) prior to initial evaluation in a pain clinic, (2) after pain clinic evaluation while considering IIPT, and (3) after completion of an IIPT program. Results Participants ranged in age from 13–17 years. Across these time points, participants demonstrated changes in thoughts and perspectives. While Time 1 was associated with ambivalence, skepticism, and some hope, Time 2 was characterized by processing information about the program and resolution of some of their ambivalence. At Time 3, participants described their experience as “challenging” and “intense” and reported recognition that they had benefited from the program. Participants also wished to pass along lessons learned to future potential patients. Discussion This study provides information to help clinicians better approach adolescents with chronic pain who may be considering IIPT.

Published
2024
Full Text
View/download PDF

9. Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

Author

Bastos, Anson, Singh, Kuldeep, Nadgeri, Abhishek, Hoffart, Johannes, Suzumura, Toyotaro, and Singh, Manish

Subjects
Computer Science - Machine Learning, Mathematics - Algebraic Topology
Abstract

In this paper we present a novel method, $\textit{Knowledge Persistence}$ ($\mathcal{KP}$), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-based evaluation is quadratic in the size of the KG, leading to long evaluation times and consequently a high carbon footprint. $\mathcal{KP}$ addresses this by representing the topology of the KG completion methods through the lens of topological data analysis, concretely using persistent homology. The characteristics of persistent homology allow $\mathcal{KP}$ to evaluate the quality of the KG completion looking only at a fraction of the data. Experimental results on standard datasets show that the proposed metric is highly correlated with ranking metrics (Hits@N, MR, MRR). Performance evaluation shows that $\mathcal{KP}$ is computationally efficient: In some cases, the evaluation time (validation+test) of a KG completion method has been reduced from 18 hours (using Hits@10) to 27 seconds (using $\mathcal{KP}$), and on average (across methods & data) reduces the evaluation time (validation+test) by $\approx$ $\textbf{99.96}\%$., Comment: To appear in proceedings of The Web Conference 2023 (WWW'23)

Published
2023

13. Energy asset stranding in resource-rich developing countries and the just transition - A framework to push research frontiers

Author

Franziska M. Hoffart and Franziska Holz

Subjects
asset stranding, energy transition, benefit sharing, sustainable development goals, transition risks, economics, Environmental sciences, GE1-350
Abstract

Climate policy will inevitably lead to the stranding of fossil energy assets such as production and transport assets for coal, oil, and natural gas. Resource-rich developing countries are particularly affected, as they have a higher risk of asset stranding due to strong fossil dependencies and wider societal consequences beyond revenue disruption. However, there is only little academic and political awareness of the challenge to manage the asset stranding in these countries, as research on transition risk like asset stranding is still in its infancy. We provide a research framework to identify wider societal consequences of fossil asset stranding. We apply it to a case study of Nigeria. Analyzing different policy measures, we argue that compensation payments come with implementation challenges. Instead of one policy alone to address asset stranding, a problem-oriented mix of policies is needed. Renewable hydrogen and just energy transition partnerships can be a contribution to economic development and SDGs. However, they can only unfold their potential if fair benefit sharing and an improvement to the typical institutional problems in resource-rich countries, such as the lack of rule of law, are achieved. We conclude with presenting a future research agenda for the global community and academia.

Published
2024
Full Text
View/download PDF

14. The Effect of Women Academic Leaders on Canadian Natural Sciences and Engineering Professors

Author

Dengate, Jennifer, Hoffart, Renée, Peter, Tracey, Farenhorst, Annemieke, and Franz-Odendaal, Tamara

Abstract

Using a sample of women natural sciences and engineering (NSE) faculty members from 13 Canadian universities, we investigated the impact of women academic leaders on women professors' perceptions of gender bias. Logistic regression analyses indicated that professors who perceived more workplace gender bias were more likely to feel that they needed to work harder to be seen as legitimate scholars than those who perceived less gender bias. However, professors who perceived that women were better represented amongst their faculty/college and university leadership were significantly less likely to feel that they needed to work harder for legitimacy than those who perceived greater gender bias in leadership. These results suggest that addressing gendered university hierarchies may moderate the impact of gender bias on women in NSE units.

Published
2021

15. Interleukin (IL)-1/IL-6-Inhibitor–Associated Drug Reaction With Eosinophilia and Systemic Symptoms (DReSS) in Systemic Inflammatory Illnesses

Author

Aamir, R., Abulaban, K., Adams, A., Lapsia, C. Aguiar, Akinsete, A., Akoghlanian, S., Al Manaa, M., AlBijadi, A., Allenspach, E., Almutairi, A., Alperin, R., Amarilyo, G., Ambler, W., Amoruso, M., Angeles-Han, S., Ardoin, S., Armendariz, S., Asfaw, L., Aviran Dagan, N., Bacha, C., Balboni, I., Balevic, S., Ballinger, S., Baluta, S., Barillas-Arias, L., Basiaga, M., Baszis, K., Baxter, S., Becker, M., Begezda, A., Behrens, E., Beil, E., Benseler, S., Bermudez-Santiago, L., Bernal, W., Bigley, T., Bingham, C., Binstadt, B., Black, C., Blackmon, B., Blakley, M., Bohnsack, J., Boneparth, A., Bradfield, H., Bridges, J., Brooks, E., Brothers, M., Brunner, H., Buckley, L., Buckley, M., Bukulmez, H., Bullock, D., Canna, S., Cannon, L., Canny, S., Cartwright, V., Cassidy, E., Castro, D., Chalom, E., Chang, J., Chang, M., Chang-Hoftman, A., Chen, A., Chiraseveenuprapund, P., Ciaglia, K., Co, D., Cohen, E., Collinge, J., Conlon, H., Connor, R., Cook, K., Cooper, A., Cooper, J., Corbin, K., Correll, C., Cron, R., Curry, M., Dalrymple, A., Datyner, E., Davis, T., De Ranieri, D., Dean, J., DeCoste, C., Dedeoglu, F., DeGuzman, M., Delnay, N., DeSantis, E., Devine, R., Dhalla, M., Dhanrajani, A., Dissanayake, D., Dizon, B., Drapeau, N., Drew, J., Driest, K., Du, Q., Duncan, E., Dunnock, K., Durkee, D., Dvergsten, J., Eberhard, A., Ede, K., Edelheit, B., Edens, C., El Tal, T., Elder, M., Elzaki, Y., Fadrhonc, S., Failing, C., Fair, D., Favier, L., Feldman, B., Fennell, J., Ferguson, P., Ferguson, I., Figueroa, C., Flanagan, E., Fogel, L., Fox, E., Fox, M., Franklin, L., Fuhlbrigge, R., Fuller, J., Furey, M., Futch-West, T., Gagne, S., Gennaro, V., Gerstbacher, D., Gilbert, M., Gironella, A., Glaser, D., Goh, I., Goldsmith, D., Gorry, S., Goswami, N., Gottlieb, B., Graham, T., Grevich, S., Griffin, T., Grim, A., Grom, A., Guevara, M., Hahn, T., Halyabar, O., Hamda Natur, M., Hammelev, E., Hammond, T., Harel, L., Harris, J., Harry, O., Hausmann, J., Hay, A., Hays, K., Hayward, K., Henderson, L., Henrickson, M., Hersh, A., Hickey, K., Hiraki, L., Hiskey, M., Hobday, P., Hoffart, C., Holland, M., Hollander, M., Hong, S., Horton, D., Horwitz, M., Hsu, J., Huber, A., Huberts, A., Huggins, J., Huie, L., Hui-Yuen, J., Ibarra, M., Imlay, A., Imundo, L., Inman, C., Jackson, A., James, K., Janow, G., Jared, S., Jiang, Y., Johnson, L., Johnson, N., Jones, J., Kafisheh, D., Kahn, P., Kaidar, K., Kasinathan, S., Kaur, R., Kessler, E., Kienzle, B., Kim, S., Kimura, Y., Kingsbury, D., Kitcharoensakkul, M., Klausmeier, T., Klein, K., Klein-Gitelman, M., Knight, A., Kovalick, L., Kramer, S., Kremer, C., Kudas, O., LaFlam, T., Lang, B., Lapidus, S., Lapin, B., Lasky, A., Lawler, C., Lawson, E., Laxer, R., Lee, P., Lee, T., Lee, A., Leisinger, E., Lentini, L., Lerman, M., Levinsky, Y., Levy, D., Li, S., Lieberman, S., Lim, L., Limenis, E., Lin, C., Ling, N., Lionetti, G., Livny, R., Lloyd, M., Lo, M., Long, A., Lopez-Peña, M., Lovell, D., Luca, N., Lvovich, S., Lytch, A., Ma, M., Machado, A., MacMahon, J., Madison, J., Mannion, M., Manos, C., Mansfield, L., Marston, B., Mason, T., Matchett, D., McAllister, L., McBrearty, K., McColl, J., McCurdy, D., McDaniels, K., McDonald, J., Meidan, E., Mellins, E., Mian, Z., Miettunen, P., Miller, M., Milojevic, D., Mitacek, R., Modica, R., Mohan, S., Moore, T., Moore, K., Moorthy, L., Moreno, J., Morgan, E., Moyer, A., Murante, B., Murphy, A., Muscal, E., Mwizerwa, O., Najafi, A., Nanda, K., Nasah, N., Nassi, L., Nativ, S., Natter, M., Nearanz, K., Neely, J., Newhall, L., Nguyen, A., Nigrovic, P., Nocton, J., Nolan, B., Nowicki, K., Oakes, R., Oberle, E., Ogbonnaya-Whittesley, S., Ogbu, E., Oliver, M., Olveda, R., Onel, K., Orandi, A., Padam, J., Paller, A., Pan, N., Pandya, J., Panupattanapong, S., Toledano, A. Pappo, Parsons, A., Patel, J., Patel, P., Patrick, A., Patrizi, S., Paul, S., Perfetto, J., Perron, M., Peskin, M., Ponder, L., Pooni, R., Prahalad, S., Puplava, B., Quinlan-Waters, M., Rabinovich, C., Rafko, J., Rahimi, H., Rampone, K., Ramsey, S., Randell, R., Ray, L., Reed, A., Reid, H., Reiff, D., Richins, S., Riebschleger, M., Rife, E., Riordan, M., Riskalla, M., Robinson, A., Robinson, L., Rodgers, L., Rodriquez, M., Rogers, D., Ronis, T., Rosado, A., Rosenkranz, M., Rosenwasser, N., Rothermel, H., Rothman, D., Rothschild, E., Roth-Wojcicki, E., Rouster-Stevens, K., Rubinstein, T., Rupp, J., Ruth, N., Sabbagh, S., Sadun, R., Santiago, L., Saper, V., Sarkissian, A., Scalzi, L., Schahn, J., Schikler, K., Schlefman, A., Schmeling, H., Schmitt, E., Schneider, R., Schulert, G., Schultz, K., Schutt, C., Seper, C., Sheets, R., Shehab, A., Shenoi, S., Sherman, M., Shirley, J., Shishov, M., Siegel, D., Singer, N., Sivaraman, V., Sloan, E., Smith, C., Smith, J., Smitherman, E., Soep, J., Son, Mary B., Sosna, D., Spencer, C., Spiegel, L., Spitznagle, J., Srinivasalu, H., Stapp, H., Steigerwald, K., Stephens, A., Sterba Rakovchik, Y., Stern, S., Stevens, B., Stevenson, R., Stewart, K., Stewart, W., Stingl, C., Stoll, M., Stringer, E., Sule, S., Sullivan, J., Sundel, R., Sutter, M., Swaffar, C., Swayne, N., Syed, R., Symington, T., Syverson, G., Szymanski, A., Taber, S., Tal, R., Tambralli, A., Taneja, A., Tanner, T., Tarvin, S., Tate, L., Taxter, A., Taylor, J., Tesher, M., Thakurdeen, T., Theisen, A., Thomas, B., Thomas, L., Thomas, N., Ting, T., Todd, C., Toib, D., Torok, K., Tory, H., Toth, M., Tse, S., Tsin, C., Twachtman-Bassett, J., Twilt, M., Valcarcel, T., Valdovinos, R., Vallee, A., Van Mater, H., Vandenbergen, S., Vannoy, L., Varghese, C., Vasquez, N., Vega-Fernandez, P., Velez, J., Verbsky, J., Verstegen, R., von Scheven, E., Vora, S., Wagner-Weiner, L., Wahezi, D., Waite, H., Walker, B., Walters, H., Waterfield, M., Waters, A., Weiser, P., Weiss, P., Weiss, J., Wershba, E., Westheuser, V., White, A., Widrick, K., Williams, C., Wong, S., Woolnough, L., Wright, T., Wu, E., Yalcindag, A., Yasin, S., Yeung, R., Yomogida, K., Zeft, A., Zhang, Y., Zhao, Y., Zhu, A., Saper, Vivian E., Tian, Lu, Verstegen, Ruud H.J., Conrad, Carol K., Cidon, Michal, Hopper, Rachel K., Kuo, Christin S., Osoegawa, Kazutoyo, Baszis, Kevin, Bingham, Catherine A., Ferguson, Ian, Hahn, Timothy, Horne, Annacarin, Isupova, Eugenia A., Jones, Jordan T., Kasapcopur, Özgür, Klein-Gitelman, Marisa S., Kostik, Mikhail M., Ozen, Seza, Phadke, Omkar, Prahalad, Sampath, Randell, Rachel L., Sener, Seher, Stingl, Cory, Abdul-Aziz, Rabheh, Akoghlanian, Shoghik, Al Julandani, Dalila, Alvarez, Marcela B., Bader-Meunier, Brigitte, Balay-Dustrude, Erin E., Balboni, Imelda, Baxter, Sarah K., Berard, Roberta A., Bhattad, Sagar, Bolaria, Roxana, Boneparth, Alexis, Cassidy, Elaine A., Co, Dominic O., Collins, Kathleen P., Dancey, Paul, Dickinson, Aileen M., Edelheit, Barbara S., Espada, Graciela, Flanagan, Elaine R., Imundo, Lisa F., Jindal, Ankur K., Kim, Hyoun-Ah, Klaus, Günter, Lake, Carol, Lapin, W. Blaine, Lawson, Erica F., Marmor, Itay, Mombourquette, Joy, Ogunjimi, Benson, Olveda, Rebecca, Ombrello, Michael J., Onel, Karen, Poholek, Catherine, Ramanan, Athimalaipet V., Ravelli, Angelo, Reinhardt, Adam, Robinson, Amanda D., Rouster-Stevens, Kelly, Saad, Nadine, Schneider, Rayfel, Selmanovic, Velma, Sefic Pasic, Irmina, Shenoi, Susan, Shilo, Natalie R., Soep, Jennifer B., Sura, Angeli, Taber, Sarah F., Tesher, Melissa, Tibaldi, Jessica, Torok, Kathryn S., Tsin, Cathy Mei, Vasquez-Canizares, Natalia, Villacis Nunez, Diana S., Way, Emily E., Whitehead, Benjamin, Zemel, Lawrence S., Sharma, Surbhi, Fernández-Viña, Marcelo A., and Mellins, Elizabeth D.

Published
2024
Full Text
View/download PDF

16. Impulsivity across severe mental disorders: a cross-sectional study of immune markers and psychopharmacotherapy

Author

Hjell, Gabriela, Rokicki, Jaroslav, Szabo, Attila, Holst, René, Tesli, Natalia, Bell, Christina, Fischer-Vieler, Thomas, Werner, Maren Caroline Frogner, Lunding, Synve Hoffart, Ormerod, Monica Bettina Elkjær Greenwood, Johansen, Ingrid Torp, Djurovic, Srdjan, Ueland, Thor, Andreassen, Ole Andreas, Melle, Ingrid, Lagerberg, Trine Vik, Mørch-Johnsen, Lynn, Steen, Nils Eiel, and Haukvik, Unn Kristin

Published
2023
Full Text
View/download PDF

24. HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations

Author

Bastos, Anson, Singh, Kuldeep, Nadgeri, Abhishek, Shekarpour, Saeedeh, Mulang, Isaiah Onando, and Hoffart, Johannes

Subjects
Computer Science - Information Retrieval, Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Recently, several Knowledge Graph Embedding (KGE) approaches have been devised to represent entities and relations in dense vector space and employed in downstream tasks such as link prediction. A few KGE techniques address interpretability, i.e., mapping the connectivity patterns of the relations (i.e., symmetric/asymmetric, inverse, and composition) to a geometric interpretation such as rotations. Other approaches model the representations in higher dimensional space such as four-dimensional space (4D) to enhance the ability to infer the connectivity patterns (i.e., expressiveness). However, modeling relation and entity in a 4D space often comes at the cost of interpretability. This paper proposes HopfE, a novel KGE approach aiming to achieve the interpretability of inferred relations in the four-dimensional space. We first model the structural embeddings in 3D Euclidean space and view the relation operator as an SO(3) rotation. Next, we map the entity embedding vector from a 3D space to a 4D hypersphere using the inverse Hopf Fibration, in which we embed the semantic information from the KG ontology. Thus, HopfE considers the structural and semantic properties of the entities without losing expressivity and interpretability. Our empirical results on four well-known benchmarks achieve state-of-the-art performance for the KG completion task., Comment: CIKM 2021 : 30th ACM International Conference on Information and Knowledge Management (full paper)

Published
2021

25. KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction

Author

Nadgeri, Abhishek, Bastos, Anson, Singh, Kuldeep, Mulang', Isaiah Onando, Hoffart, Johannes, Shekarpour, Saeedeh, and Saraswat, Vijay

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG). Especially in this presumed sentential RE setting, the context of a single sentence is often sparse. This paper introduces the KGPool method to address this sparsity, dynamically expanding the context with additional facts from the KG. It learns the representation of these facts (entity alias, entity descriptions, etc.) using neural methods, supplementing the sentential context. Unlike existing methods that statically use all expanded facts, KGPool conditions this expansion on the sentence. We study the efficacy of KGPool by evaluating it with different neural models and KGs (Wikidata and NYT Freebase). Our experimental evaluation on standard datasets shows that by feeding the KGPool representation into a Graph Neural Network, the overall method is significantly more accurate than state-of-the-art methods., Comment: ACL 2021 (findings)

Published
2021

26. Impulsivity across severe mental disorders: a cross-sectional study of immune markers and psychopharmacotherapy

Author

Gabriela Hjell, Jaroslav Rokicki, Attila Szabo, René Holst, Natalia Tesli, Christina Bell, Thomas Fischer-Vieler, Maren Caroline Frogner Werner, Synve Hoffart Lunding, Monica Bettina Elkjær Greenwood Ormerod, Ingrid Torp Johansen, Srdjan Djurovic, Thor Ueland, Ole Andreas Andreassen, Ingrid Melle, Trine Vik Lagerberg, Lynn Mørch-Johnsen, Nils Eiel Steen, and Unn Kristin Haukvik

Subjects
Impulsiveness, Cytokines, Interleukin-1, Tumor necrosis factor, Chemokine CCL5, Psychopharmacology, Psychiatry, RC435-571
Abstract

Abstract Background Impulsivity is a transdiagnostic feature linked to severe clinical expression and a potential target for psychopharmacological strategies. Biological underpinnings are largely unknown, but involvement of immune dysregulation has been indicated, and the effects of psychopharmacological agents vary. We investigated if impulsivity was associated with circulating immune marker levels and with a range of psychopharmacological treatment regimens in severe mental disorders. Methods Impulsivity was assessed in a sample (N = 657) of patients with schizophrenia or schizophreniform disorder (SCZ) (N = 116) or bipolar disorder (BD) (N = 159) and healthy participants (N = 382) using the Barratt Impulsiveness Scale (BIS-11) questionnaire. Plasma levels of systemic immune markers (RANTES, IL-1RA, IL-18, IL-18BP, sTNFR-1) were measured by enzyme immunoassays. Patients underwent thorough clinical assessment, including evaluation of psychotropic medication. Associations were assessed using linear regressions. Results Impulsivity was positively associated with SCZ (p

Published
2023
Full Text
View/download PDF

27. Keratoconus and the Impact of Treatment on Patients’ Quality of Life: A Qualitative Study

Author

Fournié, Pierre, Acquadro, Michaël, Touboul, David, Cochener, Béatrice, Chiambaretta, Frédéric, Muraine, Marc, Borderie, Vincent, Bourges, Jean-Louis, Benmedjahed, Khadra, Tugaut, Béatrice, Bernheim, Diane, Bourcier, Tristan, Burillon, Carole, David, Thierry, Delbosc, Bernard, Gain, Philippe, Hoffart, Louis, Labetoulle, Marc, Laroche, Laurent, Malet, Florence, Orignac, Isabelle, Robert, Pierre-Yves, Thuret, Gilles, Vabres, Bertrand, Malecaze, François, and Arnould, Benoit

Published
2023
Full Text
View/download PDF

32. CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

Author

Ravi, Manoj Prabhakar Kannan, Singh, Kuldeep, Mulang', Isaiah Onando, Shekarpour, Saeedeh, Hoffart, Johannes, and Lehmann, Jens

Subjects
Computer Science - Computation and Language
Abstract

In this paper, we propose CHOLAN, a modular approach to target end-to-end entity linking (EL) over knowledge bases. CHOLAN consists of a pipeline of two transformer-based models integrated sequentially to accomplish the EL task. The first transformer model identifies surface forms (entity mentions) in a given text. For each mention, a second transformer model is employed to classify the target entity among a predefined candidates list. The latter transformer is fed by an enriched context captured from the sentence (i.e. local context), and entity description gained from Wikipedia. Such external contexts have not been used in the state of the art EL approaches. Our empirical study was conducted on two well-known knowledge bases (i.e., Wikidata and Wikipedia). The empirical results suggest that CHOLAN outperforms state-of-the-art approaches on standard datasets such as CoNLL-AIDA, MSNBC, AQUAINT, ACE2004, and T-REx., Comment: accepted in EACL 2021 (full paper)

Published
2021

35. Deep Dive Text Analytics and Natural Language Understanding

Author

Gómez-Pérez, Jose Manuel, García-Silva, Andrés, Berrio, Cristian, Rigau, German, Soroa, Aitor, Lieske, Christian, Hoffart, Johannes, Sasaki, Felix, Dahlmeier, Daniel, Skadiņa, Inguna, Bērziņš, Aivars, Vasiḷjevs, Andrejs, Lynn, Teresa, Sonntag, Daniel, Editor-in-Chief, Rehm, Georg, editor, and Way, Andy, editor

Published
2023
Full Text
View/download PDF

37. Expression of ANK3 moderates the association between childhood trauma and affective traits in severe mental disorders

Author

Monica Aas, Ole A. Andreassen, Johannes Gjerstad, Linn Rødevand, Gabriela Hjell, Ingrid Torp Johansen, Synve Hoffart Lunding, Monica B. E. G. Ormerod, Trine V. Lagerverg, Nils Eiel Steen, Srdjan Djurovic, and Ibrahim Akkouh

Subjects
Medicine, Science
Abstract

Abstract Exposure to early life trauma increases the risk of psychopathology later in life. Here we investigated if ANK3 mRNA levels influence the relationship between childhood trauma experiences and clinical characteristics in mental disorders. A sample of 174 patients with bipolar disorder and 291 patients with schizophrenia spectrum disorder were included. Patients were diagnosed using the Structured Clinical Interview for DSM-IV, and childhood trauma was assessed using the childhood trauma questionnaire. Age at illness onset and number of psychotic and affective episodes were assessed from interview and medical records. Current depressive symptoms were measured using the calgary depression scale for schizophrenia and the inventory for depressive symptomatology. ANK3 expression was analyzed in whole blood using the Illumina HumanHT-12 v4 Expression BeadChip. Analyses were carried out with the Process adjusted for confounders. Within the total sample, patients with both high ANK3 expression and with the most severe childhood sexual abuse had more manic/hypomanic episodes and an earlier age at onset of the first episode. ANK3 mRNA levels also moderated the relationship between emotional neglect and manic/hypomanic episodes. Our results suggest that ANK3 expression levels moderate the association between specific types of childhood trauma and affective traits in mental disorders.

Published
2023
Full Text
View/download PDF

38. RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network

Author

Bastos, Anson, Nadgeri, Abhishek, Singh, Kuldeep, Mulang', Isaiah Onando, Shekarpour, Saeedeh, Hoffart, Johannes, and Kaul, Manohar

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). RECON uses a graph neural network to learn representations of both the sentence as well as facts stored in a KG, improving the overall extraction quality. These facts, including entity attributes (label, alias, description, instance-of) and factual triples, have not been collectively used in the state of the art methods. We evaluate the effect of various forms of representing the KG context on the performance of RECON. The empirical evaluation on two standard relation extraction datasets shows that RECON significantly outperforms all state of the art methods on NYT Freebase and Wikidata datasets. RECON reports 87.23 F1 score (Vs 82.29 baseline) on Wikidata dataset whereas on NYT Freebase, reported values are 87.5(P@10) and 74.1(P@30) compared to the previous baseline scores of 81.3(P@10) and 63.1(P@30)., Comment: The Web Conference 2021 (WWW'21) full paper

Published
2020

39. Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models

Author

Mulang', Isaiah Onando, Singh, Kuldeep, Prabhu, Chaitali, Nadgeri, Abhishek, Hoffart, Johannes, and Lehmann, Jens

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, I.1.2
Abstract

Pretrained Transformer models have emerged as state-of-the-art approaches that learn contextual information from text to improve the performance of several NLP tasks. These models, albeit powerful, still require specialized knowledge in specific scenarios. In this paper, we argue that context derived from a knowledge graph (in our case: Wikidata) provides enough signals to inform pretrained transformer models and improve their performance for named entity disambiguation (NED) on Wikidata KG. We further hypothesize that our proposed KG context can be standardized for Wikipedia, and we evaluate the impact of KG context on state-of-the-art NED model for the Wikipedia knowledge base. Our empirical results validate that the proposed KG context can be generalized (for Wikipedia), and providing KG context in transformer architectures considerably outperforms the existing baselines, including the vanilla transformer models., Comment: to appear in proceedings of CIKM 2020

Published
2020
Full Text
View/download PDF

40. From Stock Prediction to Financial Relevance: Repurposing Attention Weights to Assess News Relevance Without Manual Annotations

Author

Del Corro, Luciano and Hoffart, Johannes

Subjects
Computer Science - Computation and Language, I.2.7
Abstract

We present a method to automatically identify financially relevant news using stock price movements and news headlines as input. The method repurposes the attention weights of a neural network initially trained to predict stock prices to assign a relevance score to each headline, eliminating the need for manually labeled training data. Our experiments on the four most relevant US stock indices and 1.5M news headlines show that the method ranks relevant news highly, positively correlated with the accuracy of the initial stock price prediction task.

Published
2020

42. Treatment Fidelity in Brief versus Standard-Length School-Based Interventions for Youth with Anxiety

Author

Husabo, Elisabeth, Haugland, Bente S. M., McLeod, Bryce D., Baste, Valborg, Haaland, Åshild Tellefsen, Bjaastad, Jon Fauskanger, Hoffart, Asle, Raknes, Solfrid, Fjermestad, Krister W., Rapee, Ronald M., Ogden, Terje, and Wergeland, Gro Janne

Abstract

To examine treatment fidelity in a randomized controlled trial of indicated school-based cognitive-behavioral therapy (CBT) delivered in groups to youth with anxiety. We investigated whether adherence and competence (a) differed across brief and standard-length CBT, and (b) if adherence and competence predicted change in anxiety symptoms and impairment. Method: Sessions were observationally coded with the "Competence and Adherence Scale for CBT for Anxiety Disorders in Youth." Coders (N = 7) rated 104 sessions from 52 groups delivered by 32 facilitators (M age = 43.2 years, SD = 8.1) to 295 youth (M age = 14.0 years, SD = 0.8). Outcomes were youth- and parent-reported anxiety symptoms and impairment at post-intervention and 1-year follow-up. Linear mixed effect models were used to analyze whether fidelity predicted clinical outcomes. Results: Levels of adherence and competence were adequate in both programs, but higher in brief compared to standard-length CBT p < 0.001 and p = 0.010, respectively). Neither adherence nor competence predicted clinical outcomes at any timepoints. Conclusion: Higher levels of adherence and competence in brief CBT suggest that it may be easier for novice CBT providers to achieve fidelity in simplified and less flexible interventions. Contrary to expectation, adherence and competence did not predict clinical outcomes.

Published
2022
Full Text
View/download PDF

43. A three-year cohort study of the relationships between coping, job stress and burnout after a counselling intervention for help-seeking physicians

Author

Hoffart Asle, Tyssen Reidar, Isaksson Ro Karin E, Sexton Harold, Aasland Olaf G, and Gude Tore

Subjects
Public aspects of medicine, RA1-1270
Abstract

Abstract Background Knowledge about important factors in reduction of burnout is needed, but there is a dearth of burnout intervention program studies and their effects among physicians. The present three-year follow-up study aimed to investigate the roles of coping strategies, job stress and personality traits in burnout reduction after a counselling intervention for distressed physicians. Methods 227 physicians who attended a counselling intervention for burnout at the Resource Centre Villa Sana, Norway in 2003-2005, were followed with self-report assessments at baseline, one-year, and three-year follow-up. Main outcome measures were emotional exhaustion (one dimension of burnout), job stress, coping strategies and neuroticism. Changes in these measures were analyzed with repeated measures ANOVA. Temporal relationships between changes were examined using structural modelling with cross-lagged and synchronous panel models. Results 184 physicians (81%, 83 men, 101 women) completed the three-year follow-up assessment. Significantly reduced levels of emotional exhaustion, job stress, and emotion-focused coping strategies from baseline to one year after the intervention, were maintained at three-year follow-up. Panel modelling indicated that changes in emotion-focused coping (z = 4.05, p < 0.001) and job stress (z = 3.16, p < 0.01) preceded changes in emotional exhaustion from baseline to three-year follow-up. A similar pattern was found from baseline to one-year follow-up. Conclusion A sequential relationship indicated that reduction in emotion-focused coping and in job stress preceded reduction in emotional exhaustion. As a consequence, coping strategies and job stress could be important foci in intervention programs that aim to reduce or prevent burnout in help-seeking physicians.

Published
2010
Full Text
View/download PDF

44. Keratoconus and the Impact of Treatment on Patients’ Quality of Life: A Qualitative Study

Author

Pierre Fournié, Michaël Acquadro, David Touboul, Béatrice Cochener, Frédéric Chiambaretta, Marc Muraine, Vincent Borderie, Jean-Louis Bourges, Khadra Benmedjahed, Béatrice Tugaut, Diane Bernheim, Tristan Bourcier, Carole Burillon, Thierry David, Bernard Delbosc, Philippe Gain, Louis Hoffart, Marc Labetoulle, Laurent Laroche, Florence Malet, Isabelle Orignac, Pierre-Yves Robert, Gilles Thuret, Bertrand Vabres, François Malecaze, and Benoit Arnould

Subjects
Keratoconus, Quality of life, Questionnaire, Patient-reported outcomes, Contact lens, Cross-linking, Ophthalmology, RE1-994
Abstract

Abstract Introduction Keratoconus has a significant impact on patients’ quality of life (QoL), from diagnosis to the advanced stages of the disease. The aim of this research was to identify domains of QoL affected by this disease and its treatment. Methods Phone interviews were conducted using a semi-structured interview guide, with patients with keratoconus stratified according to their current treatment. A board of keratoconus experts helped identify the guide’s main themes. Results Thirty-five patients (rigid contact lenses, n = 9; cross-linking, n = 9; corneal ring implants, n = 8; and corneal transplantation, n = 9) were interviewed by qualitative researchers. Phone interviews revealed several QoL domains affected by the disease and its treatments: “psychological”, “social life”, “professional life”, “financial costs” and “student life”. All domains were impacted, independently of the treatment history. Few differences were found between treatment regimens and keratoconus stages. Qualitative analysis enabled the development of a conceptual framework based on Wilson and Cleary’s model for patient outcomes common to all patients. This conceptual model describes the relationship between patients’ characteristics, their symptoms, their environment, their functional visual impairment and the impact on their QoL. Conclusions These qualitative findings supported the generation of a questionnaire to evaluate the impact of keratoconus and its treatment on patients’ QoL. Cognitive debriefings confirmed its content validity. The questionnaire is applicable for all stages of keratoconus and treatments and may help tracking change over time in regular clinical settings. Psychometric validation is yet to be performed before its use in research and clinical practices.

Published
2023
Full Text
View/download PDF

45. Tobacco smoking related to childhood trauma mediated by cognitive control and impulsiveness in severe mental disorders

Author

Lunding, Synve Hoffart, Ueland, Torill, Aas, Monica, Høegh, Margrethe Collier, Werner, Maren Caroline Frogner, Rødevand, Linn, Johansen, Ingrid Torp, Hjell, Gabriela, Ormerod, Monica Bettina Elkjær Greenwood, Ringen, Petter Andreas, Ottesen, Akiah, Lagerberg, Trine Vik, Melle, Ingrid, Andreassen, Ole A., Simonsen, Carmen, and Steen, Nils Eiel

Published
2023
Full Text
View/download PDF

46. Elevated symptoms of depression and anxiety among family members and friends of critically ill COVID-19 patients – an observational study of five cohorts across four countries

Author

Lovik, Anikó, González-Hijón, Juan, Hoffart, Asle, Fawns-Ritchie, Chloe, Magnúsdóttir, Ingibjörg, Lu, Li, Unnarsdóttir, Anna Bára, Kähler, Anna K., Campbell, Archie, Hauksdóttir, Arna, Chourpiliadis, Charilaos, McCartney, Daniel L., Thordardóttir, Edda Björk, Joyce, Emily E., Frans, Emma M., Jakobsdóttir, Jóhanna, Trogstad, Lill, Andreassen, Ole A., Magnus, Per, Johnson, Sverre Urnes, Sullivan, Patrick F., Aspelund, Thor, Porteous, David J., Ask, Helga, Ebrahimi, Omid V., Valdimarsdóttir, Unnur Anna, and Fang, Fang

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results