Publications

1449 Publications visible to you, out of a total of 1449

Abstract

Not specified

Authors: Chloé Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaciga, Michael Strube, Amir Zeldes

Date Published: 13th Jul 2023

Publication Type: Proceedings

Abstract (Expand)

Automating Cross-lingual Science Journalism (CSJ) aims to generate popular science summaries from English scientific texts for non-expert readers in their local language. We introduce CSJ as a downstream task of text simplification and cross-lingual scientific summarization to facilitate science journalists’ work. We analyze the performance of possible existing solutions as baselines for the CSJ task. Based on these findings, we propose to combine the three components - SELECT, SIMPLIFY and REWRITE (SSR) to produce cross-lingual simplified science summaries for non-expert readers. Our empirical evaluation on the WIKIPEDIA dataset shows that SSR significantly outperforms the baselines for the CSJ task and can serve as a strong baseline for future work. We also perform an ablation study investigating the impact of individual components of SSR. Further, we analyze the performance of SSR on a high-quality, real-world CSJ dataset with human evaluation and in-depth analysis, demonstrating the superior performance of SSR for CSJ.

Authors: Mehwish Fatima, Michael Strube

Date Published: 8th Jul 2023

Publication Type: InProceedings

Abstract (Expand)

Coherence is an important aspect of text quality, and various approaches have been applied to coherence modeling. However, existing methods solely focus on a single document’s coherence patterns, ignoring the underlying correlation between documents. We investigate a GCN-based coherence model that is capable of capturing structural similarities between documents. Our model first identifies the graph structure of each document, from where we mine different sub-graph patterns. We then construct a heterogeneous graph for the training corpus, connecting documents based on their shared subgraphs. Finally, a GCN is applied to the heterogeneous graph to model the connectivity relationships. We evaluate our method on two tasks, assessing discourse coherence and automated essay scoring. Results show that our GCN-based model outperforms baselines, achieving a new state-of-the-art on both tasks.

Authors: Wei Liu, Xiyan Fu, Michael Strube

Date Published: 8th Jul 2023

Publication Type: InProceedings

Abstract (Expand)

Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for the task, inspired by the annotation process of PDTB. Specifically, our model jointly learns to generate discourse connectives between arguments and predict discourse relations based on the arguments and the generated connectives. To prevent our relation classifier from being misled by poor connectives generated at the early stage of training while alleviating the discrepancy between training and inference, we adopt Scheduled Sampling to the joint learning. We evaluate our method on three benchmarks, PDTB 2.0, PDTB 3.0, and PCC. Results show that our joint model significantly outperforms various baselines on three datasets, demonstrating its superiority for the task.

Authors: Wei Liu, Michael Strube

Date Published: 8th Jul 2023

Publication Type: InProceedings

Abstract

Not specified

Authors: Evan L. Ray, Logan C. Brooks, Jacob Bien, Matthew Biggerstaff, Nikos I. Bosse, Johannes Bracher, Estee Y. Cramer, Sebastian Funk, Aaron Gerding, Michael A. Johansson, Aaron Rumack, Yijin Wang, Martha Zorn, Ryan J. Tibshirani, Nicholas G. Reich

Date Published: 1st Jul 2023

Publication Type: Journal

Abstract

Not specified

Authors: Jonas R. Brehmer, Tilmann Gneiting, Marcus Herrmann, Warner Marzocchi, Martin Schlather, Kirstin Strokorb

Date Published: 15th Jun 2023

Publication Type: Journal

Abstract (Expand)

This document defines challenges and requirements for predictive computational models constructed for research purposes in personalized medicine. It specifies recommendations and requirements for the setup, formatting, validation, simulation, storing and sharing of such models, as well as their application in clinical trials and other research areas. It summarizes specific challenges regarding data input, as well as verifying and validating of such models that can be considered as best practices for modelling in research and development in the field of personalized medicine. This document also specifies recommendations and requirements for data used to construct or needed for validating models, including rules and requirements for formatting, description, annotation, interoperability, integration, accessing, as well as recording and documenting the provenance of such data. This document does not provide specific rules or requirements for the use of computational models in the clinical routine, or for diagnostic or therapeutic purposes.

Authors: Marc Kirschner, Martin Golebiewski, Heike Moser, EU-STANDS4PM consortium, ISO/TC 276/WG 5

Date Published: 8th Jun 2023

Publication Type: Manual

Powered by
(v.1.12.2)
Copyright © 2008 - 2022 The University of Manchester and HITS gGmbH