Michael Strube

Overview
Related items

About Michael Strube:

No description specified

SEEK ID: https://publications.h-its.org/people/127

Location: Germany

ORCID: Not specified

Joined: 19th Jul 2022

Expertise: Not specified

Tools: Not specified

Their tags

This person has not yet tagged anything.

Project positions

Other Projects: Natural Language Processing (Heidelberg Institute for Theoretical Studies)

Related items

Natural Language Processing

No description specified

Public web page: Not specified

Organisms: Not specified

Heidelberg Institute for Theoretical Studies

Country: Germany

City: Heidelberg

Web page: https://www.h-its.org

Cross-lingual Science Journalism: Select, Simplify and Rewrite Summaries for Non-expert Readers

Natural Language Processing

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 …

Authors: Mehwish Fatima, Michael Strube

Date Published: 8th Jul 2023

Publication Type: Journal

Citation: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, Ontario, Canada, July 2023

Created: 31st May 2023 at 10:45, Last updated: 31st May 2023 at 11:40

Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks

Natural Language Processing

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, …

Authors: Wei Liu, Xiyan Fu, Michael Strube

Date Published: 8th Jul 2023

Publication Type: InProceedings

Citation: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, Ontario, Canada, July 2023

Created: 31st May 2023 at 11:36, Last updated: 31st May 2023 at 11:40

Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation

Natural Language Processing

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 …

Authors: Wei Liu, Michael Strube

Date Published: 8th Jul 2023

Publication Type: InProceedings

Citation: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, Ontario, Canada, July 2023

Created: 31st May 2023 at 11:38, Last updated: 31st May 2023 at 11:41

DiscoScore: Evaluating text generation with BERT and discourse coherence

Natural Language Processing

Abstract (Expand)

Recently, there has been a growing interest in designing text generation systems from a discourse coherence perspective, e.g., modeling the interdependence between sentences. Still, recent BERT-based …

Authors: Wei Zhao, Michael Strube, Steffen Eger

Date Published: 2nd May 2023

Publication Type: InProceedings

Citation: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, May 2023, pp.3865-3883

Created: 6th Feb 2023 at 14:16, Last updated: 31st May 2023 at 11:30

Constrained density matching and modeling for cross-lingual alignment of contextualized representations

Natural Language Processing

Abstract (Expand)

Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized …

Authors: Wei Zhao, Steffen Eger

Date Published: 12th Dec 2022

Publication Type: InProceedings

DOI: 10.48550/arXiv.2201.13429

Citation: Proceedings of Machine Learning Research, 2022. Asian Conference on Machine Leaning, Hyderabad, India, 12-14 December 2022

Created: 8th Feb 2023 at 15:52, Last updated: 9th Feb 2023 at 16:00

View all 60 items

(v.1.12.2)

About HITS Publication SEEK | About HITS-Publication-SEEK | Funding and Programmes | Credits