Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Nils Reimers, Iryna Gurevych
- Computer ScienceConference on Empirical Methods in Natural…
- 14 August 2019
Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity is presented.
A Monolingual Tree-based Translation Model for Sentence Simplification
- Zhemin Zhu, D. Bernhard, Iryna Gurevych
- Computer ScienceInternational Conference on Computational…
- 23 August 2010
A Tree-based Simplification Model (TSM) is proposed, which, to the knowledge, is the first statistical simplification model covering splitting, dropping, reordering and substitution integrally.
MAD-X: An Adapter-based Framework for Multi-task Cross-lingual Transfer
- Jonas Pfeiffer, Ivan Vulic, Iryna Gurevych, Sebastian Ruder
- Computer Science, LinguisticsConference on Empirical Methods in Natural…
- 30 April 2020
MAD-X is proposed, an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations and introduces a novel invertible adapter architecture and a strong baseline method for adapting a pretrained multilingual model to a new language.
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
- Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho, Iryna Gurevych
- Computer ScienceConference of the European Chapter of the…
- 1 May 2020
This work proposes AdapterFusion, a new two stage learning algorithm that leverages knowledge from multiple tasks by separating the two stages, i.e., knowledge extraction and knowledge composition, so that the classifier can effectively exploit the representations learned frommultiple tasks in a non-destructive manner.
Parsing Argumentation Structures in Persuasive Essays
- Christian Stab, Iryna Gurevych
- Computer ScienceInternational Conference on Computational Logic
- 25 April 2016
A novel approach for parsing argumentation structures is presented, which globally optimizes argument component types and argumentative relations using Integer Linear Programming and significantly outperforms challenging heuristic baselines on two different types of discourse.
AdapterHub: A Framework for Adapting Transformers
- Jonas Pfeiffer, Andreas Rücklé, Iryna Gurevych
- Computer ScienceConference on Empirical Methods in Natural…
- 15 July 2020
AdaptersHub is proposed, a framework that allows dynamic “stiching-in” of pre-trained adapters for different tasks and languages that enables scalable and easy access to sharing of task-specific models, particularly in low-resource scenarios.
Making Monolingual Sentence Embeddings Multilingual Using Knowledge Distillation
- Nils Reimers, Iryna Gurevych
- Computer ScienceConference on Empirical Methods in Natural…
- 21 April 2020
An easy and efficient method to extend existing sentence embedding models to new languages by using the original (monolingual) model to generate sentence embeddings for the source language and then training a new system on translated sentences to mimic the original model.
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
- Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan, Iryna Gurevych
- Computer ScienceAnnual Meeting of the Association for…
- 27 May 2019
This paper evaluates summaries produced by state-of-the-art models via crowdsourcing and shows that such errors occur frequently, in particular with more abstractive models, which leads to an interesting downstream application for entailment models.
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification
- Andreas Hanselowski, H. Zhang, Iryna Gurevych
- Computer SciencearXiv.org
- 3 September 2018
This paper presents the claim verification pipeline approach, which, according to the preliminary results, scored third in the shared task, out of 23 competing systems, and introduces two extensions to the Enhanced LSTM (ESIM).
Annotating Argument Components and Relations in Persuasive Essays
- Christian Stab, Iryna Gurevych
- PhilosophyInternational Conference on Computational…
- 1 August 2014
An annotation scheme that includes the annotation of claims and premises as well as support and attack relations for capturing the structure of argumentative discourse is proposed.
...
...