Search Results for author: Ivan Habernal

Found 34 papers, 20 papers with code

LaCour!: Enabling Research on Argumentation in Hearings of the European Court of Human Rights

no code implementations8 Dec 2023 Lena Held, Ivan Habernal

Was there something in the hearings that triggered a particular judge to write a dissenting opinion?


DP-NMT: Scalable Differentially-Private Machine Translation

1 code implementation24 Nov 2023 Timour Igamberdiev, Doan Nam Long Vu, Felix Künnecke, Zhuo Yu, Jannik Holmer, Ivan Habernal

Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems.

Machine Translation NMT +3

To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?

no code implementations13 Jul 2023 Christopher Weiss, Frauke Kreuter, Ivan Habernal

Although the NLP community has adopted central differential privacy as a go-to framework for privacy-preserving model training or data sharing, the choice and interpretation of the key parameter, privacy budget $\varepsilon$ that governs the strength of privacy protection, remains largely arbitrary.

Decision Making Privacy Preserving

DP-BART for Privatized Text Rewriting under Local Differential Privacy

1 code implementation15 Feb 2023 Timour Igamberdiev, Ivan Habernal

Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protection to individuals.

text-classification Text Classification

Differentially Private Natural Language Models: Recent Advances and Future Directions

no code implementations22 Jan 2023 Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP.

The Legal Argument Reasoning Task in Civil Procedure

1 code implementation5 Nov 2022 Leonard Bongard, Lena Held, Ivan Habernal

We present a new NLP task and dataset from the domain of the U. S. civil procedure.


Privacy-Preserving Models for Legal Natural Language Processing

1 code implementation5 Nov 2022 Ying Yin, Ivan Habernal

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks.

Domain Adaptation Privacy Preserving +1

How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application

no code implementations5 Sep 2022 Ramit Sawhney, Atula Tejaswi Neerkaje, Ivan Habernal, Lucie Flek

Clinical NLP tasks such as mental health assessment from text, must take social constraints into account - the performance maximization must be constrained by the utmost importance of guaranteeing privacy of user data.

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

1 code implementation COLING 2022 Timour Igamberdiev, Thomas Arnold, Ivan Habernal

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents.

Privacy Preserving

Mining Legal Arguments in Court Decisions

1 code implementation12 Aug 2022 Ivan Habernal, Daniel Faber, Nicola Recchia, Sebastian Bretthauer, Iryna Gurevych, Indra Spiecker genannt Döhmann, Christoph Burchard

Identifying, classifying, and analyzing arguments in legal discourse has been a prominent area of research since the inception of the argument mining field.

Argument Mining

How reparametrization trick broke differentially-private text representation learning

1 code implementation ACL 2022 Ivan Habernal

As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods.

Privacy Preserving Representation Learning

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks

1 code implementation15 Dec 2021 Manuel Senge, Timour Igamberdiev, Ivan Habernal

Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price.

Privacy Preserving

When differential privacy meets NLP: The devil is in the detail

2 code implementations EMNLP 2021 Ivan Habernal

Our proof reveals that ADePT is not differentially private, thus rendering the experimental results unsubstantiated.

Privacy-Preserving Graph Convolutional Networks for Text Classification

1 code implementation LREC 2022 Timour Igamberdiev, Ivan Habernal

Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e. g., citation or social networks.

General Classification Privacy Preserving +3

Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision

1 code implementation Findings of the Association for Computational Linguistics 2020 Max Glockner, Ivan Habernal, Iryna Gurevych

We propose a differentiable training-framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task.

Decision Making Sentence

Computational Argumentation: A Journey Beyond Semantics, Logic, Opinions, and Easy Tasks

no code implementations WS 2018 Ivan Habernal

The classical view on argumentation, such that arguments are logical structures consisting of different distinguishable parts and that parties exchange arguments in a rational way, is prevalent in textbooks but nonexistent in the real world.

Common Sense Reasoning

C4Corpus: Multilingual Web-size Corpus with Free License

1 code implementation LREC 2016 Ivan Habernal, Omnia Zayed, Iryna Gurevych

Large Web corpora containing full documents with permissive licenses are crucial for many NLP tasks.

Argumentation Mining in User-Generated Web Discourse

no code implementations CL 2017 Ivan Habernal, Iryna Gurevych

The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people's argumentation.

Cannot find the paper you are looking for? You can Submit a new open access paper.