Search Results - "Habernal, Ivan"

Argumentation Mining in User-Generated Web Discourse by Habernal, Ivan, Gurevych, Iryna

“…The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people's argumentation. In…”
Get full text

SWSNL: Semantic Web Search Using Natural Language by Habernal, Ivan, Konopík, Miloslav

“…► We present semantic search system with a natural language interface. ► A corpus of queries in the Czech language was collected using social media. ► An…”
Get full text

Mining legal arguments in court decisions by Habernal, Ivan, Faber, Daniel, Recchia, Nicola, Bretthauer, Sebastian, Gurevych, Iryna, Spiecker genannt Döhmann, Indra, Burchard, Christoph

“…Identifying, classifying, and analyzing arguments in legal discourse has been a prominent area of research since the inception of the argument mining field…”
Get full text

Supervised sentiment analysis in Czech social media by Habernal, Ivan, Ptáček, Tomáš, Steinberger, Josef

“…•We explore state-of-the-art supervised machine learning methods for sentiment analysis of Czech social media.•We provide a large human-annotated Czech social…”
Get full text

Reprint of “Supervised sentiment analysis in Czech social media” by Habernal, Ivan, Ptáček, Tomáš, Steinberger, Josef

“…•We explore state-of-the-art supervised machine learning methods for sentiment analysis of Czech social media.•We provide a large human-annotated Czech social…”
Get full text

How reparametrization trick broke differentially-private text representation learning by Habernal, Ivan

“…As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy…”
Get full text

Private Synthetic Text Generation with Diffusion Models by Ochs, Sebastian, Habernal, Ivan

“…How capable are diffusion models of generating synthetics texts? Recent research shows their strengths, with performance reaching that of auto-regressive LLMs…”
Get full text

When differential privacy meets NLP: The devil is in the detail by Habernal, Ivan

“…Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users'…”
Get full text

LaCour!: Enabling Research on Argumentation in Hearings of the European Court of Human Rights by Held, Lena, Habernal, Ivan

“…Why does an argument end up in the final court decision? Was it deliberated or questioned during the oral hearings? Was there something in the hearings that…”
Get full text

DP-BART for Privatized Text Rewriting under Local Differential Privacy by Igamberdiev, Timour, Habernal, Ivan

“…Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally…”
Get full text

Privacy-Preserving Models for Legal Natural Language Processing by Yin, Ying, Habernal, Ivan

“…Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks…”
Get full text

Privacy-Preserving Graph Convolutional Networks for Text Classification by Igamberdiev, Timour, Habernal, Ivan

“…Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or…”
Get full text

To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems? by Weiss, Christopher, Kreuter, Frauke, Habernal, Ivan

“…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…”
Get full text

Trade-Offs Between Fairness and Privacy in Language Modeling by Matzken, Cleo, Eger, Steffen, Habernal, Ivan

“…Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the…”
Get full text

The Impact of Inference Acceleration Strategies on Bias of LLMs by Kirsten, Elisabeth, Habernal, Ivan, Nanda, Vedant, Zafar, Muhammad Bilal

“…Last few years have seen unprecedented advances in capabilities of Large Language Models (LLMs). These advancements promise to deeply benefit a vast array of…”
Get full text

Private Language Models via Truncated Laplacian Mechanism by Huang, Tianhao, Yang, Tao, Habernal, Ivan, Hu, Lijie, Wang, Di

“…Deep learning models for NLP tasks are prone to variants of privacy attacks. To prevent privacy leakage, researchers have investigated word-level…”
Get full text

Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation by Vu, Doan Nam Long, Igamberdiev, Timour, Habernal, Ivan

“…Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP…”
Get full text

The Legal Argument Reasoning Task in Civil Procedure by Bongard, Leonard, Held, Lena, Habernal, Ivan

“…We present a new NLP task and dataset from the domain of the U.S. civil procedure. Each instance of the dataset consists of a general introduction to the case,…”
Get full text

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting by Igamberdiev, Timour, Arnold, Thomas, Habernal, Ivan

“…Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In…”
Get full text

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks by Senge, Manuel, Igamberdiev, Timour, Habernal, Ivan

“…Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price. We know that stricter privacy…”
Get full text