no code implementations • EMNLP 2020 • Anne Lauscher, Vinit Ravishankar, Ivan Vuli{\'c}, Goran Glava{\v{s}}
Massively multilingual transformers (MMTs) pretrained via language modeling (e. g., mBERT, XLM-R) have become a default paradigm for zero-shot language transfer in NLP, offering unmatched transfer performance.
1 code implementation • Findings (ACL) 2022 • Chia-Chien Hung, Anne Lauscher, Simone Ponzetto, Goran Glavaš
Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD).
1 code implementation • LTEDI (ACL) 2022 • Debora Nozza, Federico Bianchi, Anne Lauscher, Dirk Hovy
Current language technology is ubiquitous and directly influences individuals’ lives worldwide.
no code implementations • 10 May 2024 • Ilia Kuznetsov, Osama Mohammed Afzal, Koen Dercksen, Nils Dycke, Alexander Goldberg, Tom Hope, Dirk Hovy, Jonathan K. Kummerfeld, Anne Lauscher, Kevin Leyton-Brown, Sheng Lu, Mausam, Margot Mieskes, Aurélie Névéol, Danish Pruthi, Lizhen Qu, Roy Schwartz, Noah A. Smith, Thamar Solorio, Jingyan Wang, Xiaodan Zhu, Anna Rogers, Nihar B. Shah, Iryna Gurevych
We hope that our work will help set the agenda for research in machine-assisted scientific quality control in the age of AI, within the NLP community and beyond.
2 code implementations • 4 Apr 2024 • Vagrant Gautam, Eileen Bingert, Dawei Zhu, Anne Lauscher, Dietrich Klakow
Robust, faithful and harm-free pronoun use for individuals is an important goal for language models as their use increases, but prior work tends to study only one or two of these characteristics at a time.
no code implementations • 24 Mar 2024 • Henning Wachsmuth, Gabriella Lapesa, Elena Cabrio, Anne Lauscher, Joonsuk Park, Eva Maria Vecchi, Serena Villata, Timon Ziegenbein
The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like.
1 code implementation • 6 Mar 2024 • Carolin Holtermann, Paul Röttger, Timm Dill, Anne Lauscher
Therefore, in this paper, we investigate the basic multilingual capabilities of state-of-the-art open LLMs beyond their intended use.
1 code implementation • 23 Jan 2024 • Carolin Holtermann, Markus Frohmann, Navid Rekabsaz, Anne Lauscher
The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks.
1 code implementation • 7 Nov 2023 • Sukannya Purkayastha, Anne Lauscher, Iryna Gurevych
In this work, we are the first to explore Jiu-Jitsu argumentation for peer review by proposing the novel task of attitude and theme-guided rebuttal generation.
no code implementations • 21 Oct 2023 • Karina Vida, Judith Simon, Anne Lauscher
For instance, we analyse what ethical theory an approach is based on, how this decision is justified, and what implications it entails.
1 code implementation • 18 Oct 2023 • Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza, Anne Lauscher
In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices.
1 code implementation • 2 Oct 2023 • Markus Frohmann, Carolin Holtermann, Shahed Masoudian, Anne Lauscher, Navid Rekabsaz
We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective knowledge transfer to a target task.
1 code implementation • 30 Sep 2023 • Jonas Belouadi, Anne Lauscher, Steffen Eger
To address this, we propose the use of TikZ, a well-known abstract graphics language that can be compiled to vector graphics, as an intermediate representation of scientific figures.
1 code implementation • 13 Sep 2023 • Tilman Beck, Hendrik Schuff, Anne Lauscher, Iryna Gurevych
However, the available NLP literature disagrees on the efficacy of this technique - it remains unclear for which tasks and scenarios it can help, and the role of the individual factors in sociodemographic prompting is still unexplored.
no code implementations • 26 May 2023 • Eddie L. Ungless, Björn Ross, Anne Lauscher
Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications.
no code implementations • 25 May 2023 • Anne Lauscher, Debora Nozza, Archie Crowley, Ehm Miltersen, Dirk Hovy
As 3rd-person pronoun usage shifts to include novel forms, e. g., neopronouns, we need more research on identity-inclusive NLP.
1 code implementation • 8 Nov 2022 • Anne Lauscher, Federico Bianchi, Samuel Bowman, Dirk Hovy
Our results show that PLMs do encode these sociodemographics, and that this knowledge is sometimes spread across the layers of some of the tested PLMs.
no code implementations • 8 Nov 2022 • Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher
Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence.
1 code implementation • 13 Oct 2022 • Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavaš
Previous work showed that incorporating demographic factors can consistently improve performance for various NLP tasks with traditional NLP models.
no code implementations • 12 Oct 2022 • Zeerak Talat, Anne Lauscher
Machine learning and NLP require the construction of datasets to train and fine-tune models.
1 code implementation • 1 Aug 2022 • Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavaš
We adapt the language representations for the sociodemographic dimensions of gender and age, using continuous language modeling and dynamic multi-task learning for adaptation, where we couple language modeling with the prediction of a sociodemographic class.
1 code implementation • NAACL 2022 • Chia-Chien Hung, Anne Lauscher, Ivan Vulić, Simone Paolo Ponzetto, Goran Glavaš
We then introduce a new framework for multilingual conversational specialization of pretrained language models (PrLMs) that aims to facilitate cross-lingual transfer for arbitrary downstream TOD tasks.
1 code implementation • ACL 2022 • Carolin Holtermann, Anne Lauscher, Simone Paolo Ponzetto
We employ our resource to assess the effect of argumentative fine-tuning and debiasing on the intrinsic bias found in transformer-based language models using a lightweight adapter-based approach that is more sustainable and parameter-efficient than full fine-tuning.
no code implementations • COLING 2022 • Anne Lauscher, Archie Crowley, Dirk Hovy
Based on our observations and ethical considerations, we define a series of desiderata for modeling pronouns in language technology.
1 code implementation • 15 Oct 2021 • Chia-Chien Hung, Anne Lauscher, Simone Paolo Ponzetto, Goran Glavaš
Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD).
no code implementations • Findings (EMNLP) 2021 • Anne Lauscher, Tobias Lüken, Goran Glavaš
Unfair stereotypical biases (e. g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology.
1 code implementation • 13 Aug 2021 • Tobias Walter, Celina Kirschner, Steffen Eger, Goran Glavaš, Anne Lauscher, Simone Paolo Ponzetto
We analyze bias in historical corpora as encoded in diachronic distributional semantic models by focusing on two specific forms of bias, namely a political (i. e., anti-communism) and racist (i. e., antisemitism) one.
no code implementations • 1 Jul 2021 • Anne Lauscher, Henning Wachsmuth, Iryna Gurevych, Goran Glavaš
Despite extensive research efforts in recent years, computational argumentation (CA) remains one of the most challenging areas of natural language processing.
1 code implementation • NAACL 2022 • Anne Lauscher, Brandon Ko, Bailey Kuehl, Sophie Johnson, David Jurgens, Arman Cohan, Kyle Lo
In our work, we address this research gap by proposing a novel framework for CCA as a document-level context extraction and labeling task.
1 code implementation • ACL 2021 • Soumya Barikeri, Anne Lauscher, Ivan Vulić, Goran Glavaš
We use the evaluation framework to benchmark the widely used conversational DialoGPT model along with the adaptations of four debiasing methods.
2 code implementations • EACL 2021 • Niklas Friedrich, Anne Lauscher, Simone Paolo Ponzetto, Goran Glavaš
In this work, we present DebIE, the first integrated platform for (1) measuring and (2) mitigating bias in word embeddings.
no code implementations • 21 Dec 2020 • Shintaro Yamamoto, Anne Lauscher, Simone Paolo Ponzetto, Goran Glavaš, Shigeo Morishima
Providing visual summaries of scientific publications can increase information access for readers and thereby help deal with the exponential growth in the number of scientific publications.
no code implementations • COLING (WANLP) 2020 • Anne Lauscher, Rafik Takieddin, Simone Paolo Ponzetto, Goran Glavaš
Our analysis yields several interesting findings, e. g., that implicit gender bias in embeddings trained on Arabic news corpora steadily increases over time (between 2007 and 2017).
1 code implementation • COLING (ArgMining) 2020 • Lily Ng, Anne Lauscher, Joel Tetreault, Courtney Napoles
Computational models of argument quality (AQ) have focused primarily on assessing the overall quality or just one specific characteristic of an argument, such as its convincingness or its clarity.
1 code implementation • COLING 2020 • Anne Lauscher, Lily Ng, Courtney Napoles, Joel Tetreault
Though preceding work in computational argument quality (AQ) mostly focuses on assessing overall AQ, researchers agree that writers would benefit from feedback targeting individual dimensions of argumentation theory.
1 code implementation • 25 May 2020 • Marilena Daquino, Silvio Peroni, David Shotton, Giovanni Colavizza, Behnam Ghavimi, Anne Lauscher, Philipp Mayr, Matteo Romanello, Philipp Zumstein
A variety of schemas and ontologies are currently used for the machine-readable description of bibliographic entities and citations.
Digital Libraries
1 code implementation • EMNLP (DeeLIO) 2020 • Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro, Iryna Gurevych, Nikolai Rozanov, Goran Glavaš
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models.
no code implementations • 1 May 2020 • Anne Lauscher, Vinit Ravishankar, Ivan Vulić, Goran Glavaš
Massively multilingual transformers pretrained with language modeling objectives (e. g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance.
4 code implementations • 13 Sep 2019 • Anne Lauscher, Goran Glavaš, Simone Paolo Ponzetto, Ivan Vulić
Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.
1 code implementation • COLING 2020 • Anne Lauscher, Ivan Vulić, Edoardo Maria Ponti, Anna Korhonen, Goran Glavaš
In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining.
1 code implementation • Joint Conference on Digital Libraries (JCDL) 2019 • Anne Lauscher, Yide Song, Kiril Gashteovski
Acknowledging the importance of citations in scientific literature, in this work we present MinScIE, an Open Information Extraction system which provides structured knowledge enriched with semantic information about citations.
1 code implementation • SEMEVAL 2019 • Anne Lauscher, Goran Glavaš
In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models.
1 code implementation • WS 2018 • Anne Lauscher, Goran Glava{\v{s}}, Kai Eckert
Argumentation is arguably one of the central features of scientific language.
no code implementations • WS 2018 • Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto
We analyze the annotated argumentative structures and investigate the relations between argumentation and other rhetorical aspects of scientific writing, such as discourse roles and citation contexts.
no code implementations • EMNLP 2018 • Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto, Kai Eckert
Exponential growth in the number of scientific publications yields the need for effective automatic analysis of rhetorical aspects of scientific writing.
no code implementations • SEMEVAL 2018 • Thorsten Keiper, Zhonghao Lyu, Sara Pooladzadeh, Yuan Xu, Jingyi Zhang, Anne Lauscher, Simone Paolo Ponzetto
Large repositories of scientific literature call for the development of robust methods to extract information from scholarly papers.