Search Results for author: Niklas Stoehr

Found 21 papers, 12 papers with code

Team “NoConflict” at CASE 2021 Task 1: Pretraining for Sentence-Level Protest Event Detection

no code implementations ACL (CASE) 2021 Tiancheng Hu, Niklas Stoehr

An ever-increasing amount of text, in the form of social media posts and news articles, gives rise to new challenges and opportunities for the automatic extraction of socio-political events.

Data Augmentation Event Detection +4

Team “DaDeFrNi” at CASE 2021 Task 1: Document and Sentence Classification for Protest Event Detection

no code implementations ACL (CASE) 2021 Francesco Re, Daniel Vegh, Dennis Atzenhofer, Niklas Stoehr

This paper accompanies our top-performing submission to the CASE 2021 shared task, which is hosted at the workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text.

Binary Classification Event Detection +3

Context versus Prior Knowledge in Language Models

no code implementations6 Apr 2024 Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr, Jennifer C. White, Aaron Schein, Ryan Cotterell

To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context.

Localizing Paragraph Memorization in Language Models

1 code implementation28 Mar 2024 Niklas Stoehr, Mitchell Gordon, Chiyuan Zhang, Owen Lewis

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data?

Language Modelling Memorization

Unsupervised Contrast-Consistent Ranking with Language Models

1 code implementation13 Sep 2023 Niklas Stoehr, Pengxiang Cheng, Jing Wang, Daniel Preotiuc-Pietro, Rajarshi Bhowmik

We compare pairwise, pointwise and listwise prompting techniques to elicit a language model's ranking knowledge.

Language Modelling Negation

ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task

no code implementations12 Jul 2023 Giuseppe Russo, Niklas Stoehr, Manoel Horta Ribeiro

Conspiracy Theory Identication task is a new shared task proposed for the first time at the Evalita 2023.

Classification Misinformation

Generalizing Backpropagation for Gradient-Based Interpretability

1 code implementation6 Jul 2023 Kevin Du, Lucas Torroba Hennigen, Niklas Stoehr, Alexander Warstadt, Ryan Cotterell

Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs.

World Models for Math Story Problems

1 code implementation7 Jun 2023 Andreas Opedal, Niklas Stoehr, Abulhair Saparov, Mrinmaya Sachan

In this paper, we consolidate previous work on categorizing and representing math story problems and develop MathWorld, which is a graph-based semantic formalism specific for the domain of math story problems.


Extracting Victim Counts from Text

1 code implementation23 Feb 2023 Mian Zhong, Shehzaad Dhuliawala, Niklas Stoehr

We cast victim count extraction as a question answering (QA) task with a regression or classification objective.

Dependency Parsing Humanitarian +2

The Ordered Matrix Dirichlet for State-Space Models

1 code implementation8 Dec 2022 Niklas Stoehr, Benjamin J. Radford, Ryan Cotterell, Aaron Schein

For discrete data, SSMs commonly do so through a state-to-action emission matrix and a state-to-state transition matrix.

Extended Multilingual Protest News Detection -- Shared Task 1, CASE 2021 and 2022

no code implementations21 Nov 2022 Ali Hürriyetoğlu, Osman Mutlu, Fırat Duruşan, Onur Uca, Alaeddin Selçuk Gürel, Benjamin Radford, Yaoyao Dai, Hansi Hettiarachchi, Niklas Stoehr, Tadashi Nomoto, Milena Slavcheva, Francielle Vargas, Aaqib Javid, Fatih Beyhan, Erdem Yörük

The CASE 2022 extension consists of expanding the test data with more data in previously available languages, namely, English, Hindi, Portuguese, and Spanish, and adding new test data in Mandarin, Turkish, and Urdu for Sub-task 1, document classification.

Document Classification Event Detection +3

The Architectural Bottleneck Principle

no code implementations11 Nov 2022 Tiago Pimentel, Josef Valvoda, Niklas Stoehr, Ryan Cotterell

This shift in perspective leads us to propose a new principle for probing, the architectural bottleneck principle: In order to estimate how much information a given component could extract, a probe should look exactly like the component.

Open-Ended Question Answering

Rethinking the Event Coding Pipeline with Prompt Entailment

1 code implementation11 Oct 2022 Clément Lefebvre, Niklas Stoehr

In this work, we propose PR-ENT, a new event coding approach that is more flexible and resource-efficient, while maintaining competitive accuracy: first, we extend an event description such as "Military injured two civilians'' by a template, e. g. "People were [Z]" and prompt a pre-trained (cloze) language model to fill the slot Z.

Humanitarian Language Modelling +1

An Ordinal Latent Variable Model of Conflict Intensity

1 code implementation8 Oct 2022 Niklas Stoehr, Lucas Torroba Hennigen, Josef Valvoda, Robert West, Ryan Cotterell, Aaron Schein

It is based only on the action category ("what") and disregards the subject ("who") and object ("to whom") of an event, as well as contextual information, like associated casualty count, that should contribute to the perception of an event's "intensity".

Event Extraction

UniMorph 4.0: Universal Morphology

no code implementations LREC 2022 Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieraś, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina J. Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Lane, Mohit Raj, Matt Coler, Jaime Rafael Montoya Samame, Delio Siticonatzi Camaiteri, Benoît Sagot, Esaú Zumaeta Rojas, Didier López Francis, Arturo Oncevay, Juan López Bautista, Gema Celeste Silva Villegas, Lucas Torroba Hennigen, Adam Ek, David Guriel, Peter Dirix, Jean-Philippe Bernardy, Andrey Scherbakov, Aziyana Bayyr-ool, Antonios Anastasopoulos, Roberto Zariquiey, Karina Sheifer, Sofya Ganieva, Hilaria Cruz, Ritván Karahóǧa, Stella Markantonatou, George Pavlidis, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Candy Angulo, Jatayu Baxi, Andrew Krizhanovsky, Natalia Krizhanovskaya, Elizabeth Salesky, Clara Vania, Sardana Ivanova, Jennifer White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan North Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo M. Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Prud'hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya D. McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova

The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.

Morphological Inflection

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

1 code implementation ICLR Workshop GTRL 2021 Cristina Guzman, Daphna Keidar, Tristan Meynier, Andreas Opedal, Niklas Stoehr

We first learn the generative BA parameters in a supervised fashion using a Graph Neural Network (GNN) and a Random Forest Regressor, by minimizing the squared loss between the true generative parameters and the latent variables.

Decoder Disentanglement +1

The CoRisk-Index: A data-mining approach to identify industry-specific risk assessments related to COVID-19 in real-time

1 code implementation27 Mar 2020 Fabian Stephany, Niklas Stoehr, Philipp Darius, Leonie Neuhäuser, Ole Teutloff, Fabian Braesemann

This alternative data set can complement more traditional economic indicators in times of the fast-evolving crisis as it allows for a real-time analysis of risk assessments.

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

1 code implementation12 Oct 2019 Niklas Stoehr, Emine Yilmaz, Marc Brockschmidt, Jan Stuehmer

While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem.

Disentanglement Graph Embedding +2

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