Search Results for author: Katharina von der Wense

Found 15 papers, 6 papers with code

CLIX: Cross-Lingual Explanations of Idiomatic Expressions

no code implementations6 Jan 2025 Aaron Gluck, Katharina von der Wense, Maria Pacheco

Automated definition generation systems have been proposed to support vocabulary expansion for language learners.

Measuring Contextual Informativeness in Child-Directed Text

1 code implementation23 Dec 2024 Maria Valentini, Téa Wright, Ali Marashian, Jennifer Weber, Eliana Colunga, Katharina von der Wense

To address an important gap in creating children's stories for vocabulary enrichment, we investigate the automatic evaluation of how well stories convey the semantics of target vocabulary words, a task with substantial implications for generating educational content.

Informativeness Language Modeling +2

MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset

no code implementations13 Dec 2024 Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence E Hunter, Katharina von der Wense

They: 1) do not cover the educational domain; 2) typically focus on low-complexity, generic knowledge or broad domains, which do not adequately assess the models' knowledge in specific subjects; and 3) often rely on templates that can bias model predictions.

Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA

1 code implementation13 Dec 2024 George Arthur Baker, Ankush Raut, Sagi Shaier, Lawrence E Hunter, Katharina von der Wense

Here, we demonstrate the effects of the "lost in the middle" problem in the multi-hop question answering setting -- in which multiple reasoning "hops" over disconnected documents are required -- and show that performance degrades not only with respect to the distance of information from the edges of the context, but also between pieces of information.

Multi-hop Question Answering Question Answering

From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation

1 code implementation1 Dec 2024 Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, Katharina von der Wense

Many of the world's languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only available parallel data are small amounts of religious texts.

Domain Adaptation Low Resource Neural Machine Translation +3

Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models

1 code implementation6 Nov 2024 Minh Duc Bui, Katharina von der Wense, Anne Lauscher

To investigate this, we create the first multimodal and multilingual parallel hate speech dataset, annotated by a multicultural set of annotators, called Multi3Hate.

Hate Speech Detection Navigate

More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing

no code implementations10 Oct 2024 Sagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence E Hunter, Matt Jones

In this paper we propose Conditionally Overlapping Mixture of ExperTs (COMET), a general deep learning method that addresses these challenges by inducing a modular, sparse architecture with an exponential number of overlapping experts.

Image Classification Language Modeling +2

It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension

no code implementations24 Jun 2024 Sagi Shaier, Lawrence E Hunter, Katharina von der Wense

Additionally, given recent advancements in input emphasis, we ask a second research question: 2) Does emphasizing either the question, the context, or both enhance performance?

Reading Comprehension

The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification

no code implementations3 May 2024 Minh Duc Bui, Katharina von der Wense

Current natural language processing (NLP) research tends to focus on only one or, less frequently, two dimensions - e. g., performance, privacy, fairness, or efficiency - at a time, which may lead to suboptimal conclusions and often overlooking the broader goal of achieving trustworthy NLP.

Fairness text-classification +1

Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget

no code implementations30 Apr 2024 Minh Duc Bui, Fabian David Schmidt, Goran Glavaš, Katharina von der Wense

We further find that KD yields larger gains over pretraining from scratch when the data must be repeated under the fixed computation budget.

Knowledge Distillation Language Modeling +2

TAMS: Translation-Assisted Morphological Segmentation

no code implementations21 Mar 2024 Enora Rice, Ali Marashian, Luke Gessler, Alexis Palmer, Katharina von der Wense

Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes.

Segmentation Translation

Desiderata for the Context Use of Question Answering Systems

no code implementations31 Jan 2024 Sagi Shaier, Lawrence E Hunter, Katharina von der Wense

Prior work has uncovered a set of common problems in state-of-the-art context-based question answering (QA) systems: a lack of attention to the context when the latter conflicts with a model's parametric knowledge, little robustness to noise, and a lack of consistency with their answers.

Question Answering

Who Are All The Stochastic Parrots Imitating? They Should Tell Us!

no code implementations16 Oct 2023 Sagi Shaier, Lawrence E. Hunter, Katharina von der Wense

In this opinion piece, we argue that LMs in their current state will never be fully trustworthy in critical settings and suggest a possible novel strategy to handle this issue: by building LMs such that can cite their sources - i. e., point a user to the parts of their training data that back up their outputs.

Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems

1 code implementation16 Oct 2023 Sagi Shaier, Kevin Bennett, Lawrence Hunter, Katharina von der Wense

State-of-the-art question answering (QA) models exhibit a variety of social biases (e. g., with respect to sex or race), generally explained by similar issues in their training data.

Fairness Question Answering

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