no code implementations • 6 Jan 2025 • Aaron Gluck, Katharina von der Wense, Maria Pacheco
Automated definition generation systems have been proposed to support vocabulary expansion for language learners.
1 code implementation • 23 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.
no code implementations • 13 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.
1 code implementation • 13 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.
1 code implementation • 1 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
1 code implementation • 6 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.
no code implementations • 10 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.
no code implementations • 24 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?
no code implementations • 3 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.
no code implementations • 30 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.
no code implementations • 21 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.
1 code implementation • 31 Jan 2024 • Sagi Shaier, Kevin Bennett, Lawrence E Hunter, Katharina von der Wense
(RQ2) Do models' absolute scores differ between the two approaches?
no code implementations • 31 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.
no code implementations • 16 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.
1 code implementation • 16 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.