Qa dataset explosion: A taxonomy of nlp resources for question answering and reading comprehension
Alongside huge volumes of research on deep learning models in NLP in the recent years,
there has been much work on benchmark datasets needed to track modeling progress …
there has been much work on benchmark datasets needed to track modeling progress …
Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models
Existing neural information retrieval (IR) models have often been studied in homogeneous
and narrow settings, which has considerably limited insights into their out-of-distribution …
and narrow settings, which has considerably limited insights into their out-of-distribution …
Zero-shot neural passage retrieval via domain-targeted synthetic question generation
A major obstacle to the wide-spread adoption of neural retrieval models is that they require
large supervised training sets to surpass traditional term-based techniques, which are …
large supervised training sets to surpass traditional term-based techniques, which are …
The curse of dense low-dimensional information retrieval for large index sizes
N Reimers, I Gurevych - arXiv preprint arXiv:2012.14210, 2020 - arxiv.org
Information Retrieval using dense low-dimensional representations recently became
popular and showed out-performance to traditional sparse-representations like BM25 …
popular and showed out-performance to traditional sparse-representations like BM25 …
Multicqa: Zero-shot transfer of self-supervised text matching models on a massive scale
We study the zero-shot transfer capabilities of text matching models on a massive scale, by
self-supervised training on 140 source domains from community question answering forums …
self-supervised training on 140 source domains from community question answering forums …
Learning to Reuse Distractors to Support Multiple-Choice Question Generation in Education
Multiple-choice questions (MCQs) are widely used in digital learning systems, as they allow
for automating the assessment process. However, owing to the increased digital literacy of …
for automating the assessment process. However, owing to the increased digital literacy of …
Neural retrieval for question answering with cross-attention supervised data augmentation
Neural models that independently project questions and answers into a shared embedding
space allow for efficient continuous space retrieval from large corpora. Independently …
space allow for efficient continuous space retrieval from large corpora. Independently …
Multimodal large language models for inclusive collaboration learning tasks
A Lewis - Proceedings of the 2022 Conference of the North …, 2022 - aclanthology.org
This PhD project leverages advancements in multimodal large language models to build an
inclusive collaboration feedback loop, in order to facilitate the automated detection …
inclusive collaboration feedback loop, in order to facilitate the automated detection …
A systematic evaluation of transfer learning and pseudo-labeling with BERT-based ranking models
Due to high annotation costs making the best use of existing human-created training data is
an important research direction. We, therefore, carry out a systematic evaluation of …
an important research direction. We, therefore, carry out a systematic evaluation of …
How to quantify the degree of explainability: experiments and practical implications
Explainable AI was born as a pathway to allow humans to explore and understand the inner
working of complex systems. Though, establishing what is an explanation and objectively …
working of complex systems. Though, establishing what is an explanation and objectively …