Tasks
Related Papers
Task-based evaluation for machine translation
AbstractIn an effort to reduce the subjectivity, cost, and complexity of evaluation methods for machine translation (MT) and other language technologies, task-based assessment is examined as an alternative to metrics-based …...
An Interaction-Centric Dataset for Learning Automation Rules in Smart Homes
AbstractThe term smart home refers to a living environment that by its connected sensors and actuators is capable of providing intelligent and contextualised support to its user. This may result …...
Deep Learning in Semantic Kernel Spaces
AbstractKernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks. Expressive kernels, such as Tree Kernels, achieve excellent performance in NLP. On …...
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
AbstractWord embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different …...
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference
AbstractThe state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We aim to reduce the inference …...
Are Pretrained Convolutions Better than Pretrained Transformers?
AbstractIn the era of pre-trained language models, Transformers are the de facto choice of model architectures. While recent research has shown promise in entirely convolutional, or CNN, architectures, they have …...
EBERT: Efficient BERT Inference with Dynamic Structured Pruning
Pruning has been demonstrated as an effective way of reducing computational complexity for deep networks, especially CNNs for computer vision tasks. In this paper, we investigate the opportunity to accelerate …...
Studying the Evolution of Scientific Topics and their Relationships
We propose a study of the development of scientific topics through time, as well as the relations between them within the scientific field of computational linguistics and across subfields. We …...
ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence
AbstractAnalyzing conflicts and political violence around the world is a persistent challenge in the political science and policy communities due in large part to the vast volumes of specialized text …...
Dataset of Student Solutions to Algorithm and Data Structure Programming Assignments
AbstractWe present a dataset containing source code solutions to algorithmic programming exercises solved by hundreds of Bachelor-level students at the University of Hamburg. These solutions were collected during the winter …...
Re-train or Train from Scratch? Comparing Pre-training Strategies of BERT in the Medical Domain
AbstractBERT models used in specialized domains all seem to be the result of a simple strategy: initializing with the original BERT and then resuming pre-training on a specialized corpus. This …...
Unified Demonstration Retriever for In-Context Learning
AbstractIn-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been …...