• Publications
  • Influence
Latent Multi-Task Architecture Learning
TLDR
This work presents an approach that learns a latent multi-task architecture that jointly addresses (a)--(c) and consistently outperforms previous approaches to learning latent architectures for multi- task problems and achieves up to 15% average error reductions over common approaches to MTL.
Sluice networks: Learning what to share between loosely related tasks
TLDR
Sluice Networks is introduced, a general framework for multi-task learning where trainable parameters control the amount of sharing and it is shown that a) label entropy is predictive of gains in sluice networks, confirming findings for hard parameter sharing and b) while slUice networks easily fit noise, they are robust across domains in practice.
Identifying beneficial task relations for multi-task learning in deep neural networks
TLDR
Light is shed on the specific task relations that can lead to gains from MTL models over single-task setups in deep neural networks for NLP.
Sequence Classification with Human Attention
TLDR
Estimated human attention derived from eye-tracking corpora is used to regularize attention functions in recurrent neural networks and shows substantial improvements across a range of tasks, including sentiment analysis, grammatical error detection, and detection of abusive language.
Weakly Supervised Part-of-speech Tagging Using Eye-tracking Data
TLDR
This work shows that given raw text, a dictionary, and eyetracking data obtained from naive participants reading text, it can be shown that a weakly supervised PoS tagger using a secondorder HMM with maximum entropy emissions is possible.
Bridging the Gaps: Multi Task Learning for Domain Transfer of Hate Speech Detection
TLDR
This paper investigates methods for bridging differences in annotation and data collection of abusive language tweets such as different annotation schemes, labels, or geographic and cultural influences from data sampling, and considers three distinct sets of annotations.
Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs
TLDR
A way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations is devised, which provides insights on the types of transformations that different approaches can model.
Learning attention for historical text normalization by learning to pronounce
TLDR
Interestingly, it is observed that, as previously conjectured, multi-task learning can learn to focus attention during decoding, in ways remarkably similar to recently proposed attention mechanisms, which is an important step toward understanding how MTL works.
Latent Multitask Architecture Learning
TLDR
This work presents an approach that learns a latent multi-task architecture that jointly addresses (a)–(c) and consistently outperforms previous approaches to learning latent architectures for multi- task problems and achieves up to 15% average error reductions over common approaches.
...
1
2
3
...