We argue that extrapolation to examples outside the training space will often be easier for models that capture global structures, rather than just maximise their local fit to the training data. We show that this is true for two popular models: the Decomposable Attention Model and word2vec
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP t...
This article reports the results of an experiment addressing extrapolation in function learning, in ...
Representational spaces learned via language modeling are fundamental to Natural Language Processing...
Previous work on probing word representations for linguistic knowledge has focused on interpolation ...
The human ability to generalize beyond interpolation, often called extrapolation or symbol-binding, ...
The ability to identify influential training examples enables us to debug training data and explain ...
Natural Language Inference (NLI) models are known to learn from biases and artefacts within their tr...
We introduce a new approach for exploring how humans learn and represent functional relationships ba...
Natural language inference (NLI) models are susceptible to learning shortcuts, i.e. decision rules t...
Natural language inference (NLI) is a central problem in natural language processing (NLP) of predic...
Despite their wide adoption, the underlying training and memorization dynamics of very large languag...
Inducing sparseness while training neural networks has been shown to yield models with a lower memor...
The digital era floods us with an excessive amount of text data. To make sense of such data automati...
Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BE...
This paper aims to compare different regularization strategies to address a common phenomenon, sever...
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP t...
This article reports the results of an experiment addressing extrapolation in function learning, in ...
Representational spaces learned via language modeling are fundamental to Natural Language Processing...
Previous work on probing word representations for linguistic knowledge has focused on interpolation ...
The human ability to generalize beyond interpolation, often called extrapolation or symbol-binding, ...
The ability to identify influential training examples enables us to debug training data and explain ...
Natural Language Inference (NLI) models are known to learn from biases and artefacts within their tr...
We introduce a new approach for exploring how humans learn and represent functional relationships ba...
Natural language inference (NLI) models are susceptible to learning shortcuts, i.e. decision rules t...
Natural language inference (NLI) is a central problem in natural language processing (NLP) of predic...
Despite their wide adoption, the underlying training and memorization dynamics of very large languag...
Inducing sparseness while training neural networks has been shown to yield models with a lower memor...
The digital era floods us with an excessive amount of text data. To make sense of such data automati...
Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BE...
This paper aims to compare different regularization strategies to address a common phenomenon, sever...
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP t...
This article reports the results of an experiment addressing extrapolation in function learning, in ...
Representational spaces learned via language modeling are fundamental to Natural Language Processing...
DOI
Add to ORKG