Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions.
In this paper, we extend the arc-hybrid system for transition-based parsing with a swap transition that enables reordering of the words and construction of non-projective trees.
Named Entity Recognition for social media data is challenging because of its inherent noisiness.
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.
End-to-end (E2E) models, which take raw text as input and produce the desired output directly, need not depend on token-level labels.
The paper describes experiments on estimating emotion intensity in tweets using a generalized regressor system.
Natural language inference (NLI) is a central problem in language understanding.
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems.
This view suggests that the RNN should only be used to encode linguistic features and that only the final representation should be `merged' with the image features at a later stage.