Lasuie: Unifying information extraction with latent adaptive structure-aware generative language model
Universally modeling all typical information extraction tasks (UIE) with one generative
language model (GLM) has revealed great potential by the latest study, where various IE …
language model (GLM) has revealed great potential by the latest study, where various IE …
Pop music transformer: Beat-based modeling and generation of expressive pop piano compositions
A great number of deep learning based models have been recently proposed for automatic
music composition. Among these models, the Transformer stands out as a prominent …
music composition. Among these models, the Transformer stands out as a prominent …
Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation
Code representation learning, which aims to encode the semantics of source code into
distributed vectors, plays an important role in recent deep-learning-based models for code …
distributed vectors, plays an important role in recent deep-learning-based models for code …
Code prediction by feeding trees to transformers
Code prediction, more specifically autocomplete, has become an essential feature in
modern IDEs. Autocomplete is more effective when the desired next token is at (or close to) …
modern IDEs. Autocomplete is more effective when the desired next token is at (or close to) …
Multi-hop attention graph neural network
Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art
performance on many graph representation learning tasks. Currently, at every layer …
performance on many graph representation learning tasks. Currently, at every layer …
Sentibert: A transferable transformer-based architecture for compositional sentiment semantics
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment
semantics. The model incorporates contextualized representation with binary constituency …
semantics. The model incorporates contextualized representation with binary constituency …
Image captioning through image transformer
Automatic captioning of images is a task that combines the challenges of image analysis
and text generation. One important aspect of captioning is the notion of attention: how to …
and text generation. One important aspect of captioning is the notion of attention: how to …
Integrating tree path in transformer for code representation
Learning distributed representation of source code requires modelling its syntax and
semantics. Recent state-of-the-art models leverage highly structured source code …
semantics. Recent state-of-the-art models leverage highly structured source code …
Transformer grammars: Augmenting transformer language models with syntactic inductive biases at scale
Abstract We introduce Transformer Grammars (TGs), a novel class of Transformer language
models that combine (i) the expressive power, scalability, and strong performance of …
models that combine (i) the expressive power, scalability, and strong performance of …
HiCLIP: Contrastive language-image pretraining with hierarchy-aware attention
The success of large-scale contrastive vision-language pretraining (CLIP) has benefited
both visual recognition and multimodal content understanding. The concise design brings …
both visual recognition and multimodal content understanding. The concise design brings …