In the context of structure-to-structure transformation tasks, learning
...
Human linguistic capacity is often characterized by compositionality and...
Machine translation has seen rapid progress with the advent of
Transform...
What explains the dramatic progress from 20th-century to 21st-century AI...
Current language models can generate high-quality text. Are they simply
...
A framework and method are proposed for the study of constituent composi...
We present Harmonic Memory Networks (HMem), a neural architecture for
kn...
Abstractive summarization, the task of generating a concise summary of i...
A longstanding question in cognitive science concerns the learning mecha...
Neuro-symbolic representations have proved effective in learning structu...
How do learners acquire languages from the limited data available to the...
We introduce HUBERT which combines the structured-representational power...
Neural networks (NNs) are able to perform tasks that rely on composition...
We incorporate Tensor-Product Representations within the Transformer in ...
Generating formal-language represented by relational tuples, such as Lis...
Recurrent neural networks (RNNs) can learn continuous vector representat...
Neural models of Knowledge Base data have typically employed composition...
idely used recurrent units, including Long-short Term Memory (LSTM) and ...
Widely used recurrent units, including Long-short Term Memory (LSTM) and...
Distinguishing between core and non-core dependents (i.e., arguments and...
We present a formal language with expressions denoting general symbol
st...
Gradient Symbolic Computation is proposed as a means of solving discrete...
Deep learning (DL) has in recent years been widely used in natural langu...
We present a new approach to the design of deep networks for natural lan...
We present a new tensor product generation network (TPGN) that generates...
We introduce an architecture, the Tensor Product Recurrent Network (TPRN...
In this paper we present the initial development of a general theory for...
Question answering tasks have shown remarkable progress with distributed...