Related papers: Neural Multi-Source Morphological Reinflection
This paper presents a morphological lexicon for English that handles more than 317000 inflected forms derived from over 90000 stems. The lexicon is available in two formats. The first can be used by an implementation of a two-level…
While most neural generative models generate outputs in a single pass, the human creative process is usually one of iterative building and refinement. Recent work has proposed models of editing processes, but these mostly focus on editing…
Neural encoding is a field in neuroscience that focuses on characterizing how information from stimuli is encoded in the spiking activity of neurons. When more than one stimulus is present, a theory known as multiplexing posits that neurons…
We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model. A…
Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. Prior work has either hard-coded object-centric features,…
In this short paper, we explore a new way to refactor a simple but tricky-to-parallelize tree-traversal algorithm to harness multicore parallelism. Crucially, the refactoring draws from some classic techniques from programming-languages…
In this paper, we present our method for neural face reenactment, called HyperReenact, that aims to generate realistic talking head images of a source identity, driven by a target facial pose. Existing state-of-the-art face reenactment…
A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual…
This paper proposes a learning model, based on rank-fusion graphs, for general applicability in multimodal prediction tasks, such as multimodal regression and image classification. Rank-fusion graphs encode information from multiple…
In this paper, the problem of recovery of morphological information lost in abbreviated forms is addressed with a focus on highly inflected languages. Evidence is presented that the correct inflected form of an expanded abbreviation can in…
Visual encoding and decoding models act as gateways to understanding the neural mechanisms underlying human visual perception. Typically, visual encoding models that predict brain activity from stimuli and decoding models that reproduce…
Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making…
This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network…
Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of…
Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often…
Whether neural networks can serve as cognitive models of morphological learning remains an open question. Recent work has shown that encoder-decoder models can acquire irregular patterns, but evidence that they generalize these patterns…
Learning-based methods for routing have gained significant attention in recent years, both in single-objective and multi-objective contexts. Yet, existing methods are unsuitable for routing on multigraphs, which feature multiple edges with…
We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of…
Reinforcement learning (RL) is a foundation of learning in biological systems and provides a framework to address numerous challenges with real-world artificial intelligence applications. Efficient implementations of RL techniques could…
Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge between different…