However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models.
Representation learning tries to learn a common low dimensional space for the representations of users and items.
The performance of meta-learning approaches for few-shot learning generally depends on three aspects: features suitable for comparison, the classifier ( base learner ) suitable for low-data scenarios, and valuable information from the samples to classify.
Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge.
For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning.
Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow).
Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency.
Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process.
We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links.
Ranked #2 on Link Prediction on FB122
To solve this problem, many methods have been studied, which can be generally categorized into two types, i. e., representation learning-based CF methods and matching function learning-based CF methods.
As far as we know, we are the first to propose a neural model for unsupervised CWS and achieve competitive performance to the state-of-the-art statistical models on four different datasets from SIGHAN 2005 bakeoff.
Recursive Neural Network (RecNN), a type of models which compose words or phrases recursively over syntactic tree structures, has been proven to have superior ability to obtain sentence representation for a variety of NLP tasks.
Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years.
This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units.
However, if we consider segmenting a given sentence, the most intuitive idea is to predict whether to segment for each gap between two consecutive characters, which in comparison makes previous approaches seem too complex.
In the age of information exploding, multi-document summarization is attracting particular attention for the ability to help people get the main ideas in a short time.