Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.
On four benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively filter out the noises in retrieval results and significantly outperforms the vanilla kNN-MT model.
LiDAR odometry plays an important role in self-localization and mapping for autonomous navigation, which is usually treated as a scan registration problem.
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record.
We propose a radically different approach that: (i) employs analog memories to maximize the capacity of each memory cell, and (ii) jointly optimizes model compression and physical storage to maximize memory utility.
The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust.
Many recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothesis while completely ignoring the premise.
At the same time, the spectrum extraction results before and after calibration are compared, results show the characteristics of the extracted one-dimensional waveform are more close to an ideal optics system, and the PSF of the corrected object spectrum image estimated by the blind deconvolution method is nearly central symmetry, which indicates that our proposed method can significantly reduce the complexity of spectrum extraction and improve extraction accuracy.
In multi-document summarization, a set of documents to be summarized is assumed to be on the same topic, known as the underlying topic in this paper.
Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.
Despite the success of deep learning on many fronts especially image and speech, its application in text classification often is still not as good as a simple linear SVM on n-gram TF-IDF representation especially for smaller datasets.
In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm.