OpenKiwi
We introduce OpenKiwi, a Pytorch-based open source framework for translation quality estimation. OpenKiwi supports training and testing of word-level and sentence-level quality estimation systems, implementing the winning systems of the WMT 2015-18 quality estimation campaigns. We benchmark OpenKiwi on two datasets from WMT 2018 (English-German SMT and NMT), yielding state-of-the-art performance on the word-level tasks and near state-of-the-art in the sentence-level tasks. …

K‑Means Modified Inter and Intra Clustering (KM-I2C)
Big data has become popular for processing, storing and managing massive volumes of data. The clustering of datasets has become a challenging issue in the field of big data analytics. The K-means algorithm is best suited for finding similarities between entities based on distance measures with small datasets. Existing clustering algorithms require scalable solutions to manage large datasets. This study presents two approaches to the clustering of large datasets using MapReduce. The first approach, K-Means Hadoop MapReduce (KM-HMR), focuses on the MapReduce implementation of standard K-means. The second approach enhances the quality of clusters to produce clusters with maximum intra-cluster and minimum inter-cluster distances for large datasets. The results of the proposed approaches show significant improvements in the efficiency of clustering in terms of execution times. Experiments conducted on standard K-means and proposed solutions show that the KM-I2C approach is both effective and efficient. …

Lead-like Recognizer (LeadR)
A competitive baseline in sentence-level extractive summarization of news articles is the Lead-3 heuristic, where only the first 3 sentences are extracted. The success of this method is due to the tendency for writers to implement progressive elaboration in their work by writing the most important content at the beginning. In this paper, we introduce the Lead-like Recognizer (LeadR) to show how the Lead heuristic can be extended to summarize multi-section documents where it would not usually work well. This is done by introducing a neural model which produces a probability distribution over positions for sentences, so that we can locate sentences with introduction-like qualities. To evaluate the performance of our model, we use the task of summarizing multi-section documents. LeadR outperforms several baselines on this task, including a simple extension of the Lead heuristic designed for the task. Our work suggests that predicted position is a strong feature to use when extracting summaries. …

Hierarchical Routing Mixture of Experts (HRME)
In regression tasks the distribution of the data is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal-distributed data, and strong local models are needed to make good predictions. Addressing these problems, we propose a binary tree-structured hierarchical routing mixture of experts (HRME) model that has classifiers as non-leaf node experts and simple regression models as leaf node experts. The classifier nodes jointly soft-partition the input-output space based on the natural separateness of multimodal data. This enables simple leaf experts to be effective for prediction. Further, we develop a probabilistic framework for the HRME model, and propose a recursive Expectation-Maximization (EM) based algorithm to learn both the tree structure and the expert models. Experiments on a collection of regression tasks validate the effectiveness of our method compared to a variety of other regression models. …