While traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency, they struggle to reflect adequacy. Model-based MT metrics trained on segment-level human judgments have emerged as an attractive replacement due to strong correlation results. These models, however, require potentially expensive re-training for new domains and languages. Furthermore, their decisions are inherently non-transparent and appear to reflect unwelcome biases. We explore the simple type-based classifier metric, MacroF1, and study its applicability to MT evaluation. We find that MacroF1 is competitive on direct assessment, and outperforms others in indicating downstream cross-lingual information retrieval task performance. Further, we show that MacroF1 can be used to effectively compare supervised and unsupervised neural machine translation, and reveal significant qualitative differences in the methods' outputs.

Machine learning algorithms have been very successful to solve problems in the natural language processing (NLP) domain for many years, especially supervised and unsupervised methods. However, this is not the case with reinforcement learning (RL), which is somewhat surprising since in other domains, reinforcement learning methods have experienced an increased level of success with some impressive results, for instance in board games such as AlphaGo Zero [106]. Yet, deep reinforcement learning for natural language processing is still in its infancy when compared to supervised learning [65]. Thus, the goal of this article is to provide a review of applications of reinforcement learning to NLP and we present an analysis of the underlying structure of the problems that make them viable to be treated entirely or partially as RL problems intended as an aid to newcomers to the field. We also analyze some existing research gaps and provide a list of promising research directions in which natural language systems might benefit from reinforcement learning algorithms.

The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion. The proposed approach, called Boltzmann Tuning of Generative Models (BTGM), applies to a wide range of applications. It covers conditional generative modelling as a particular case, and offers an affordable alternative to rejection sampling. The contribution of the paper is twofold. Firstly, the objective is formalized and tackled as a well-posed optimization problem; a practical methodology is proposed to choose among the candidate criteria representing the same goal, the one best suited to efficiently learn a tuned generative model. Secondly, the merits of the approach are demonstrated on a real-world application, in the context of robust design for energy policies, showing the ability of BTGM to sample the extreme regions of the considered criteria.

In this paper, we introduce UnifiedM2, a general-purpose misinformation model that jointly models multiple domains of misinformation with a single, unified setup. The model is trained to handle four tasks: detecting news bias, clickbait, fake news, and verifying rumors. By grouping these tasks together, UnifiedM2learns a richer representation of misinformation, which leads to state-of-the-art or comparable performance across all tasks. Furthermore, we demonstrate that UnifiedM2's learned representation is helpful for few-shot learning of unseen misinformation tasks/datasets and model's generalizability to unseen events.

In February, 2011, an Israeli computer scientist named Noam Slonim proposed building a machine that would be better than people at something that seems inextricably human: arguing about politics. Slonim, who had done his doctoral work on machine learning, works at an I.B.M. Research facility in Tel Aviv, and he had watched with pride a few days before as the company's natural-language-processing machine, Watson, won "Jeopardy!" Afterward, I.B.M. sent an e-mail to thousands of researchers across its global network of labs, soliciting ideas for a "grand challenge" to follow the "Jeopardy!" It occurred to Slonim that they might try to build a machine that could defeat a champion debater. He made a single-slide presentation, and then a somewhat more elaborate one, and then a more elaborate one still, and, after many rounds competing against many other I.B.M. researchers, Slonim won the chance to build his machine, which he called Project Debater.

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the $\ell_{2}$ norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. $\ell_{1}$ norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the $\ell_{1}$ refinement substantially outperforms four state-of-the-art baselines in both supervised and unsupervised settings. It is therefore recommended that this strategy be adopted as a standard for CLWE methods.

It is well known that recurrent neural networks (RNNs) faced limitations in learning long-term dependencies that have been addressed by memory structures in long short-term memory (LSTM) networks. Matrix neural networks feature matrix representation which inherently preserves the spatial structure of data and has the potential to provide better memory structures when compared to canonical neural networks that use vector representation. Neural Turing machines (NTMs) are novel RNNs that implement notion of programmable computers with neural network controllers to feature algorithms that have copying, sorting, and associative recall tasks. In this paper, we study the augmentation of memory capacity with a matrix representation of RNNs and NTMs (MatNTMs). We investigate if matrix representation has a better memory capacity than the vector representations in conventional neural networks. We use a probabilistic model of the memory capacity using Fisher information and investigate how the memory capacity for matrix representation networks are limited under various constraints, and in general, without any constraints. In the case of memory capacity without any constraints, we found that the upper bound on memory capacity to be $N^2$ for an $N\times N$ state matrix. The results from our experiments using synthetic algorithmic tasks show that MatNTMs have a better learning capacity when compared to its counterparts.

This paper models residential consumers' energy-consumption behavior by load patterns and distributions and reveals the relationship between consumers' load patterns and socioeconomic features by machine learning. We analyze the real-world smart meter data and extract load patterns using K-Medoids clustering, which is robust to outliers. We develop an analytical framework with feature selection and deep learning models to estimate the relationship between load patterns and socioeconomic features. Specifically, we use an entropy-based feature selection method to identify the critical socioeconomic characteristics that affect load patterns and benefit our method's interpretability. We further develop a customized deep neural network model to characterize the relationship between consumers' load patterns and selected socioeconomic features. Numerical studies validate our proposed framework using Pecan Street smart meter data and survey. We demonstrate that our framework can capture the relationship between load patterns and socioeconomic information and outperform benchmarks such as regression and single DNN models.

This paper discusses the need of an automated system for detecting print errors and the efficacy of Convolutional Neural Networks in such an application. We recognise the need of a dataset containing print error samples and propose a way to generate one artificially. We discuss the algorithms to generate such data along with the limitaions and advantages of such an apporach. Our final trained network gives a remarkable accuracy of 99.83\% in testing. We further evaluate how such efficiency was achieved and what modifications can be tested to further the results.

Tensor Decomposition Networks(TDNs) prevail for their inherent compact architectures. For providing convenience, we present a toolkit named TedNet that is based on the Pytorch framework, to give more researchers a flexible way to exploit TDNs. TedNet implements 5 kinds of tensor decomposition(i.e., CANDECOMP/PARAFAC(CP), Block-Term Tucker(BT), Tucker-2, Tensor Train(TT) and Tensor Ring(TR)) on traditional deep neural layers, the convolutional layer and the fully-connected layer. By utilizing these basic layers, it is simple to construct a variety of TDNs like TR-ResNet, TT-LSTM, etc. TedNet is available at https://github.com/tnbar/tednet.