Much previous work in artificial intelligence has neglected representing time in all its complexity. In particular, it has neglected continuous change and the indeterminacy of the future. To rectify this, I have developed a first-order temporal logic, in which it is possible to name and prove things about facts, events, plans, and world histories. In particular, the logic provides analyses of causality, continuous change in quantities, the persistence of facts (the frame problem), and the relationship between tasks and actions. It may be possible to implement a temporal-inference machine based on this logic, which keeps track of several “maps” of a time line, one per possible history.

A Temporal Logic for Reasoning about Processes and Plans.

This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. The task was also opened up to additional test suites to probe specific aspects of translation.

/pdf/findings-of-the-2019-conference-on-machine-translation-wmt19-4hs5zeff36.pdf

Findings of the 2019 Conference on Machine Translation (WMT19)

Similarity has always been a key aspect in computer science and statistics. Any time two element vectors are compared, many different similarity approaches can be used, depending on the final goal of the comparison (Euclidean distance, Pearson correlation coefficient, Spearman's rank correlation coefficient, and others). But if the comparison has to be applied to more complex data samples, with features having different dimensionality and types which might need compression before processing, these measures would be unsuitable. In these cases, a siamese neural network may be the best choice: it consists of two identical artificial neural networks each capable of learning the hidden representation of an input vector. The two neural networks are both feedforward perceptrons, and employ error back-propagation during training; they work parallelly in tandem and compare their outputs at the end, usually through a cosine distance. The output generated by a siamese neural network execution can be considered the semantic similarity between the projected representation of the two input vectors. In this overview we first describe the siamese neural network architecture, and then we outline its main applications in a number of computational fields since its appearance in 1994. Additionally, we list the programming languages, software packages, tutorials, and guides that can be practically used by readers to implement this powerful machine learning model.

Siamese Neural Networks: An Overview.

Advances in neural information processing systems 3

Sentiment analysis (SA), also called Opinion Mining (OM) is the task of extracting and analyzing people’s opinions, sentiments, attitudes, perceptions, etc., toward different entities such as topics, products, and services. The fast evolution of Internet-based applications like websites, social networks, and blogs, leads people to generate enormous heaps of opinions and reviews about products, services, and day-to-day activities. Sentiment analysis poses as a powerful tool for businesses, governments, and researchers to extract and analyze public mood and views, gain business insight, and make better decisions. This paper presents a complete study of sentiment analysis approaches, challenges, and trends, to give researchers a global survey on sentiment analysis and its related fields. The paper presents the applications of sentiment analysis and describes the generic process of this task. Then, it reviews, compares, and investigates the used approaches to have an exhaustive view of their advantages and drawbacks. The challenges of sentiment analysis are discussed next to clarify future directions.

A comprehensive survey on sentiment analysis: Approaches, challenges and trends

Code-mixing is the phenomenon of mixing the vocabulary and syntax of multiple languages in the same sentence. It is an increasingly common occurrence in today’s multilingual society and poses a big challenge when encountered in different downstream tasks. In this paper, we present a hybrid architecture for the task of Sentiment Analysis of English-Hindi code-mixed data. Our method consists of three components, each seeking to alleviate different issues. We first generate subword level representations for the sentences using a CNN architecture. The generated representations are used as inputs to a Dual Encoder Network which consists of two different BiLSTMs - the Collective and Specific Encoder. The Collective Encoder captures the overall sentiment of the sentence, while the Specific Encoder utilizes an attention mechanism in order to focus on individual sentiment-bearing sub-words. This, combined with a Feature Network consisting of orthographic features and specially trained word embeddings, achieves state-of-the-art results - 83.54% accuracy and 0.827 F1 score - on a benchmark dataset.

/pdf/de-mixing-sentiment-from-code-mixed-text-48vmmqt25n.pdf

De-Mixing Sentiment from Code-Mixed Text

We introduce five new natural language inference (NLI) datasets focused on temporal reasoning. We recast four existing datasets annotated for event duration—how long an event lasts—and event ordering—how events are temporally arranged—into more than one million NLI examples. We use these datasets to investigate how well neural models trained on a popular NLI corpus capture these forms of temporal reasoning.

/pdf/temporal-reasoning-in-natural-language-inference-3ar276ckjs.pdf

Temporal Reasoning in Natural Language Inference.

Online media outlets, in a bid to expand their reach and subsequently increase revenue through ad monetisation, have begun adopting clickbait techniques to lure readers to click on articles. The article fails to fulfill the promise made by the headline. Traditional methods for clickbait detection have relied heavily on feature engineering which, in turn, is dependent on the dataset it is built for. The application of neural networks for this task has only been explored partially. We propose a novel approach considering all information found in a social media post. We train a bidirectional LSTM with an attention mechanism to learn the extent to which a word contributes to the post's clickbait score in a differential manner. We also employ a Siamese net to capture the similarity between source and target information. Information gleaned from images has not been considered in previous approaches. We learn image embeddings from large amounts of data using Convolutional Neural Networks to add another layer of complexity to our model. Finally, we concatenate the outputs from the three separate components, serving it as input to a fully connected layer. We conduct experiments over a test corpus of 19538 social media posts, attaining an F1 score of 65.37% on the dataset bettering the previous state-of-the-art, as well as other proposed approaches, feature engineering or otherwise.

Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks

In an age where people are becoming increasing likely to trust information found through online media, journalists have begun employing techniques to lure readers to articles by using catchy headlines, called clickbait. These headlines entice the user into clicking through the article whilst not providing information relevant to the headline itself. Previous methods of detecting clickbait have explored techniques heavily dependent on feature engineering, with little experimentation having been tried with neural network architectures. We introduce a novel model combining recurrent neural networks, attention layers and image embeddings. Our model uses a combination of distributed word embeddings derived from unannotated corpora, character level embeddings calculated through Convolutional Neural Networks. These representations are passed through a bidirectional LSTM with an attention layer. The image embeddings are also learnt from large data using CNNs. Experimental results show that our model achieves an F1 score of 65.37% beating the previous benchmark of 55.21%.

Yash Kumar Lal

Papers

De-Mixing Sentiment from Code-Mixed Text

Temporal Reasoning in Natural Language Inference.

Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks

Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks

A Neural Clickbait Detection Engine.