Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

There are 15 Chapters to display the Global Artificial Intelligence in Platform as a Service (PaaS) Market Chapter 1, Overview to describe Definition, Specifications and Classification of Global Artificial Intelligence in Platform as a Service (PaaS) market, Applications [SME & Large Enterprises], Market Segment by Types, Machine Learning Platform, Natural Language Processing Service, Visual Analysis Service, Language Processing Service & Data Insight Service; Chapter 2, objective of the study.

A digitally native company that helps organizations reinvent themselves to create a way forward and unleash their potential, Globant is the place where innovation, design, and engineering meet scale. Globant is a disruptor in the professional services arena and we leverage the latest technologies and methodologies in the digital and cognitive space to help organizations transform in every aspect. A pure-play in the digital and cognitive fields, Globant has a global presence with delivery centers in North America, Latin America, Europe, and Asia through which we offer a deep knowledge of the latest trends and technologies. With over 17,250 professionals present in 18 countries working for companies like Google, Rockwell Automation, Electronic Arts, and Santander, among others, we are featured as a business case study at Harvard, MIT, and Stanford apart from being a member of the Cybersecurity Tech Accord (2019).

With the growth of social medias, such as Twitter, plenty of user-generated data emerge daily. The short texts published on Twitter -- the tweets -- have earned significant attention as a rich source of information to guide many decision-making processes. However, their inherent characteristics, such as the informal, and noisy linguistic style, remain challenging to many natural language processing (NLP) tasks, including sentiment analysis. Sentiment classification is tackled mainly by machine learning-based classifiers. The literature has adopted word representations from distinct natures to transform tweets to vector-based inputs to feed sentiment classifiers. The representations come from simple count-based methods, such as bag-of-words, to more sophisticated ones, such as BERTweet, built upon the trendy BERT architecture. Nevertheless, most studies mainly focus on evaluating those models using only a small number of datasets. Despite the progress made in recent years in language modelling, there is still a gap regarding a robust evaluation of induced embeddings applied to sentiment analysis on tweets. Furthermore, while fine-tuning the model from downstream tasks is prominent nowadays, less attention has been given to adjustments based on the specific linguistic style of the data. In this context, this study fulfils an assessment of existing language models in distinguishing the sentiment expressed in tweets by using a rich collection of 22 datasets from distinct domains and five classification algorithms. The evaluation includes static and contextualized representations. Contexts are assembled from Transformer-based autoencoder models that are also fine-tuned based on the masked language model task, using a plethora of strategies.

With the advent of Artificial Intelligence (AI)-empowered communications, industry, academia, and standardization organizations are progressing on the definition of mechanisms and procedures to address the increasing complexity of future 5G and beyond communications. In this context, the International Telecommunication Union (ITU) organized the first AI for 5G Challenge to bring industry and academia together to introduce and solve representative problems related to the application of Machine Learning (ML) to networks. In this paper, we present the results gathered from Problem Statement~13 (PS-013), organized by Universitat Pompeu Fabra (UPF), which primary goal was predicting the performance of next-generation Wireless Local Area Networks (WLANs) applying Channel Bonding (CB) techniques. In particular, we overview the ML models proposed by participants (including Artificial Neural Networks, Graph Neural Networks, Random Forest regression, and gradient boosting) and analyze their performance on an open dataset generated using the IEEE 802.11ax-oriented Komondor network simulator. The accuracy achieved by the proposed methods demonstrates the suitability of ML for predicting the performance of WLANs. Moreover, we discuss the importance of abstracting WLAN interactions to achieve better results, and we argue that there is certainly room for improvement in throughput prediction through ML.

Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all the previously mentioned drawbacks). The entropic out-of-distribution detection solution comprises the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a SoftMax loss drop-in replacement because swapping the SoftMax loss with the IsoMax loss requires no changes in the model's architecture or training procedures/hyperparameters. In this paper, we propose to perform what we call an isometrization of the distances used in the IsoMax loss. Additionally, we propose to replace the entropic score with the minimum distance score. Our experiments showed that these simple modifications increase out-of-distribution detection performance while keeping the solution seamless.

Examining a 20th-century Scandinavian legal theoretical tradition, we can extract an ontological naturalistic, a logical empiristic, and a modern idealistic rationale. We introduce the mathematical syntactic figure present in the `logical empiricism' in a contemporary mathematical logic. A new formal framework for describing explicit purchase statutes (Sweden) is gradually developed and subsequently proposed. This new framework is based on a many-sorted first-order logic (MFOL) approach, where the semantics are grounded in concrete `physical' objects and situations with a legal relevance. Specifically, we present a concrete formal syntactic translation of one of the central statutes of Swedish legislation for the purchase of immovable property. Additionally, we discuss the potential implications that a subsequent development of such formalisations would have for constructing artificial agents (e.g., software) that can be used as `co-creative' legal assistance for solving highly complex legal issues concerning the transfer of property, among others.

Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication. While various task settings have been proposed in existing literature, they mostly focus on creating common ground under static context and ignore the aspect of maintaining them overtime under dynamic context. In this work, we propose a novel task setting to study the ability of both creating and maintaining common ground in dynamic environments. Based on our minimal task formulation, we collected a large-scale dataset of 5,617 dialogues to enable fine-grained evaluation and analysis of various dialogue systems. Through our dataset analyses, we highlight novel challenges introduced in our setting, such as the usage of complex spatio-temporal expressions to create and maintain common ground. Finally, we conduct extensive experiments to assess the capabilities of our baseline dialogue system and discuss future prospects of our research.

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called \textit{graphon autoencoder} to build an interpretable and scalable graph generative model. This framework treats observed graphs as induced graphons in functional space and derives their latent representations by an encoder that aggregates Chebshev graphon filters. A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs). We develop an efficient learning algorithm to learn the encoder and the decoder, minimizing the Wasserstein distance between the model and data distributions. This algorithm takes the KL divergence of the graph distributions conditioned on different graphons as the underlying distance and leads to a reward-augmented maximum likelihood estimation. The graphon autoencoder provides a new paradigm to represent and generate graphs, which has good generalizability and transferability.

Welcome to our May 2021 monthly digest where you can catch up with any AIhub stories you may have missed, get the low-down on recent events, and much more. In this edition we look at research into the oceans, AI and philosophy of mind, and highlight some interesting podcasts. This month we focused on the UN sustainable development goal (SDG) of life below water. We interviewed Nayat Sánchez-Pi, director of Inria Chile and leader of the OcéanIA project. The project team is developing new artificial intelligence and mathematical modelling tools to contribute to the understanding of the oceans and their role in regulating and sustaining the biosphere, and tackling climate change.