This paper presents the results and findings of the Financial Narrative Summarisation Shared Task on summarising UK, Greek, and Spanish annual reports. The shared task was organised as part of the 5th Financial Narrative Processing Workshop (FNP 2023). The Financial Narrative summarisation Shared Task (FNS 2023) has been running since 2020 as part of the Financial Narrative Processing (FNP) workshop series [15–20]. The shared task included one main challenge, which is the use of either abstractive or extractive automatic summarisers to summarise long documents in terms of UK, Greek, and Spanish financial annual reports. This shared task is the fourth to target financial documents. The data for the shared task was created and collected from publicly available annual reports published by firms listed on the Stock Exchanges of the UK, Greece, and Spain. A total number of 6 systems from 3 different teams participated in the shared task.

Estimating the Fuel Oil Consumption (FOC) of a vessel is a critical task for the maritime industry, affecting route planning and the overall management of the vessel's operation and maintenance. Consumption is strongly coupled with the operation of the Main Engine (ME), but also with the environmental conditions (i.e., weather, ocean-energy spectrum) and the hydrodynamic features (i.e., resistance, propulsion) of the vessel. Current research shows that a multitude of features collected either from the AIS (Automatic Identification System) or on-board sensors can assist to the continuous prediction of FOC. Even when a FOC estimation model is perfectly trained on a specific vessel, its performance may degrade over time, when new weather conditions apply or when the hydrodynamics of the vessel change over time, due to fouling, aging and negligent maintenance. This work presents an online learning framework that employs a custom encoding-decoding Neural Network scheme and real-time data from various on-board sensors, to appropriately update FOC estimation models. The model is able to adapt to newly acquired data using a temporally-aware batch scheme, that samples from the initial training set using a custom auto-encoder.

Abstract The recent breakthroughs in deep neural architectures across multiple machine learning fields have led to the widespread use of deep neural models. These learners are often applied as black-box models that ignore or insufficiently utilize a wealth of preexisting semantic information. In this study, we focus on the text classification task, investigating methods for augmenting the input to deep neural networks (DNNs) with semantic information. We extract semantics for the words in the preprocessed text from the WordNet semantic graph, in the form of weighted concept terms that form a semantic frequency vector. Concepts are selected via a variety of semantic disambiguation techniques, including a basic, a part-of-speech-based, and a semantic embedding projection method. Additionally, we consider a weight propagation mechanism that exploits semantic relationships in the concept graph and conveys a spreading activation component. We enrich word2vec embeddings with the resulting semantic vector through concatenation or replacement and apply the semantically augmented word embeddings on the classification task via a DNN. Experimental results over established datasets demonstrate that our approach of semantic augmentation in the input space boosts classification performance significantly, with concatenation offering the best performance. We also note additional interesting findings produced by our approach regarding the behavior of term frequency - inverse document frequency normalization on semantic vectors, along with the radical dimensionality reduction potential with negligible performance loss.

JedAI is an open-source toolkit that allows for building and benchmarking thousands of schema-agnostic Entity Resolution (ER) pipelines through a non-learning, blocking-based end-to-end workflow. In this paper, we present its latest release, JedAI3 , which conveys two new end-to-end workflows: one for budgetagnostic ER that is based on similarity joins, and one for budgetaware (i.e., progressive) ER. This version also adds support for pre-trained word or character embeddings and connects JedAI to the Python data analysis ecosystem. Overall, these enhancements provide JedAI with features offered by no other ER tool, especially in the schema- and domain-agnostic context.

Within this work we describe a framework for the collection and summarization of information from the Web in an entity-driven manner. The framework consists of a set of appropriate workflows and the Social Web Observatory platform, which implements those workflows, supporting them through a language analysis pipeline. The pipeline includes text collection/crawling, identification of different entities, clustering of texts into events related to entities, entity-centric sentiment analysis, but also text analytics and visualization functionalities. The latter allow the user to take advantage of the gathered information as actionable knowledge: to understand the dynamics of the public opinion for a given entity over time and across real-world events. We describe the platform and the analysis functionality and evaluate the performance of the system, by allowing human users to score how the system fares in its intended purpose of summarizing entity-centered information from different sources in the Web.

In this work we face the challenge of estimating a ship's main-engine rotational speed from vessel data series, in the context of sea vessel route optimization. To this end, we study the value of different vessel data types as predictors of the engine rotational speed. As a result, we utilize speed data under a time-series view and examine how extracting locally-aware prediction models affects the learning performance. We apply two different approaches: the first utilizes clustering as a pre-processing step to the creation of many local models; the second builds upon splines to predict the target value. Given the above, we show that clustering can improve performance and demonstrate how the number of clusters affects the outcome. We also show that splines perform in a promising manner, but do not clearly outperform other methods. On the other hand, we show that spline regression combined with a Delaunay partitioning offers most competitive results.

This work examines document clustering as a record linkage problem, focusing on named-entities and frequent terms, using several vector and graph-based document representation methods and k-means clustering with different similarity measures. The JedAI Record Linkage toolkit is employed for most of the record linkage pipeline tasks (i.e. preprocessing, scalable feature representation, blocking and clustering) and the OpenCalais platform for entity extraction. The resulting clusters are evaluated with multiple clustering quality metrics. The experiments show very good clustering results and significant speedups in the clustering process, which indicates the suitability of both the record linkage formulation and the JedAI toolkit for improving the scalability for large-scale document clustering tasks.

JedAI is an Entity Resolution toolkit that can be used in three ways: (i) as an open-source library that combines state-of-the-art methods into a plethora of end-to-end workflows, (ii) as a user-friendly desktop application with a wizardlike interface that provides complex, out-of-the-box solutions even to lay users, and (iii) as a workbench for comparing the performance of numerous workflows over both structured and semi-structured data. Here, we present its significant upgrade, JedAI 2.0, which enhances the original version in three important respects: (i) time efficiency , as the running time has been drastically reduced with the use of high performance data structures and multi-core processing, (ii) effectiveness , since we enriched its library with more established methods, a new layer that exploits loose schema binding as well as the automatic, data-driven configuration of individual methods or entire workflows, and (iii) usability , as the GUI now enables users to manually configure any method based on concrete guidelines, to store the matching results into any of the supported data formats and to visually explore both input and output data.

George Giannakopoulos, Jeff Kubina, John Conroy, Josef Steinberger, Benoit Favre, Mijail Kabadjov, Udo Kruschwitz, Massimo Poesio. Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2015.

In several concept attainment systems, ranging from recommendation systems to information filtering, a sliding window of learning instances has been used in the learning process to allow the learner to follow concepts that change over time. However, no analytic study has been performed on the relation between the size of the sliding window and the performance of a learning system. In this work, we present such an analytic model that describes the effect of the sliding window size on the prediction performance of a learning system based on iterative feedback. Using a signal-to-noise approach to model the learning ability of the underlying machine learning algorithms, we can provide good estimates of the average performance of a modeling system independently of the supervised machine learning algorithm employed. We experimentally validate the effectiveness of the proposed methodology with detailed experiments using synthetic and real datasets, and a variety of learning algorithms, including Support Vector Machines, Naive Bayes, Nearest Neighbor and Decision Trees. The results validate the analysis and indicate very good estimation performance in different settings.