Search

There are more than 2,000 listed companies on the UK’s London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single financial year. UK annual reports are very lengthy documents with around 80 pages on average. In this study, we aim to benchmark a variety of summarisation methods on a set of different pre-trained transformers with different extraction techniques. In addition, we considered multiple evaluation metrics in order to investigate their differing behaviour and applicability on a dataset from the Financial Narrative Summarisation (FNS 2020) shared task, which is composed of annual reports published by firms listed on the London Stock Exchange and their corresponding summaries. We hypothesise that some evaluation metrics do not reflect true summarisation ability and propose a novel BRUGEscore metric, as the harmonic mean of ROUGE-2 and BERTscore. Finally, we perform a statistical significance test on our results to verify whether they are statistically robust, alongside an adversarial analysis task with three different corruption methods.

Natural Language Processing is increasingly being applied in the finance and business industry to analyse the text of many different types of financial documents. Given the increasing growth of firms around the world, the volume of financial disclosures and financial texts in different languages and forms is increasing sharply and therefore the study of language technology methods that automatically summarise content has grown rapidly into a major research area. Corpora for financial narrative summarisation exist in English, but there is a significant lack of financial text resources in the French language. To remedy this, we present CoFiF Plus, the first financial narrative summarisation dataset providing a comprehensive set of financial text written in the French language. The dataset has been extracted from french financial reports published in PDF file format. It is composed of 1,703 reports from the most capitalised companies in France (Euronext Paris) covering a time frame from 1995 to 2021. This paper describes the collection, annotation and validation of the financial reports and their summaries. It also describes the dataset and gives the results of some baseline summarisers.

Welcome to the 4th Financial Narrative Processing Workshop (FNP 2022). This year the workshop is held at the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022) in Marseille, France on 24 June 2022 (a full-day event). This is an international gathering of researchers and speakers working on Financial Narratives from computing, accounting and finance. Following the success of the First FNP 2018 at LREC’18 in Japan, the Second FNP 2019 at NoDaLiDa 2019 in Finland, the Multiling 2019 Financial narrative Summarisation task at RANLP in Bulgaria, the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020) at COLING 2020 in Barcelona, Spain and the 3rd Financial Narrative Processing Workshop (FNP 2021) in Lancaster UK, we have received a great deal of positive feedback and interest in continuing the development of the financial narrative processing field, especially from our shared task participants. This has resulted in the organization of the 4th Financial Narrative Processing Workshop (FNP 2022). The FNP 2022 workshop achieved our aim of supporting the rapidly growing area of financial text mining. We ran three different shared tasks focusing on text summarization, structure detection and causal sentence detection, namely FNS, FinToc and FinCausal shared tasks respectively. The shared tasks attracted several teams from different universities and organisations from around the globe. The shared tasks resulted in the large scale experimental results and state of the art methods applied mainly to financial data. This shows the importance and growth of this field and we want to continue to be associated with top NLP venues. The workshop focused mainly on the use of Natural Language Processing (NLP), Machine Learning (ML), and Corpus Linguistics (CL) methods related to all aspects of financial text summarisation, text mining and financial narrative processing (FNP). There is a growing interest in the a

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 Financial Narrative Processing 2022 Workshop (FNP 2022 Workshop). The Financial Narrative summarisation Shared Task (FNS-2022) has been running since 2020 as part of the Financial Narrative Processing (FNP) workshop series (El-Haj et al., 2022; El-Haj et al., 2021; El-Haj et al., 2020b; El-Haj et al., 2019c; El-Haj et al., 2018). The shared task included one main task 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 third 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 UK, Greece and Spain. A total number of 14 systems from 7 different teams participated in the shared task.}

Natural Language Processing is increasingly being applied to analyse the text of many different types of financial documents. For many tasks, it has been shown that standard language models and tools need to be adapted to the financial domain in order to properly represent domain specific vocabulary, styles and meanings. Previous work has almost exclusively focused on English financial text, so in this paper we describe the creation of novel financial word embeddings for three languages: English, French and Arabic. In order to evaluate the effectiveness of the embeddings, we started by evaluating the English embeddings on a sentiment analysis classification task using the existing FinancialPhrase dataset and show improved performance over a standard GloVe based model using convolutional neural networks

Natural Language Processing is increasingly being applied to analyse the text of many different types of financial documents. For many tasks, it has been shown that standard language models and tools need to be adapted to the financial domain in order to properly represent domain specific vocabulary, styles and meanings. Previous work has almost exclusively focused on English financial text, so in this paper we describe the creation of novel financial word embeddings for three languages: English, French and Arabic. In order to evaluate the effectiveness of the embeddings, we started by evaluating the English embeddings on a sentiment analysis classification task using the existing FinancialPhrase dataset and show improved performance over a standard GloVe based model using convolutional neural networks

This paper presents the results and findings of the Financial Narrative Summarisation Shared Task on summarising UK annual reports. The shared task was organised as part of the Financial Narrative Processing 2021 Workshop (FNP 2021 Workshop). The shared task included one main task which is the use of either abstractive or extractive automatic summarisers to summarise long documents in terms of UK financial annual reports. This shared task is the second to target financial documents. The data for the shared task was created and collected from publicly available UK annual reports published by firms listed on the London Stock Exchange. A total number of 10 systems from 5 different teams participated in the shared task. In addition, we had two baseline and two topline summarisers to help evaluate the results of the participating teams and compare them to the state-of-the-art systems.

In this paper we show the results of our participation in the FNS 2021 shared task. In our work we propose an end to end financial narrative summarization system that first selects salient sentences from the document and then paraphrases extracted sentences. This method generates an overall concise summary that maximises the ROUGE metric with the gold standard summary. The end to end system is developed using a hybrid extractive and abstractive architecture followed by joint training using policy-based reinforcement learning to bridge together the two networks. Empirically, we achieve better scores than the proposed baselines and toplines of FNS 2021 (LexRank, TextRank, MUSE topline and POLY baseline) and we were ranked 2nd in the shared task competition. Keywords: Summarization, Neural networks, Reinforcement learning, sequence to sequence learning; actor-critic methods; policy gradients.