In this paper, we address the challenge of discovering financial signals in narrative financial reports. As these documents are often lengthy and tend to blend routine information with new information, it is challenging for professionals to discern critical financial signals. To this end, we leverage the inherent nature of the year-to-year structure of reports to define a novel signal-highlighting task; more importantly, we propose a compare-and-contrast multistage pipeline that recognizes different relationships between the reports and locates relevant rationales for these relationships. We also create and publicly release a human-annotated dataset for our task. Our experiments on the dataset validate the effectiveness of our pipeline, and we provide detailed analyses and ablation studies to support our findings.
In this system demonstration, we seek to streamline the process of reviewing financial statements and provide insightful information for practitioners. We develop FISH, an interactive system that extracts and highlights crucial textual signals from financial statements efficiently and precisely. To achieve our goal, we integrate pre-trained BERT representations and a fine-tuned BERT highlighting model with a newly-proposed two-stage classify-then-highlight pipeline. We also conduct the human evaluation, showing FISH can provide accurate financial signals. FISH overcomes the limitations of existing research andmore importantly benefits both academics and practitioners in finance as they can leverage state-of-the-art contextualized language models with their newly gained insights. The system is available online at https://fish-web-fish.de.r.appspot.com/, and a short video for introduction is at https://youtu.be/ZbvZQ09i6aw.
While internalized “implicit knowledge” in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question. Based on the text-to-text transfer transformer (T5) model, this work explores a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice (MC) question answering tasks. Experiments on three representative MC datasets show the surprisingly good performance of our simple template, coupled with a logit normalization technique for disambiguation. Furthermore, we verify that our proposed template can be easily extended to other MC tasks with contexts such as supporting facts in open-book question answering settings. Starting from the MC task, this work initiates further research to find generic natural language templates that can effectively leverage stored knowledge in pretrained models.
This paper presents a web-based information system, RiskFinder, for facilitating the analyses of soft and hard information in financial reports. In particular, the system broadens the analyses from the word level to sentence level, which makes the system useful for practitioner communities and unprecedented among financial academics. The proposed system has four main components: 1) a Form 10-K risk-sentiment dataset, consisting of a set of risk-labeled financial sentences and pre-trained sentence embeddings; 2) metadata, including basic information on each company that published the Form 10-K financial report as well as several relevant financial measures; 3) an interface that highlights risk-related sentences in the financial reports based on the latest sentence embedding techniques; 4) a visualization of financial time-series data for a corresponding company. This paper also conducts some case studies to showcase that the system can be of great help in capturing valuable insight within large amounts of textual information. The system is now online available at
https://cfda.csie.org/RiskFinder/.