ClimateBert: A Pretrained Language Model for Climate-Related Text

Webersinke, Nicolas; Kraus, Mathias; Bingler, Julia Anna; Leippold, Markus

doi:10.48550/arxiv.2110.12010

Cited by 14 publications

(26 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 Extensions of the BERT methodology can be found in Webersinke et al (2021); Bingler et al (2022b). 6 To mitigate concerns that we introduce a bias in our analysis due to some interference with determinants for CDS offerings, we also analyzed our climate scores for an equally-sized sample of US stocks that we selected randomly from the Russell 3000 index.…”

Section: Introductionmentioning

confidence: 99%

Ask BERT: How Regulatory Disclosure of Transition and Physical Climate Risks Affects the CDS Term Structure

Kölbel

Leippold

Rillaerts

et al. 2022

Journal of Financial Econometrics

View full text Add to dashboard Cite

We use BERT, an AI-based algorithm for language understanding, to quantify regulatory climate risk disclosures and analyze their impact on the term structure in the credit default swap (CDS) market. Risk disclosures can either increase or decrease CDS spreads, depending on whether the disclosure reveals new risks or reduces uncertainty. Training BERT to differentiate between transition and physical climate risks, we find that disclosing transition risks increases CDS spreads after the Paris Climate Agreement of 2015, while disclosing physical risks decreases the spreads. In addition, we also find that the election of Trump had a negative impact on CDS spreads for firms exposed to transition risk. These impacts are consistent with theoretical predictions and economically and statistically significant.

show abstract

Section: Introductionmentioning

confidence: 99%

Ask BERT: How Regulatory Disclosure of Transition and Physical Climate Risks Affects the CDS Term Structure

Kölbel

Leippold

Rillaerts

et al. 2022

Journal of Financial Econometrics

View full text Add to dashboard Cite

show abstract

“…Figure 2 and the following sections provide some guidance for authors and publishers of hydrologic articles interested in future-proofing their work by making research findable and synthesisable. The benefit of applying this guidance lies not only in making the individual article accessible for a long time, it also will improve the development of hydrology-specific text mining solutions, which have a higher accuracy than generic approaches as shown in other fields (Gu et al, 2021;Webersinke et al, 2022). Therefore, if hydrology wants to make use of these lifelines to deal with increasing publication numbers and available knowledge, we also need to make a community effort to prepare for them.…”

Section: Guidance For Future-proofing Hydrologic Knowledgementioning

confidence: 99%

“…greenwashing (e.g. ClimateBERT, Bingler et al, 2022;Webersinke et al, 2022) or by summarizing climate impact evidence across more than 100 000 scientific articles (Callaghan et al, 2021). In the field of materials sciences, Tshitoyan et al (2019) were able to not only reveal the knowledge hidden in thousands of publications on material science properties, but were also able to find new promising thermoelectric compounds 4 years (!)…”

Section: Guidance For Future-proofing Hydrologic Knowledgementioning

confidence: 99%

Lifelines for a drowning science ‐ improving findability and synthesis of hydrologic publications

Stein

Mukkavilli

Wagener

2022

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…New BERT models and applications are being reported at rapid speed as the model is continuously applied in new fields. Examples are the recently developed Cli-mateBert, a pre-trained language model for climaterelated text (Webersinke et al, 2021) or COVID-Twitter-BERT (CT-BERT) (Müller et al, 2020).…”

Section: Text Classificationmentioning

confidence: 99%

A New Dataset for Topic-Based Paragraph Classification in Genocide-Related Court Transcripts

Schirmer¹,

Kruschwitz²,

Donabauer³

2022

Preprint

View full text Add to dashboard Cite

Recent progress in natural language processing has been impressive in many different areas with transformer-based approaches setting new benchmarks for a wide range of applications. This development has also lowered the barriers for people outside the NLP community to tap into the tools and resources applied to a variety of domain-specific applications. The bottleneck however still remains the lack of annotated gold-standard collections as soon as one's research or professional interest falls outside the scope of what is readily available. One such area is genocide-related research (also including the work of experts who have a professional interest in accessing, exploring and searching large-scale document collections on the topic, such as lawyers). We present GTC (Genocide Transcript Corpus), the first annotated corpus of genocide-related court transcripts which serves three purposes: (1) to provide a first reference corpus for the community, (2) to establish benchmark performances (using state-of-the-art transformer-based approaches) for the new classification task of paragraph identification of violence-related witness statements, (3) to explore first steps towards transfer learning within the domain. We consider our contribution to be addressing in particular this year's hot topic on Language Technology for All.

show abstract

ClimateBert: A Pretrained Language Model for Climate-Related Text

Cited by 14 publications

References 0 publications

Ask BERT: How Regulatory Disclosure of Transition and Physical Climate Risks Affects the CDS Term Structure

Ask BERT: How Regulatory Disclosure of Transition and Physical Climate Risks Affects the CDS Term Structure

Lifelines for a drowning science ‐ improving findability and synthesis of hydrologic publications

A New Dataset for Topic-Based Paragraph Classification in Genocide-Related Court Transcripts

Contact Info

Product

Resources

About