The workweek is the best time to start a family – A Study of GPT-2 Based Claim Generation

Gretz, Shai; Bilu, Yonatan; Cohen-Karlik, Edo; Slonim, Noam

doi:10.18653/v1/2020.findings-emnlp.47

Cited by 16 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging external knowledge, though a promising feature for guiding finetuning, may benefit from better encoding strategies compared to the conventional method of using control codes in text. However, given that the identified knowledge is extractive and that we encoded multiple aspects and targets per example in contrast to related controlled text generation approaches Schiller et al, 2020;Gretz et al, 2020;Cachola et al, 2020), further investigations with importance sampling of argumentative knowledge are advised. Ideally, such sampling would be tailored to a specific domain or target audience.…”

Section: Discussionmentioning

confidence: 99%

“…However, they have been applied to the domain of argumentation only recently, specifically for argument generation. Gretz et al (2020) proposed a pipeline based on GPT-2 (Radford et al, 2019) for generating coherent claims for a given debate topic. A more controlled approach for argument generation was developed by Schiller et al (2020), which performs argument generation with fine-grained control of topic, aspect (core reasoning), and stance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Generating Informative Conclusions for Argumentative Texts

Syed¹,

Khatib²,

Alshomary³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

The purpose of an argumentative text is to support a certain conclusion. Yet, they are often omitted, expecting readers to infer them rather. While appropriate when reading an individual text, this rhetorical device limits accessibility when browsing many texts (e.g., on a search engine or on social media). In these scenarios, an explicit conclusion makes for a good candidate summary of an argumentative text. This is especially true if the conclusion is informative, emphasizing specific concepts from the text. With this paper we introduce the task of generating informative conclusions: First, Webis-ConcluGen-21 is compiled, a large-scale corpus of 136,996 samples of argumentative texts and their conclusions. Second, two paradigms for conclusion generation are investigated; one extractive, the other abstractive in nature. The latter exploits argumentative knowledge that augment the data via control codes and finetuning the BART model on several subsets of the corpus. Third, insights are provided into the suitability of our corpus for the task, the differences between the two generation paradigms, the trade-off between informativeness and conciseness, and the impact of encoding argumentative knowledge. The corpus, code, and the trained models are publicly available. 1

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Generating Informative Conclusions for Argumentative Texts

Syed¹,

Khatib²,

Alshomary³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…Dathathri et al (2019) train two models that control the sentiment and topic of the output of pre-trained language models at inference. Gretz et al (2020a) fine-tune GPT-2 on existing, labeled datasets to generate claims for given topics. However, the latter works do not explore generation for such a fine-grained and explicit control as proposed in this work.…”

Section: Related Workmentioning

confidence: 99%

“…Models for argument and claim generation have been discussed in our related work and are widely available. Gretz et al (2020a) suggest that, in order to allow for a fine-grained control over claim/argument generation, aspect selection needs to be handled carefully, which is what we have focused on in this work. The dangers of misuse of language models like the CTRL have been extensively discussed by its authors (Keskar et al, 2019).…”

Section: Ethics Statementmentioning

confidence: 99%

Aspect-Controlled Neural Argument Generation

Schiller¹,

Daxenberger²,

Gurevych³

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we present the Arg-CTRL-a language model for argument generation that can be controlled to generate sentence-level arguments for a given topic, stance, and aspect. We define argument aspect detection as a necessary method to allow this fine-granular control and crowdsource a dataset with 5,032 arguments annotated with aspects. Our evaluation shows that the Arg-CTRL is able to generate high-quality, aspectspecific arguments, applicable to automatic counter-argument generation. We publish the model weights and all datasets and code to train the Arg-CTRL. 1 Nuclear reactors produce radioactive waste ...

show abstract

“…Claim generation, however, may be different from premise summarization, because it takes stance into account. Although some studies on argument mining [1, 15,17] explore claim generation, few generate claims for financial opinions. Many studies in financial opinion mining stop at step 3 in Fig.…”

mentioning

confidence: 99%

FinTech Applications

Chen

Huang

Chen

2021

From Opinion Mining to Financial Argument Mining

View full text Add to dashboard Cite

The Financial Stability Board defines financial technology (FinTech) as “technology-enabled innovation in financial services.” At the 2015 World Economic Forum, experts proposed a taxonomy for financial services that can be classified into six major categories: payments, deposits and lending, market provisioning, capital raising, insurance, and investment management. Because financial opinion mining can be applied to many listed services, we survey various cases in this chapter and show that financial opinion mining is useful and crucial in many financial application scenarios.

show abstract

The workweek is the best time to start a family – A Study of GPT-2 Based Claim Generation

Cited by 16 publications

References 27 publications

Generating Informative Conclusions for Argumentative Texts

Generating Informative Conclusions for Argumentative Texts

Aspect-Controlled Neural Argument Generation

FinTech Applications

Contact Info

Product

Resources

About