Aspect-Controlled Neural Argument Generation

• URL: http://arxiv.org/abs/2005.00084v1
• Date: Thu, 30 Apr 2020 20:17:22 GMT
• Title: Aspect-Controlled Neural Argument Generation
• Authors: Benjamin Schiller and Johannes Daxenberger and Iryna Gurevych
• Abstract summary: We train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect. Our evaluation shows that our generation model is able to generate high-quality, aspect-specific arguments. These arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments.
• Score: 65.91772010586605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 train a language model for argument generation that can be controlled on a fine-grained level 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 our generation model is able to generate high-quality, aspect-specific arguments. Moreover, these arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments. We publish all datasets and code to fine-tune the language model.

Related papers

• "Let's Argue Both Sides": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities [0.8999666725996974]
  We propose Argument Generation as a method of forcing models to utilize their reasoning capabilities. Our method involves the generation of arguments for each possible inference result, and asking the end model to rank the generated arguments.
  arXiv  Detail & Related papers  (2024-10-16T19:49:30Z)
• Auditing Counterfire: Evaluating Advanced Counterargument Generation with Evidence and Style [11.243184875465788]
  GPT-3.5 Turbo ranked highest in argument quality with strong paraphrasing and style adherence, particularly in reciprocity' style arguments. The stylistic counter-arguments still fall short of human persuasive standards, where people also preferred reciprocal to evidence-based rebuttals.
  arXiv  Detail & Related papers  (2024-02-13T14:53:12Z)
• Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation [62.069374456021016]
  We present the ArgTersely benchmark for sentence-level counter-argument generation. We also propose Arg-LlaMA for generating high-quality counter-argument.
  arXiv  Detail & Related papers  (2023-12-21T06:51:34Z)
• Exploring the Potential of Large Language Models in Computational Argumentation [54.85665903448207]
  Large language models (LLMs) have demonstrated impressive capabilities in understanding context and generating natural language. This work aims to embark on an assessment of LLMs, such as ChatGPT, Flan models, and LLaMA2 models, in both zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2023-11-15T15:12:15Z)
• ArgU: A Controllable Factual Argument Generator [0.0]
  ArgU is a neural argument generator capable of producing factual arguments from input facts and real-world concepts. We have compiled and released an annotated corpora of 69,428 arguments spanning six topics and six argument schemes.
  arXiv  Detail & Related papers  (2023-05-09T10:49:45Z)
• Retrieval-Augmented Generative Question Answering for Event Argument Extraction [66.24622127143044]
  We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings.
  arXiv  Detail & Related papers  (2022-11-14T02:00:32Z)
• Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets [49.65208986436848]
  We investigate the effect of Argument Mining dataset composition in few- and zero-shot settings. Our findings show that, while fine-tuning is mandatory to achieve acceptable model performance, using carefully composed training samples and reducing the training sample size by up to almost 90% can still yield 95% of the maximum performance.
  arXiv  Detail & Related papers  (2022-05-23T17:14:32Z)
• Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction [80.61458287741131]
  We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE) By formulating EAE as a language generation task, our method effectively encodes event structures and captures the dependencies between arguments. Our proposed model finetunes multilingual pre-trained generative language models to generate sentences that fill in the language-agnostic template with arguments extracted from the input passage.
  arXiv  Detail & Related papers  (2022-03-15T23:00:32Z)
• AMPERSAND: Argument Mining for PERSuAsive oNline Discussions [41.06165177604387]
  We propose a computational model for argument mining in online persuasive discussion forums. Our approach relies on identifying relations between components of arguments in a discussion thread. Our models obtain significant improvements compared to recent state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-04-30T10:33:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.