GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates

Agarwal, Vibhor; Joglekar, Sagar; Young, Anthony P.; Sastry, Nishanth

doi:10.1145/3485447.3512144

Cited by 11 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where GraphEncoder t (•) indicate that one of its layers has been modified by t. To be more specific, a pretext token t ⟨𝑘 ⟩,𝑙 will modify the 𝑙-th layer of the graph encoder into t ⟨𝑘 ⟩,𝑙 ⊙ H 𝑙 with an elementwise multiplication, where we multiply the pretext token t ⟨𝑘 ⟩,𝑙 with each row of H 𝑙 element-wise 1 . Subsequently, when 𝑙 < 𝐿, the next layer will be generated as…”

Section: Multi-task Pre-trainingmentioning

confidence: 99%

“…The Web has evolved into an universal data repository, linking an expansive array of entities to create vast and intricate graphs. Mining such widespread graph data has fueled a myriad of Web applications, ranging from Web mining [1,54] and social network analysis [63,65] to content recommendation [35,66]. Contemporary techniques for graph analysis predominantly rely on graph representation learning, particularly graph neural networks (GNNs) [12,13,23,43,60].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

Yu,

Zhou,

Fang

et al. 2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have emerged as a mainstream technique for graph representation learning. However, their efficacy within an end-to-end supervised framework is significantly tied to the availability of task-specific labels. To mitigate labeling costs and enhance robustness in few-shot settings, pre-training on self-supervised tasks has emerged as a promising method, while prompting has been proposed to further narrow the objective gap between pretext and downstream tasks. Although there has been some initial exploration of prompt-based learning on graphs, they primarily leverage a single pretext task, resulting in a limited subset of general knowledge that could be learned from the pre-training data. Hence, in this paper, we propose MultiGPrompt, a novel multi-task pre-training and prompting framework to exploit multiple pretext tasks for more comprehensive pre-trained knowledge. First, in pre-training, we design a set of pretext tokens to synergize multiple pretext tasks. Second, we propose a dual-prompt mechanism consisting of composed and open prompts to leverage task-specific and global pre-training knowledge, to guide downstream tasks in few-shot settings. Finally, we conduct extensive experiments on six public datasets to evaluate and analyze Multi-GPrompt.

show abstract

Section: Multi-task Pre-trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

Yu,

Zhou,

Fang

et al. 2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

show abstract

“…Thus, we define the refutation reward 𝑟 𝑟𝑒 𝑓 𝑢𝑡𝑎𝑡𝑖𝑜𝑛 to reward the actions that increase refutation of ĉ and penalize actions that decrease the refutation of ĉ. Following similar disbelief and polarity classification research works [2,41], we build the refutation classifier 𝑓 𝑟𝑒 𝑓 𝑢𝑡𝑎𝑡𝑖𝑜𝑛 using BERT [20] which measures whether the text expresses refutation. However, distinct from Jiang et al [41], who only use the response text for classification, we use both the tweet and generated response as input.…”

Section: 14mentioning

confidence: 99%

Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation

Ahamad

Kumar

2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

The spread of online misinformation threatens public health, democracy, and the broader society. While professional fact-checkers form the first line of defense by fact-checking popular false claims, they do not engage directly in conversations with misinformation spreaders. On the other hand, non-expert ordinary users act as eyeson-the-ground who proactively counter misinformation -recent research has shown that 96% counter-misinformation responses are made by ordinary users. However, research also found that 2/3 times, these responses are rude and lack evidence. This work seeks to create a counter-misinformation response generation model to empower users to effectively correct misinformation. This objective is challenging due to the absence of datasets containing groundtruth of ideal counter-misinformation responses, and the lack of models that can generate responses backed by communication theories. In this work, we create two novel datasets of misinformation and counter-misinformation response pairs from in-the-wild social media and crowdsourcing from college-educated students. We annotate the collected data to distinguish poor from ideal responses that are factual, polite, and refute misinformation. We propose MisinfoCorrect, a reinforcement learning-based framework that learns to generate counter-misinformation responses for an input misinformation post. The model rewards the generator to increase the politeness, factuality, and refutation attitude while retaining text fluency and relevancy. Quantitative and qualitative evaluation shows that our model outperforms several baselines by generating high-quality counter-responses. This work illustrates the promise of generative text models for social good -here, to help create a safe and reliable information ecosystem. The code and data is accessible on https://github.com/claws-lab/MisinfoCorrect.

show abstract

“…To cope with the limitations in terms of the data that an instance has available, we take a conversational approach 2 . We capture the conversational context of each post using GraphNLI (Agarwal et al 2022), a state-of-the-art graph learning-based framework. This is in stark contrast to previous works (Bin Zia et al 2022;Kurita, Belova, and Anastasopoulos 2019;Risch and Krestel 2020) that look at each post in isolation.…”

Section: Introductionmentioning

confidence: 99%

Decentralised Moderation for Interoperable Social Networks: A Conversation-Based Approach for Pleroma and the Fediverse

Agarwal,

Raman,

Sastry

et al. 2024

ICWSM

View full text Add to dashboard Cite

The recent development of decentralised and interoperable social networks (such as the "fediverse") creates new challenges for content moderators. This is because millions of posts generated on one server can easily "spread" to another, even if the recipient server has very different moderation policies. An obvious solution would be to leverage moderation tools to automatically tag (and filter) posts that contravene moderation policies, e.g. related to toxic speech. Recent work has exploited the conversational context of a post to improve this automatic tagging, e.g. using the replies to a post to help classify if it contains toxic speech. This has shown particular potential in environments with large training sets that contain complete conversations. This, however, creates challenges in a decentralised context, as a single conversation may be fragmented across multiple servers. Thus, each server only has a partial view of an entire conversation because conversations are often federated across servers in a non-synchronized fashion. To address this, we propose a decentralised conversation-aware content moderation approach suitable for the fediverse. Our approach employs a graph deep learning model (GraphNLI) trained locally on each server. The model exploits local data to train a model that combines post and conversational information captured through random walks to detect toxicity. We evaluate our approach with data from Pleroma, a major decentralised and interoperable micro-blogging network containing 2 million conversations. Our model effectively detects toxicity on larger instances, exclusively trained using their local post information (0.8837 macro-F1). Yet, we show that this approach does not perform well on smaller instances that do not possess sufficient local training data. Thus, in cases where a server contains insufficient data, we strategically retrieve information (posts or model parameters) from other servers to reconstruct larger conversations and improve results. With this, we show that we can attain a macro-F1 of 0.8826. Our approach has considerable scope to improve moderation in decentralised and interoperable social networks such as Pleroma or Mastodon.

show abstract

GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates

Cited by 11 publications

References 28 publications

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation

Decentralised Moderation for Interoperable Social Networks: A Conversation-Based Approach for Pleroma and the Fediverse

Contact Info

Product

Resources

About