Lexicon Guided Attentive Neural Network Model for Argument Mining

Lin, J.; Huang, Kuo Yu; Huang, Hen-Hsen; Chen, Hsin-Hsi

doi:10.18653/v1/w19-4508

Cited by 7 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the AM systems that use neural attention, the one used in [29] integrate hierarchical attention and biGRU for the analysis of the quality of the argument, the one in [30] use attention to integrate sentiment lexicon, while in other works [31], [32], [33] attention modules are stacked on top of recurrent layers. The use of Pointer Networks for AM has also been investigated [34].…”

Section: B Neural Attention For Ammentioning

confidence: 99%

Multi-Task Attentive Residual Networks for Argument Mining

Galassi

Lippi

Torroni

2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.

show abstract

Section: B Neural Attention For Ammentioning

confidence: 99%

Multi-Task Attentive Residual Networks for Argument Mining

Galassi

Lippi

Torroni

2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Among the AM systems that use neural attention, the one used in [18] integrate hierarchical attention and biGRU for the analysis of the quality of the argument, the one in [19] use attention to integrate sentiment lexicon, while in other works [20]- [22] attention modules are stacked on top of recurrent layers. The use of Pointer Networks for AM has also been investigated [23].…”

Section: B Neural Attention For Ammentioning

confidence: 99%

Multi-Task Attentive Residual Networks for Argument Mining

Galassi,

Lippi,

Torroni

2021

Preprint

View full text Add to dashboard Cite

We explore the use of residual networks and neural attention for argument mining and in particular link prediction. The method we propose makes no assumptions on document or argument structure. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble. We evaluate it on a challenging data set consisting of usergenerated comments, as well as on two other datasets consisting of scientific publications. On the user-generated content dataset, our model outperforms state-of-the-art methods that rely on domain knowledge. On the scientific literature datasets it achieves results comparable to those yielded by BERT-based approaches but with a much smaller model size.

show abstract

“…However, it should still be unambiguously supportive of or against a topic. Claims will not be annotated as an argument unless they include some evidence or reasoning behind the claim; however, Lin et al (2019) do find a few wrongly annotated sentences in this regard. The corpus comes with a fixed 70-10-20 split.…”

Section: Datasetsmentioning

confidence: 99%

Spurious Correlations in Cross-Topic Argument Mining

Jakobsen¹,

Barrett²,

Søgaard³

2021

Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics

View full text Add to dashboard Cite

Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than merely relying on withintopic spurious correlations. We examine the effectiveness of this approach by analysing the output of single-task and multi-task models for cross-topic argument mining through a combination of linear approximations of their decision boundaries, manual feature grouping, challenge examples, and ablations across the input vocabulary. Surprisingly, we show that cross-topic models still rely mostly on spurious correlations and only generalise within closely related topics, e.g., a model trained only on closed-class words and a few common open-class words outperforms a state-of-theart cross-topic model on distant target topics.

show abstract

Lexicon Guided Attentive Neural Network Model for Argument Mining

Cited by 7 publications

References 18 publications

Multi-Task Attentive Residual Networks for Argument Mining

Multi-Task Attentive Residual Networks for Argument Mining

Multi-Task Attentive Residual Networks for Argument Mining

Spurious Correlations in Cross-Topic Argument Mining

Contact Info

Product

Resources

About