PPubMed22 Jan 2020Cited 8×

Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning

Andrea Galassi, Kristian Kersting, Marco Lippi, Xiaoting Shao, Paolo Torroni

Abstract

Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap toward performing advanced reasoning tasks. In this position paper, we posit that neural-symbolic and statistical relational learning could play a crucial role in the integration of symbolic and sub-symbolic methods to achieve this goal.

A figure from Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning — fig. from the paper

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

The paper argues that combining neural‑symbolic and statistical relational learning can advance argumentation mining by enabling joint reasoning and learning.

What’s new

i.Proposes a neural‑symbolic framework for joint detection of argument components and relations.
ii.Demonstrates integration of DeepProbLog and Ground‑Specific Markov Logic Networks for argumentation mining.
iii.Highlights the advantage of embedding logical constraints directly into the training process.
iv.Outlines challenges and future research directions for symbolic‑subsymbolic integration.

How they did it

The authors outline a design that couples neural classifiers with probabilistic logic programs, using DeepProbLog and GS‑MLN to encode soft and hard constraints, enabling joint training and inference.

Caveats

✕Inference efficiency remains a challenge for large‑scale argumentation datasets.
✕Existing neural‑symbolic and SRL tools are not yet mainstream and need better integration with NLP models.
✕Selecting appropriate logical languages and weight learning strategies is still an open problem.

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Similar papers in all four archives

The same idea searched in arXiv, PubMed, bioRxiv and chemRxiv at once, so a method can lead you to where it is being applied.

AarXiv3 found

PPubMed4 found

BbioRxiv2 found

CchemRxiv2 found

Searching the other archives…