paper-with-me

Papers

Employing Argumentation Knowledge Graphs for Neural Argument Generation

2021-08-01 · ACL 2021 5 · Khalid Al Khatib, Lukas Trautner, Henning Wachsmuth, Yufang Hou, Benno Stein

Generating high-quality arguments, while being challenging, may benefit a wide range of downstream applications, such as writing assistants and argument search engines. Motivated by the effectiveness of utilizing knowledge graphs for supporting general text generation tasks, this paper investigates the usage of argumentation-related knowledge graphs to control the generation of arguments. In particular, we construct and populate three knowledge graphs, employing several compositions of them to encode various knowledge into texts of debate portals and relevant paragraphs from Wikipedia. Then, the texts with the encoded knowledge are used to fine-tune a pre-trained text generation model, GPT-2. We evaluate the newly created arguments manually and automatically, based on several dimensions important in argumentative contexts, including argumentativeness and plausibility. The results demonstrate the positive impact of encoding the graphs{'} knowledge into debate portal texts for generating arguments with superior quality than those generated without knowledge.

📄 PDF Abstract BibTeX

Code (1)

webis-de/ACL-21 공식 구현

Tasks

Knowledge GraphsText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

First Workshop on Argumentation Knowledge Graphs

2021-09-13 · AKBC Workshop ArgKG 2021 10 · Anonymous

First Workshop on Argumentation Knowledge Graphs

Knowledge Graphs

Improving Quality Assessment of Online Reviews UsingFormal Argumentation Theory and Knowledge Graphs

2021-09-13 · AKBC Workshop ArgKG 2021 10 · Anonymous

In this extended abstract, we introduce a previously developed framework for the assessment of the quality of product reviews by using formal argumentation theory and machine learning. Then, we outline current developme…

BIG-bench Machine LearningKnowledge Graphs

End-to-end argumentation knowledge graph construction

2021-09-13 · AKBC Workshop ArgKG 2021 10 · Anonymous

This paper studies the end-to-end construction of an argumentation knowledge graph that is intended to support argument synthesis, argumentative question answering, or fake news detection, among others. The study is moti…

16kFake News Detectiongraph constructionKnowledge Graphs+2

Aggregation in Value-Based Argumentation Frameworks

2019-07-22 · Grzegorz Lisowski, Sylvie Doutre, Umberto Grandi

Value-based argumentation enhances a classical abstract argumentation graph - in which arguments are modelled as nodes connected by directed arrows called attacks - with labels on arguments, called values, and an orderin…

Abstract Argumentation

Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)

2020-12-10 · Nico Potyka

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning…

BIG-bench Machine Learning