TACAM: Topic And Context Aware Argument Mining

@article{Fromm2019TACAMTA,
  title={TACAM: Topic And Context Aware Argument Mining},
  author={Michael Fromm and Evgeniy Faerman and T. Seidl},
  journal={2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI)},
  year={2019},
  pages={99-106}
}
In this work we address the problem of argument search. The purpose of argument search is the distillation of pro and contra arguments for requested topics from large text corpora. In previous works, the usual approach is to use a standard search engine to extract text parts which are relevant to the given topic and subsequently use an argument recognition algorithm to select arguments from them. The main challenge in the argument recognition task, which is also known as argument mining, is… 

Figures and Tables from this paper

Focusing Knowledge-based Graph Argument Mining via Topic Modeling

TLDR
This paper presents a hybrid model that combines latent Dirichlet allocation and word embeddings to obtain external knowledge from structured and unstructured data to study the task of sentence-level argument mining.

Diversity Aware Relevance Learning for Argument Search

TLDR
This work introduces a new multi-step approach for the argument retrieval problem that employs a machine learning model to capture semantic relationships between arguments and leads to a significant improvement in the argument retrieved task even though it requires less data.

On the Effect of Sample and Topic Sizes for Argument Mining Datasets

TLDR
This work inquires whether it is necessary for acceptable performance of Argument Mining to have datasets growing in size or, if not, how smaller datasets have to be composed for optimal performance.

A multi-task approach to argument frame classification at variable granularity levels

TLDR
This work presents an approach to bridge between coarse-grained and issue-specific inventories for classifying argumentation frames and proposes a supervised approach to classifying frames of arguments at a variable level of granularity by clustering issue- specific, user-provided labels into frame clusters and predicting the frame cluster that an argument evokes.

Towards a Holistic View on Argument Quality Prediction

TLDR
Grounded on rich results from thorough empirical evaluations, this work assesses the generalization capabilities of argument quality estimation across diverse domains, the interplay with related argument mining tasks, and the impact of emotions on perceived argument strength.

Argument Mining Driven Analysis of Peer-Reviews

TLDR
It is shown that Argument Mining can be used to efficiently extract the most relevant parts from reviews, which are paramount for the publication decision, and the process remains interpretable, since the extracted arguments can be highlighted in a review without detaching them from their context.

Exploring Argument Retrieval with Transformers Notebook for the Touché Lab on Argument Retrieval at CLEF 2020

TLDR
This work investigates three approaches to employ transformer-based models as part of an information retrieval pipeline, and investigates embedding of documents using Google’s BERT-like universal sentence encoder (USE) combined with a subsequent retrieval step based on a nearest-neighbor search in the embedding space.

Don’t Drop the Topic - The Role of the Prompt in Argument Identification in Student Writing

TLDR
This paper cluster a recently released corpus through topic modeling into prompts and train argument identification models on different data settings and shows that, given the same amount of training data, prompt-specific training performs better than cross-prompt training.

Relational and Fine-Grained Argument Mining

TLDR
The main part of the article describes the research on argument mining, both coarse- grained and fine-grained methods, and on same-side stance classification, a relational approach to the problem of stance classification and concludes with an outlook.

Explainable Machine Learning and Mining of Influential Patterns from Sparse Web

  • C. LeungFan JiangYibin Zhang
  • Computer Science
    2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)
  • 2020
TLDR
A web intelligent solution to conduct explainable machine learning and mining of influential patterns from sparse web is presented, which provides a compressed representation of sparse web, discovers influential websites and/or web pages that are frequently browsed or surfed by web surfers, and recommends these influential Websites to otherweb surfers.

References

SHOWING 1-10 OF 45 REFERENCES

Robust Argument Unit Recognition and Classification

TLDR
This paper casts ARC as a sequence labeling task, develops a number of methods for ARC sequence tagging and establishes the state of the art for ARC-8, a new benchmark for evaluating the ARC task.

Cross-topic Argument Mining from Heterogeneous Sources

TLDR
This paper proposes a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts and shows that integrating topic information into bidirectional long short-term memory networks outperforms vanilla BiLSTMs in F1 in two- and three-label cross-topic settings.

Extracting Argument and Domain Words for Identifying Argument Components in Texts

TLDR
The experiments show that replacing n-grams and syntactic rules with features and constraints using extracted argument and domain words significantly improves argument mining performance for persuasive essays.

Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks

TLDR
A new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts that generalizes best to unseen topics and outperforms vanilla BiLSTM models by 6% in accuracy and 11% in F-score is proposed.

Context-Independent Claim Detection for Argument Mining

TLDR
This work proposes a method that exploits structured parsing information to detect claims without resorting to contextual information, and yet achieve a performance comparable to that of state-of-the-art methods that heavily rely on the context.

ArgumenText: Searching for Arguments in Heterogeneous Sources

TLDR
This paper presents an argument retrieval system capable of retrieving sentential arguments for any given controversial topic, and finds that its system covers 89% of arguments found in expert-curated lists of arguments from an online debate portal, and also identifies additional valid arguments.

Building an Argument Search Engine for the Web

TLDR
An argument search framework for studying how people query for arguments, how to mine arguments from the web, or how to rank them is developed and a prototype search engine is built that relies on an initial, freely accessible index of nearly 300k arguments crawled from reliable web resources.

Some Facets of Argument Mining for Opinion Analysis

TLDR
A conceptual semantics of the relations of evaluative expressions with a discourse structure such as an elaboration, an illustration, or a reformulation must also be interpreted as an argument is developed.

Argumentation Mining in User-Generated Web Discourse

TLDR
The findings show that argumentation mining in user-generated Web discourse is a feasible but challenging task and offers the data, source codes, and annotation guidelines to the community under free licenses.

Context-aware Argumentative Relation Mining

TLDR
This paper presents contextaware argumentative relation mining that uses features extracted from writing topics as well as from windows of context sentences that improve predictive performance in two argumentative relations classification tasks.