Cross-topic Argument Mining from Heterogeneous Sources

@inproceedings{Stab2018CrosstopicAM,
  title={Cross-topic Argument Mining from Heterogeneous Sources},
  author={Christian Stab and Tristan Miller and Benjamin Schiller and Pranav Rai and Iryna Gurevych},
  booktitle={EMNLP},
  year={2018}
}
Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. We show that… 
Spurious Correlations in Cross-Topic Argument Mining
TLDR
Surprisingly, it is shown 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-the-art cross- topic model on distant target topics.
TACAM: Topic And Context Aware Argument Mining
TLDR
This work argues that topic information is crucial for argument mining, since the topic defines the semantic context of an argument, and proposes different models for the classification of arguments, which take information about a topic of a argument into account.
Corpus Wide Argument Mining - a Working Solution
TLDR
This work presents a first end-to-end high-precision, corpus-wide argument mining system, made possible by combining sentence-level queries over an appropriate indexing of a very large corpus of newspaper articles, with an iterative annotation scheme.
Classification and Clustering of Arguments with Contextualized Word Embeddings
TLDR
For the first time, it is shown how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets.
Fine-Grained Argument Unit Recognition and Classification
TLDR
This work presents a dataset of arguments from heterogeneous sources annotated as spans of tokens within a sentence, as well as with a corresponding stance, and shows that and how such difficult argument annotations can be effectively collected through crowdsourcing with high interannotator agreement.
Lexicon Guided Attentive Neural Network Model for Argument Mining
TLDR
This paper proposes a methodology to integrate lexicon information into a neural network model by attention mechanism and conducts experiments on the UKP dataset, which is collected from heterogeneous sources and contains several text types, e.g., microblog, Wikipedia, and news.
Transferring Knowledge from Discourse to Arguments: A Case Study with Scientific Abstracts
TLDR
An annotation scheme for argumentative units and relations is proposed and used to enrich an existing corpus with an argumentation layer and the feasibility of using automatically identified argumentative components and relations to predict the acceptance of papers in computer science venues is explored.
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.
ArgumenText: Argument Classification and Clustering in a Generalized Search Scenario
TLDR
This contribution outlines the major technology-related challenges and proposed solutions for the tasks of argument extraction from heterogeneous sources and argument clustering and lays out exemplary industry applications and remaining challenges.
Tree-Constrained Graph Neural Networks For Argument Mining
TLDR
An extensive experimental evaluation on a collection of sentence classification tasks conducted on several argument mining corpora is presented, showing that the proposed approach performs well with respect to state-of-the-art techniques.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
Cross-Domain Mining of Argumentative Text through Distant Supervision
TLDR
A distant supervision approach that acquires argumentative text segments automatically from online debate portals and freely provides the underlying corpus for research, showing that training on such a corpus improves the effectiveness and robustness of mining argumentativeText.
Understanding and Detecting Diverse Supporting Arguments on Controversial Issues
TLDR
Experimental results show that LambdaMART (Burges, 2010) ranker that uses features informed by argument types yields better performance than the same ranker trained without type information.
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.
Context Dependent Claim Detection
TLDR
This work formally defines the challenging task of automatic claim detection in a given context and outlines a preliminary solution, and assess its performance over annotated real world data, collected specifically for that purpose over hundreds of Wikipedia articles.
What is the Essence of a Claim? Cross-Domain Claim Identification
TLDR
While the divergent conceptualization of claims in different datasets is indeed harmful to cross-domain classification, it is shown that there are shared properties on the lexical level as well as system configurations that can help to overcome these gaps.
Neural End-to-End Learning for Computational Argumentation Mining
TLDR
This work investigates neural techniques for end-to-end computational argumentation mining and finds that jointly learning 'natural' subtasks, in a multi-task learning setup, improves performance.
Contextual LSTM (CLSTM) models for Large scale NLP tasks
TLDR
Results from experiments indicate that using both words and topics as features improves performance of the CLSTM models over baseline L STM models for these tasks, demonstrating the significant benefit of using context appropriately in natural language (NL) tasks.
Argumentation Mining on the Web from Information Seeking Perspective
TLDR
It is argued that an annotation scheme for argumentation mining is a function of the task requirements and the corpus properties and it is found that the choice of the argument components to be annotated strongly depends on the register, the length of the document, and inherently on the literary devices and structures used for expressing argumentation.
Unit Segmentation of Argumentative Texts
TLDR
This paper studies the major parameters of unit segmentation systematically, and explores the effectiveness of various features, when capturing words separately, along with their neighbors, or even along with the entire text.
SemEval-2016 Task 6: Detecting Stance in Tweets
TLDR
A shared task on detecting stance from tweets: given a tweet and a target entity (person, organization, etc.), automatic natural language systems must determine whether the tweeter is in favor of the given target, against thegiven target, or whether neither inference is likely.
...
1
2
3
4
5
...