1 |
Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning
|
|
|
|
BASE
|
|
Show details
|
|
4 |
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Algorithmus für Kreativität gesucht. Herausforderungen maschinellen Sprachverstehens ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Exploiting Background Knowledge for Argumentative Relation Classification
|
|
|
|
Abstract:
Argumentative relation classification is the task of determining the type of relation (e.g., support or attack) that holds between two argument units. Current state-of-the-art models primarily exploit surface-linguistic features including discourse markers, modals or adverbials to classify argumentative relations. However, a system that performs argument analysis using mainly rhetorical features can be easily fooled by the stylistic presentation of the argument as opposed to its content, in cases where a weak argument is concealed by strong rhetorical means. This paper explores the difficulties and the potential effectiveness of knowledge-enhanced argument analysis, with the aim of advancing the state-of-the-art in argument analysis towards a deeper, knowledge-based understanding and representation of arguments. We propose an argumentative relation classification system that employs linguistic as well as knowledge-based features, and investigate the effects of injecting background knowledge into a neural baseline model for argumentative relation classification. Starting from a Siamese neural network that classifies pairs of argument units into support vs. attack relations, we extend this system with a set of features that encode a variety of features extracted from two complementary background knowledge resources: ConceptNet and DBpedia. We evaluate our systems on three different datasets and show that the inclusion of background knowledge can improve the classification performance by considerable margins. Thus, our work offers a first step towards effective, knowledge-rich argument analysis.
|
|
Keyword:
argument classification; argument structure analysis; argumentative functions; background knowledge; commonsense knowledge relations; Data processing Computer science
|
|
URN:
urn:nbn:de:0030-drops-103723
|
|
URL: https://doi.org/10.4230/OASIcs.LDK.2019.8 https://drops.dagstuhl.de/opus/volltexte/2019/10372/
|
|
BASE
|
|
Hide details
|
|
13 |
Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Exploiting Background Knowledge for Argumentative Relation Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Exploiting background knowledge for argumentative relation classification
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|