activity
20172023
most citedRanking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs

7 citations · 22 across the 12 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

cs.CL20196 cited

Implicit Knowledge in Argumentative Texts: An Annotated Corpus

Maria Becker, Katharina Korfhage, Anette Frank

When speaking or writing, people omit information that seems clear and evident, such that only part of the message is expressed in words. Especially in argumentative texts it is ve…

cs.CL2019

Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling

Angel Daza, Anette Frank

We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language.…

cs.CL2019

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

Todor Mihaylov, Anette Frank

In this work, we propose to use linguistic annotations as a basis for a \textit{Discourse-Aware Semantic Self-Attention} encoder that we employ for reading comprehension on long na…

cs.CL2019

Dissecting Content and Context in Argumentative Relation Analysis

Juri Opitz, Anette Frank

When assessing relations between argumentative units (e.g., support or attack), computational systems often exploit disclosing indicators or markers that are not part of elementary…

cs.CL2019

Assessing the Difficulty of Classifying ConceptNet Relations in a Multi-Label Classification Setting

Maria Becker, Michael Staniek, Vivi Nastase +1

Commonsense knowledge relations are crucial for advanced NLU tasks. We examine the learnability of such relations as represented in CONCEPTNET, taking into account their specific p…

cs.CL20191 cited

Automatic Accuracy Prediction for AMR Parsing

Juri Opitz, Anette Frank

Abstract Meaning Representation (AMR) represents sentences as directed, acyclic and rooted graphs, aiming at capturing their meaning in a machine readable format. AMR parsing conve…