• Publications
  • Influence
Computational Argumentation Quality Assessment in Natural Language
TLDR
This paper presents the first holistic work on computational argumentation quality in natural language. Expand
  • 68
  • 18
  • PDF
Collective Classification for Fine-grained Information Status
TLDR
We add a fine-grained information status layer to the Wall Street Journal portion of the OntoNotes corpus. Expand
  • 38
  • 11
  • PDF
Global Inference for Bridging Anaphora Resolution
TLDR
We present the first work on antecedent selection for bridging resolution without restrictions on anaphor or relation types and show that the variety of bridging anaphora is much higher than reported previously. Expand
  • 42
  • 7
  • PDF
A Rule-Based System for Unrestricted Bridging Resolution: Recognizing Bridging Anaphora and Finding Links to Antecedents
TLDR
We propose a rule-based approach for the challenging task of unrestricted bridging resolution, where bridging anaphors are not limited to definite NPs and semantic relations between anaphor and their antecedents are not restricted to meronymic relations. Expand
  • 22
  • 5
  • PDF
Will it Blend? Blending Weak and Strong Labeled Data in a Neural Network for Argumentation Mining
TLDR
We propose a methodology to blend high quality but scarce strong labeled data with noisy but abundant weak labeled data during the training of neural networks, and show the advantages of the blending scheme. Expand
  • 22
  • 4
  • PDF
Cascading Collective Classification for Bridging Anaphora Recognition using a Rich Linguistic Feature Set
TLDR
We develop linguistically motivated discourse structure, lexico-semantic and genericity detection features and integrate these into a cascaded minority preference algorithm that models bridging recognition as a subtask of learning finegrained information status (IS). Expand
  • 17
  • 3
  • PDF
A Deterministic Algorithm for Bridging Anaphora Resolution
TLDR
We create new word embeddings (embeddings_bridging) to represent the meaning of an NP beyond its head easily. Expand
  • 6
  • 3
  • PDF
Argumentation Quality Assessment: Theory vs. Practice
TLDR
Argumentation quality is viewed differently in argumentation theory and in practical assessment approaches. Expand
  • 33
  • 2
  • PDF
Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction
TLDR
We build two datasets and develop a framework (TDMS-IE) aimed at automatically extracting task, dataset, metric and score from NLP papers, towards the automatic construction of leaderboards. Expand
  • 14
  • 2
  • PDF
Unrestricted Bridging Resolution
TLDR
We investigate the phenomenon of bridging anaphors that are not coreferent but instead linked via associative relations to the antecedent. Expand
  • 13
  • 2
  • PDF