Papers by Manfred Pinkal
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge (L18-1)
Copied to clipboard
| Challenge: | Various approaches for script knowledge extraction and processing have been proposed in recent years. |
| Approach: | They propose a dataset to evaluate natural language understanding approaches based on commonsense knowledge. |
| Outcome: | The proposed dataset provides test cases for the broader natural language understanding community. |
Multi-layer Annotation of the Rigveda (L18-1)
Copied to clipboard
| Challenge: | Using a multi-level annotation, we present a corpus of the R. GVEDA . |
| Approach: | They propose a multi-level annotation of the R . GVEDA, a Sanskrit text composed in the 2. millenium BCE, and a basic argument identification algorithm to supplement missing verb-argument links. |
| Outcome: | The proposed model replaces verb-argument links by LSTM based model . the proposed model is based on a LS-based model to supplement missing verb-al arguments. |
Semi-Supervised Clustering for Short Answer Scoring (L18-1)
Copied to clipboard
| Challenge: | Existing approaches to SAS use unsupervised clustering and have teachers label some items after clustering. |
| Approach: | They propose to use semi-supervised clustering to provide structured groups of answers in addition to a score. |
| Outcome: | The proposed method improves clustering performance from 0.504 kappa for unsupervised clustering to 0.566 kppa. |
Mapping Texts to Scripts: An Entailment Study (L18-1)
Copied to clipboard
| Challenge: | Script knowledge is crucial for text understanding systems, providing a basis for commonsense inference. |
| Approach: | They propose to map event mentions in a text to script events using crowdsourced event descriptions. |
| Outcome: | The proposed model improves the performance of text-to-script mapping systems by integrating paraphrase sets with crowdsourced event descriptions. |
Grounding Semantic Roles in Images (D18-1)
Copied to clipboard
| Challenge: | Experimental results show that visual semantic role labeling is useful for text understanding . image-based role annotations are prohibitive, but the model induces frame-semantic visual representations . |
| Approach: | They propose to train a visual semantic role labeling model without prohibitive image annotations . they render candidate participants as image regions of objects and train vSRL model which learns to ground roles in the regions which depict the corresponding participant . |
| Outcome: | The proposed model trains without prohibitive image-based role annotations without prohibiting image-related annotations. |