3 citations · 6 across the 6 of their papers we have counts for
11 papers
Domain Adaptation for Sparse-Data Settings: What Do We Gain by Not Using Bert?
Marina Sedinkina, Martin Schmitt, Hinrich Schütze
The practical success of much of NLP depends on the availability of training data. However, in real-world scenarios, training data is often scarce, not least because many applicati…
Scene Graph Generation for Better Image Captioning?
Maximilian Mozes, Martin Schmitt, Vladimir Golkov +2
We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generate…
Continuous Entailment Patterns for Lexical Inference in Context
Martin Schmitt, Hinrich Schütze
Combining a pretrained language model (PLM) with textual patterns has been shown to help in both zero- and few-shot settings. For zero-shot performance, it makes sense to design pa…
Semi-Automated Labeling of Requirement Datasets for Relation Extraction
Jeremias Bohn, Jannik Fischbach, Martin Schmitt +2
Creating datasets manually by human annotators is a laborious task that can lead to biased and inhomogeneous labels. We propose a flexible, semi-automatic framework for labeling da…
Ranking vs. Classifying: Measuring Knowledge Base Completion Quality
Marina Speranskaya, Martin Schmitt, Benjamin Roth
Knowledge base completion (KBC) methods aim at inferring missing facts from the information present in a knowledge base (KB) by estimating the likelihood of candidate facts. In the…
Position Information in Transformers: An Overview
Philipp Dufter, Martin Schmitt, Hinrich Schütze
Transformers are arguably the main workhorse in recent Natural Language Processing research. By definition a Transformer is invariant with respect to reordering of the input. Howev…