Search Results for author:
Found 10 papers, 8 papers with code
TUDa at WMT21: Sentence-Level Direct Assessment with Adapters
This paper presents our submissions to the WMT2021 Shared Task on Quality Estimation, Task 1 Sentence-Level Direct Assessment.
InstructIR: High-Quality Image Restoration Following Human Instructions
All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model.
mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs
To this end, we \textit{re-align} an image encoder previously tuned to an English LLM to a new, multilingual LLM -- for this, we leverage multilingual data from a mix of vision-and-language tasks, which we obtain by machine-translating high-quality English data to 95 languages.
Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
We evaluate 8 different publicly available multilingual CLIP models on zero-shot image classification (ZS-IC) for each of the 92 Babel-ImageNet languages, demonstrating a significant gap between English ImageNet performance and that of high-resource languages (e. g., German or Chinese), and an even bigger gap for low-resource languages (e. g., Sinhala or Lao).
One does not fit all! On the Complementarity of Vision Encoders for Vision and Language Tasks
While many VEs -- of different architectures, trained on different data and objectives -- are publicly available, they are not designed for the downstream V+L tasks.
UKP-SQUARE: An Online Platform for Question Answering Research
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e. g., extractive, abstractive), require different model architectures (e. g., generative, discriminative), and setups (e. g., with or without retrieval).
xGQA: Cross-Lingual Visual Question Answering
In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task.
TWEAC: Transformer with Extendable QA Agent Classifiers
We argue that there exist a wide range of specialized QA agents in literature.
Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image.
AdapterDrop: On the Efficiency of Adapters in Transformers
Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements.
