David Schlangen

Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images

2017

Current referring expression generation systems mostly deliver their output as one-shot, written expressions. We present on-going work on incremental generation of spoken expressions referring to objects in real-world images. This approach extends upon previous work …

Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer

2021

Fabian Galetzka, Jewgeni Rose, David Schlangen, Jens Lehmann. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU

2021 · arXiv (Cornell University)

Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole, abstracting away the notion …

Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft

2024 · arXiv (Cornell University)

In the Minecraft Collaborative Building Task, two players collaborate: an Architect (A) provides instructions to a Builder (B) to assemble a specified structure using 3D blocks. In this work, we investigate the use of large …