Search Results for author: Daniel Bauer

Found 16 papers, 1 papers with code

Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions

no code implementations16 Jun 2023 Chad DeChant, Iretiayo Akinola, Daniel Bauer

We therefore demonstrate the task of learning to summarize and answer questions about a robot agent's past actions using natural language alone.

Language Modelling Large Language Model +1

Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling

no code implementations13 Oct 2022 Aashish Arora, Harshitha Malireddi, Daniel Bauer, Asad Sayeed, Yuval Marton

Unlike previous work, our model does not require pre-training or fine-tuning on additional tasks, beyond using off-the-shelf (static or contextual) embeddings and supervision.

Multi-Task Learning Sentence

Summarizing a virtual robot's past actions in natural language

no code implementations13 Mar 2022 Chad DeChant, Daniel Bauer

We propose and demonstrate the task of giving natural language summaries of the actions of a robotic agent in a virtual environment.

Instruction Following

NLP in Human Rights Research -- Extracting Knowledge Graphs About Police and Army Units and Their Commanders

1 code implementation13 Jan 2022 Daniel Bauer, Tom Longley, Yueen Ma, Tony Wilson

In this working paper we explore the use of an NLP system to assist the work of Security Force Monitor (SFM).

Knowledge Graphs

Deep Inverse Sensor Models as Priors for evidential Occupancy Mapping

no code implementations2 Dec 2020 Daniel Bauer, Lars Kuhnert, Lutz Eckstein

In this work, we describe a novel approach to integrate deep ISMs together with geometric ISMs into the evidential occupancy mapping framework.

Autonomous Driving

Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework

no code implementations29 Mar 2019 Daniel Bauer, Lars Kuhnert, Lutz Eckstein

To perform high speed tasks, sensors of autonomous cars have to provide as much information in as few time steps as possible.

Deep, spatially coherent Occupancy Maps based on Radar Measurements

no code implementations29 Mar 2019 Daniel Bauer, Lars Kuhnert, Lutz Eckstein

One essential step to realize modern driver assistance technology is the accurate knowledge about the location of static objects in the environment.

The Dependency-Parsed FrameNet Corpus

no code implementations LREC 2012 Daniel Bauer, Hagen F{\"u}rstenau, Owen Rambow

When training semantic role labeling systems, the syntax of example sentences is of particular importance.

Dependency Parsing POS +2

Cannot find the paper you are looking for? You can Submit a new open access paper.