Search Results for author: Hendrik Strobelt

Found 27 papers, 15 papers with code

LMdiff: A Visual Diff Tool to Compare Language Models

1 code implementation EMNLP (ACL) 2021 Hendrik Strobelt, Benjamin Hoover, Arvind Satyanarayan, Sebastian Gehrmann

While different language models are ubiquitous in NLP, it is hard to contrast their outputs and identify which contexts one can handle better than the other.

GenNI: Human-AI Collaboration for Data-Backed Text Generation

no code implementations19 Oct 2021 Hendrik Strobelt, Jambay Kinley, Robert Krueger, Johanna Beyer, Hanspeter Pfister, Alexander M. Rush

These controls allow users to globally constrain model generations, without sacrificing the representation power of the deep learning models.

Text Generation

Beyond Faithfulness: A Framework to Characterize and Compare Saliency Methods

no code implementations29 Sep 2021 Angie Boggust, Harini Suresh, Hendrik Strobelt, John Guttag, Arvind Satyanarayan

Saliency methods calculate how important each input feature is to a machine learning model’s prediction, and are commonly used to understand model reasoning.

Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior

1 code implementation20 Jul 2021 Angie Boggust, Benjamin Hoover, Arvind Satyanarayan, Hendrik Strobelt

Saliency methods -- techniques to identify the importance of input features on a model's output -- are a common step in understanding neural network behavior.

FairyTailor: A Multimodal Generative Framework for Storytelling

1 code implementation13 Jul 2021 Eden Bensaid, Mauro Martino, Benjamin Hoover, Jacob Andreas, Hendrik Strobelt

Natural language generation (NLG) for storytelling is especially challenging because it requires the generated text to follow an overall theme while remaining creative and diverse to engage the reader.

Story Generation

Latent Compass: Creation by Navigation

no code implementations20 Dec 2020 Sarah Schwettmann, Hendrik Strobelt, Mauro Martino

Our approach puts creators in the discovery loop during real-time tool use, in order to identify directions that are perceptually meaningful to them, and generate interpretable image translations along those directions.

Image Manipulation

Understanding the Role of Individual Units in a Deep Neural Network

2 code implementations10 Sep 2020 David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza, Bolei Zhou, Antonio Torralba

Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.

Image Classification Image Generation +1

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models

1 code implementation ACL 2020 Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann

Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism.

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models

no code implementations NeurIPS 2020 Vijil Chenthamarakshan, Payel Das, Samuel C. Hoffman, Hendrik Strobelt, Inkit Padhi, Kar Wai Lim, Benjamin Hoover, Matteo Manica, Jannis Born, Teodoro Laino, Aleksandra Mojsilovic

CogMol also includes insilico screening for assessing toxicity of parent molecules and their metabolites with a multi-task toxicity classifier, synthetic feasibility with a chemical retrosynthesis predictor, and target structure binding with docking simulations.

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models

1 code implementation11 Oct 2019 Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann

We present exBERT, an interactive tool named after the popular BERT language model, that provides insights into the meaning of the contextual representations by matching a human-specified input to similar contexts in a large annotated dataset.

Language Modelling

ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion

no code implementations2 Oct 2019 Andreas Hinterreiter, Peter Ruch, Holger Stitz, Martin Ennemoser, Jürgen Bernard, Hendrik Strobelt, Marc Streit

The confusion matrix is an established way for visualizing these class errors, but it was not designed with temporal or comparative analysis in mind.

Active Learning Model Selection +1

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures

1 code implementation30 Jul 2019 Dylan Cashman, Adam Perer, Remco Chang, Hendrik Strobelt

In this paper, we present Rapid Exploration of Model Architectures and Parameters, or REMAP, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures.

Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection

no code implementations ICLR Workshop DeepGenStruct 2019 Tom Sercu, Sebastian Gehrmann, Hendrik Strobelt, Payel Das, Inkit Padhi, Cicero dos Santos, Kahini Wadhawan, Vijil Chenthamarakshan

We present the pipeline in an interactive visual tool to enable the exploration of the metrics, analysis of the learned latent space, and selection of the best model for a given task.

Model Selection

On the Units of GANs (Extended Abstract)

no code implementations29 Jan 2019 David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba

We quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output.

Progressive Data Science: Potential and Challenges

no code implementations19 Dec 2018 Cagatay Turkay, Nicola Pezzotti, Carsten Binnig, Hendrik Strobelt, Barbara Hammer, Daniel A. Keim, Jean-Daniel Fekete, Themis Palpanas, Yunhai Wang, Florin Rusu

We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.

Debugging Sequence-to-Sequence Models with Seq2Seq-Vis

no code implementations WS 2018 Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, Alex Rush, er

Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks.


Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

1 code implementation25 Apr 2018 Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, Alexander M. Rush

In this work, we present a visual analysis tool that allows interaction with a trained sequence-to-sequence model through each stage of the translation process.


LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks

1 code implementation23 Jun 2016 Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister, Alexander M. Rush

In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics.

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