Search Results for author: Regina Barzilay

Found 108 papers, 51 papers with code

Composing Molecules with Multiple Property Constraints

no code implementations ICML 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

These rationales are identified from molecules as substructures that are likely responsible for each property of interest.

Drug Discovery

CapWAP: Image Captioning with a Purpose

no code implementations EMNLP 2020 Adam Fisch, Kenton Lee, Ming-Wei Chang, Jonathan Clark, Regina Barzilay

In this task, we use question-answer (QA) pairs{---}a natural expression of information need{---}from users, instead of reference captions, for both training and post-inference evaluation.

Image Captioning Question Answering +1

Learning to Split for Automatic Bias Detection

no code implementations28 Apr 2022 Yujia Bao, Regina Barzilay

As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection.

Bias Detection

Conformal Prediction Sets with Limited False Positives

1 code implementation15 Feb 2022 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

We propose to trade coverage for a notion of precision by enforcing that the presence of incorrect candidates in the predicted conformal sets (i. e., the total number of false positives) is bounded according to a user-specified tolerance.

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

1 code implementation7 Feb 2022 Hannes Stärk, Octavian-Eugen Ganea, Lagnajit Pattanaik, Regina Barzilay, Tommi Jaakkola

Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery.

Drug Discovery

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

1 code implementation ICLR 2022 Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne, Yatao Bian, Regina Barzilay, Tommi Jaakkola, Andreas Krause

Protein complex formation is a central problem in biology, being involved in most of the cell's processes, and essential for applications, e. g. drug design or protein engineering.

Graph Matching Translation

Fragment-based Sequential Translation for Molecular Optimization

no code implementations NeurIPS Workshop AI4Scien 2021 Benson Chen, Xiang Fu, Regina Barzilay, Tommi Jaakkola

Equipped with the learned fragment vocabulary, we propose Fragment-based Sequential Translation (FaST), which learns a reinforcement learning (RL) policy to iteratively translate model-discovered molecules into increasingly novel molecules while satisfying desired properties.

Drug Discovery reinforcement-learning +1

Crystal Diffusion Variational Autoencoder for Periodic Material Generation

1 code implementation ICLR 2022 Tian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola

Generating the periodic structure of stable materials is a long-standing challenge for the material design community.

Translation

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

no code implementations ICLR 2022 Wengong Jin, Jeremy Wohlwend, Regina Barzilay, Tommi Jaakkola

In this paper, we propose a generative model to automatically design the CDRs of antibodies with enhanced binding specificity or neutralization capabilities.

Trading Coverage for Precision: Conformal Prediction with Limited False Discoveries

no code implementations29 Sep 2021 Adam Fisch, Tal Schuster, Tommi S. Jaakkola, Regina Barzilay

In this paper, we develop a new approach to conformal prediction in which we aim to output a precise set of promising prediction candidates that is guaranteed to contain a limited number of incorrect answers.

Drug Discovery

Text Style Transfer with Confounders

no code implementations29 Sep 2021 Tianxiao Shen, Regina Barzilay, Tommi S. Jaakkola

Existing methods for style transfer operate either with paired sentences or distributionally matched corpora which differ only in the desired style.

Style Transfer Text Style Transfer

Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis

no code implementations CVPR 2021 Karren Yang, Samuel Goldman, Wengong Jin, Alex X. Lu, Regina Barzilay, Tommi Jaakkola, Caroline Uhler

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.

Contrastive Learning Image Generation

Learning Stable Classifiers by Transferring Unstable Features

no code implementations15 Jun 2021 Yujia Bao, Shiyu Chang, Regina Barzilay

Specifically, we derive a representation that encodes the unstable features by contrasting different data environments in the source task.

Transfer Learning

Learning Graph Models for Template-Free Retrosynthesis

no code implementations arXiv 2021 Vignesh Ram Somnath, Charlotte Bunne, Connor W. Coley, Andreas Krause, Regina Barzilay

Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule.

Single-step retrosynthesis

Nutri-bullets Hybrid: Consensual Multi-document Summarization

no code implementations NAACL 2021 Darsh Shah, Lili Yu, Tao Lei, Regina Barzilay

We present a method for generating comparative summaries that highlight similarities and contradictions in input documents.

Document Summarization Language Modelling +2

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers

1 code implementation26 May 2021 Yujia Bao, Shiyu Chang, Regina Barzilay

In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes.

Image Classification Text Classification

Consistent Accelerated Inference via Confident Adaptive Transformers

no code implementations EMNLP 2021 Tal Schuster, Adam Fisch, Tommi Jaakkola, Regina Barzilay

In this work, we present CATs -- Confident Adaptive Transformers -- in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence.

Generating Related Work

no code implementations18 Apr 2021 Darsh J Shah, Regina Barzilay

Communicating new research ideas involves highlighting similarities and differences with past work.

Document Summarization Multi-Document Summarization

Nutribullets Hybrid: Multi-document Health Summarization

2 code implementations8 Apr 2021 Darsh J Shah, Lili Yu, Tao Lei, Regina Barzilay

We present a method for generating comparative summaries that highlights similarities and contradictions in input documents.

Language Modelling Text Infilling

Few-shot Conformal Prediction with Auxiliary Tasks

1 code implementation17 Feb 2021 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

We develop a novel approach to conformal prediction when the target task has limited data available for training.

Drug Discovery Meta-Learning

Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models

no code implementations9 Nov 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

Drug combinations play an important role in therapeutics due to its better efficacy and reduced toxicity.

CapWAP: Captioning with a Purpose

1 code implementation9 Nov 2020 Adam Fisch, Kenton Lee, Ming-Wei Chang, Jonathan H. Clark, Regina Barzilay

In this task, we use question-answer (QA) pairs---a natural expression of information need---from users, instead of reference captions, for both training and post-inference evaluation.

Image Captioning Question Answering +1

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

1 code implementation21 Oct 2020 Jiaming Luo, Frederik Hartmann, Enrico Santus, Yuan Cao, Regina Barzilay

We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian).

Decipherment

Efficient Conformal Prediction via Cascaded Inference with Expanded Admission

1 code implementation ICLR 2021 Adam Fisch, Tal Schuster, Tommi Jaakkola, Regina Barzilay

This set is guaranteed to contain a correct answer with high probability, and is well-suited for many open-ended classification tasks.

Drug Discovery

Improved Conditional Flow Models for Molecule to Image Synthesis

1 code implementation15 Jun 2020 Karren Yang, Samuel Goldman, Wengong Jin, Alex Lu, Regina Barzilay, Tommi Jaakkola, Caroline Uhler

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development.

Contrastive Learning Image Generation

Learning Graph Models for Retrosynthesis Prediction

no code implementations NeurIPS 2021 Vignesh Ram Somnath, Charlotte Bunne, Connor W. Coley, Andreas Krause, Regina Barzilay

Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule.

Optimal Transport Graph Neural Networks

2 code implementations8 Jun 2020 Benson Chen, Gary Bécigneul, Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola

Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information.

Drug Discovery Graph Regression +1

Enforcing Predictive Invariance across Structured Biomedical Domains

no code implementations6 Jun 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

We evaluate our method on multiple applications: molecular property prediction, protein homology and stability prediction and show that RGM significantly outperforms previous state-of-the-art baselines.

Domain Generalization Molecular Property Prediction

Uncertainty Quantification Using Neural Networks for Molecular Property Prediction

1 code implementation20 May 2020 Lior Hirschfeld, Kyle Swanson, Kevin Yang, Regina Barzilay, Connor W. Coley

While we believe these results show that existing UQ methods are not sufficient for all common use-cases and demonstrate the benefits of further research, we conclude with a practical recommendation as to which existing techniques seem to perform well relative to others.

Drug Discovery Experimental Design +1

Adaptive Invariance for Molecule Property Prediction

no code implementations5 May 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

Effective property prediction methods can help accelerate the search for COVID-19 antivirals either through accurate in-silico screens or by effectively guiding on-going at-scale experimental efforts.

Transfer Learning

Improving Molecular Design by Stochastic Iterative Target Augmentation

2 code implementations ICML 2020 Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay, Tommi Jaakkola

The property predictor is then used as a likelihood model for filtering candidate structures from the generative model.

Program Synthesis

Blank Language Models

1 code implementation EMNLP 2020 Tianxiao Shen, Victor Quach, Regina Barzilay, Tommi Jaakkola

We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks.

Ancient Text Restoration Language Modelling +1

Multi-Objective Molecule Generation using Interpretable Substructures

2 code implementations8 Feb 2020 Wengong Jin, Regina Barzilay, Tommi Jaakkola

These rationales are identified from molecules as substructures that are likely responsible for each property of interest.

Drug Discovery

Generative Models for Graph-Based Protein Design

1 code implementation ICLR Workshop DeepGenStruct 2019 John Ingraham, Vikas Garg, Regina Barzilay, Tommi Jaakkola

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice.

Protein Folding

Capturing Greater Context for Question Generation

1 code implementation22 Oct 2019 Luu Anh Tuan, Darsh J Shah, Regina Barzilay

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension.

Question Answering Question Generation +1

Automatic Fact-guided Sentence Modification

3 code implementations30 Sep 2019 Darsh J Shah, Tal Schuster, Regina Barzilay

This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document.

Fact Checking

Iterative Target Augmentation for Effective Conditional Generation

no code implementations25 Sep 2019 Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay, Tommi Jaakkola

Many challenging prediction problems, from molecular optimization to program synthesis, involve creating complex structured objects as outputs.

Program Synthesis

Denoising Improves Latent Space Geometry in Text Autoencoders

no code implementations25 Sep 2019 Tianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi Jaakkola

Neural language models have recently shown impressive gains in unconditional text generation, but controllable generation and manipulation of text remain challenging.

Denoising Text Generation

The Limitations of Stylometry for Detecting Machine-Generated Fake News

no code implementations CL 2020 Tal Schuster, Roei Schuster, Darsh J Shah, Regina Barzilay

Recent developments in neural language models (LMs) have raised concerns about their potential misuse for automatically spreading misinformation.

Fake News Detection Language Modelling +1

Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B

1 code implementation ACL 2019 Jiaming Luo, Yuan Cao, Regina Barzilay

In this paper we propose a novel neural approach for automatic decipherment of lost languages.

Decipherment

Hierarchical Graph-to-Graph Translation for Molecules

1 code implementation11 Jun 2019 Wengong Jin, Regina Barzilay, Tommi Jaakkola

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties.

Drug Discovery Graph-To-Graph Translation +1

Educating Text Autoencoders: Latent Representation Guidance via Denoising

3 code implementations ICML 2020 Tianxiao Shen, Jonas Mueller, Regina Barzilay, Tommi Jaakkola

We prove that this simple modification guides the latent space geometry of the resulting model by encouraging the encoder to map similar texts to similar latent representations.

Denoising Style Transfer +1

Path-Augmented Graph Transformer Network

2 code implementations29 May 2019 Benson Chen, Regina Barzilay, Tommi Jaakkola

Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN).

Molecular Property Prediction

Learning Multimodal Graph-to-Graph Translation for Molecule Optimization

no code implementations ICLR 2019 Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

We evaluate our model on multiple molecule optimization tasks and show that our model outperforms previous state-of-the-art baselines by a significant margin.

Graph-To-Graph Translation Translation

Analyzing Learned Molecular Representations for Property Prediction

6 code implementations2 Apr 2019 Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay

In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.

Molecular Property Prediction

Inferring Which Medical Treatments Work from Reports of Clinical Trials

2 code implementations NAACL 2019 Eric Lehman, Jay DeYoung, Regina Barzilay, Byron C. Wallace

In this paper, we present a new task and corpus for making this unstructured evidence actionable.

Learning Multimodal Graph-to-Graph Translation for Molecular Optimization

5 code implementations3 Dec 2018 Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines.

Graph-To-Graph Translation Translation

GraphIE: A Graph-Based Framework for Information Extraction

2 code implementations NAACL 2019 Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, Regina Barzilay

Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies.

Deriving Machine Attention from Human Rationales

3 code implementations EMNLP 2018 Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay

Attention-based models are successful when trained on large amounts of data.

The Three Pillars of Machine Programming

no code implementations20 Mar 2018 Justin Gottschlich, Armando Solar-Lezama, Nesime Tatbul, Michael Carbin, Martin Rinard, Regina Barzilay, Saman Amarasinghe, Joshua B. Tenenbaum, Tim Mattson

In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research.

Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

1 code implementation NeurIPS 2017 Wengong Jin, Connor W. Coley, Regina Barzilay, Tommi Jaakkola

The prediction of organic reaction outcomes is a fundamental problem in computational chemistry.

Grounding Language for Transfer in Deep Reinforcement Learning

1 code implementation1 Aug 2017 Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL).

reinforcement-learning

Representation Learning for Grounded Spatial Reasoning

1 code implementation TACL 2018 Michael Janner, Karthik Narasimhan, Regina Barzilay

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment.

reinforcement-learning Representation Learning

Style Transfer from Non-Parallel Text by Cross-Alignment

12 code implementations NeurIPS 2017 Tianxiao Shen, Tao Lei, Regina Barzilay, Tommi Jaakkola

We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

Decipherment Machine Translation +3

Deriving Neural Architectures from Sequence and Graph Kernels

no code implementations ICML 2017 Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola

The design of neural architectures for structured objects is typically guided by experimental insights rather than a formal process.

Graph Regression Language Modelling

Unsupervised Learning of Morphological Forests

no code implementations TACL 2017 Jiaming Luo, Karthik Narasimhan, Regina Barzilay

This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary.

Aspect-augmented Adversarial Networks for Domain Adaptation

1 code implementation TACL 2017 Yuan Zhang, Regina Barzilay, Tommi Jaakkola

We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain.

Domain Adaptation General Classification +1

sk_p: a neural program corrector for MOOCs

no code implementations11 Jul 2016 Yewen Pu, Karthik Narasimhan, Armando Solar-Lezama, Regina Barzilay

We present a novel technique for automatic program correction in MOOCs, capable of fixing both syntactic and semantic errors without manual, problem specific correction strategies.

Machine Translation Translation

Rationalizing Neural Predictions

3 code implementations EMNLP 2016 Tao Lei, Regina Barzilay, Tommi Jaakkola

Our approach combines two modular components, generator and encoder, which are trained to operate well together.

Sentiment Analysis

Semi-supervised Question Retrieval with Gated Convolutions

1 code implementation NAACL 2016 Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Katerina Tymoshenko, Alessandro Moschitti, Lluis Marquez

Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions.

Question Answering

Molding CNNs for text: non-linear, non-consecutive convolutions

2 code implementations EMNLP 2015 Tao Lei, Regina Barzilay, Tommi Jaakkola

Moreover, we extend the n-gram convolution to non-consecutive words to recognize patterns with intervening words.

General Classification Sentiment Analysis

Language Understanding for Text-based Games Using Deep Reinforcement Learning

3 code implementations EMNLP 2015 Karthik Narasimhan, tejas kulkarni, Regina Barzilay

We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations.

reinforcement-learning text-based games

An Unsupervised Method for Uncovering Morphological Chains

1 code implementation TACL 2015 Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words.

Morphological Analysis

Automatic Aggregation by Joint Modeling of Aspects and Values

no code implementations23 Jan 2014 Christina Sauper, Regina Barzilay

We test our model on two tasks, joint aspect identification and sentiment analysis on a set of Yelp reviews and aspect identification alone on a set of medical summaries.

Sentiment Analysis

Learning to Win by Reading Manuals in a Monte-Carlo Framework

no code implementations18 Jan 2014 S. R. K. Branavan, David Silver, Regina Barzilay

In this paper, we present an approach to language grounding which automatically interprets text in the context of a complex control application, such as a game, and uses domain knowledge extracted from the text to improve control performance.

Learning Document-Level Semantic Properties from Free-Text Annotations

no code implementations15 Jan 2014 S. R. K. Branavan, Harr Chen, Jacob Eisenstein, Regina Barzilay

The paraphrase structure is linked with a latent topic model of the review texts, enabling the system to predict the properties of unannotated documents and to effectively aggregate the semantic properties of multiple reviews.

Content Modeling Using Latent Permutations

no code implementations15 Jan 2014 Harr Chen, S. R. K. Branavan, Regina Barzilay, David R. Karger

We present a novel Bayesian topic model for learning discourse-level document structure.

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