Search Results for author:
Found 274 papers, 134 papers with code
Understanding Dropout: Training Multi-Layer Perceptrons with Auxiliary Independent Stochastic Neurons
In this paper, a simple, general method of adding auxiliary stochastic neurons to a multi-layer perceptron is proposed.
Classifying and Visualizing Motion Capture Sequences using Deep Neural Networks
The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition.
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks.
Bounding the Test Log-Likelihood of Generative Models
Several interesting generative learning algorithms involve a complex probability distribution over many random variables, involving intractable normalization constants or latent variable normalization.
How to Construct Deep Recurrent Neural Networks
Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurrent layers to build a deep RNN (Schmidhuber, 1992; El Hihi and Bengio, 1996).
On the Number of Linear Regions of Deep Neural Networks
We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions that they have.
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN).
Ranked #47 on
Machine Translation
on WMT2014 English-French
Iterative Neural Autoregressive Distribution Estimator (NADE-k)
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #7 on
Image Generation
on Binarized MNIST
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such minimizations, and it is often thought that a main source of difficulty for these local methods to find the global minimum is the proliferation of local minima with much higher error than the global minimum.
Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning
Conditional computation has been proposed as a way to increase the capacity of a deep neural network without increasing the amount of computation required, by activating some parameters and computation "on-demand", on a per-example basis.
Neural Machine Translation by Jointly Learning to Align and Translate
Neural machine translation is a recently proposed approach to machine translation.
Ranked #4 on
Dialogue Generation
on Persona-Chat
(using extra training data)
On the Equivalence Between Deep NADE and Generative Stochastic Networks
Orderless NADEs are trained based on a criterion that stochastically maximizes $P(\mathbf{x})$ with all possible orders of factorizations.
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems.
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder--Decoder and a newly proposed gated recursive convolutional neural network.
Not All Neural Embeddings are Born Equal
Neural language models learn word representations that capture rich linguistic and conceptual information.
Iterative Neural Autoregressive Distribution Estimator NADE-k
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #8 on
Image Generation
on Binarized MNIST
End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes.
On Using Very Large Target Vocabulary for Neural Machine Translation
The models trained by the proposed approach are empirically found to outperform the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs).
Ranked #10 on
Music Modeling
on JSB Chorales
Embedding Word Similarity with Neural Machine Translation
Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural language model.
Gated Feedback Recurrent Neural Networks
In this work, we propose a novel recurrent neural network (RNN) architecture.
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images.
Describing Videos by Exploiting Temporal Structure
In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.
On Using Monolingual Corpora in Neural Machine Translation
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation.
Learning to Understand Phrases by Embedding the Dictionary
Distributional models that learn rich semantic word representations are a success story of recent NLP research.
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks.
Ranked #34 on
Image Classification
on MNIST
Attention-Based Models for Speech Recognition
Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration.
Ranked #17 on
Speech Recognition
on TIMIT
Describing Multimedia Content using Attention-based Encoder--Decoder Networks
Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the observed target is composed of multiple random variables that have a rich joint distribution, given the input.
Larger-Context Language Modelling
In the experi- ments, we evaluate the proposed approach while varying the number of context sentences and observe that the proposed late fusion is superior to the usual way of incorporating additional inputs to the LSTM.
Oracle performance for visual captioning
The task of associating images and videos with a natural language description has attracted a great amount of attention recently.
Iterative Refinement of the Approximate Posterior for Directed Belief Networks
Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods.
A Controller-Recognizer Framework: How necessary is recognition for control?
Recently there has been growing interest in building active visual object recognizers, as opposed to the usual passive recognizers which classifies a given static image into a predefined set of object categories.
First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks
In this paper, we propose and study a novel visual object tracking approach based on convolutional networks and recurrent networks.
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features.
Ranked #18 on
Semantic Segmentation
on CamVid
Natural Language Understanding with Distributed Representation
This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015.
Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
We propose multi-way, multilingual neural machine translation.
Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
Document classification tasks were primarily tackled at word level.
End-to-End Goal-Driven Web Navigation
We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments.
Learning Distributed Representations of Sentences from Unlabelled Data
Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data.
Ranked #16 on
Subjectivity Analysis
on SUBJ
A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation.
Ranked #3 on
Machine Translation
on WMT2015 English-German
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e. g., attention mechanism), learning algorithms (e. g., scheduled sampling and sequence-level training) and novel applications (e. g., image/video description generation, speech recognition, etc.)
Query-Efficient Imitation Learning for End-to-End Autonomous Driving
A policy function trained in this way however is known to suffer from unexpected behaviours due to the mismatch between the states reachable by the reference policy and trained policy functions.
Recurrent Neural Networks for Multivariate Time Series with Missing Values
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.
Ranked #4 on
Multivariate Time Series Imputation
on MuJoCo
Multivariate Time Series Forecasting
Multivariate Time Series Imputation
+3
Gated Word-Character Recurrent Language Model
We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs.
Can neural machine translation do simultaneous translation?
We investigate the potential of attention-based neural machine translation in simultaneous translation.
First Result on Arabic Neural Machine Translation
Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation.
Zero-Resource Translation with Multi-Lingual Neural Machine Translation
In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, mulitlingual neural machine translate that enables zero-resource machine translation.
A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
However, there is no parallel training data available between X and Y but, training data is available between X & Z and Z & Y (as is often the case in many real world applications).
Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRUcontroller.
Ranked #5 on
Question Answering
on bAbi
Context-Dependent Word Representation for Neural Machine Translation
Based on this observation, in this paper we propose to contextualize the word embedding vectors using a nonlinear bag-of-words representation of the source sentence.
Towards Music Captioning: Generating Music Playlist Descriptions
Descriptions are often provided along with recommendations to help users' discovery.
Convolutional Recurrent Neural Networks for Music Classification
We introduce a convolutional recurrent neural network (CRNN) for music tagging.
Learning to Translate in Real-time with Neural Machine Translation
Translating in real-time, a. k. a.
Fully Character-Level Neural Machine Translation without Explicit Segmentation
We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of BLEU score and human judgment.
Spatio-temporal Dynamics of Intrinsic Networks in Functional Magnetic Imaging Data Using Recurrent Neural Networks
We introduce a novel recurrent neural network (RNN) approach to account for temporal dynamics and dependencies in brain networks observed via functional magnetic resonance imaging (fMRI).
Semantic Noise Modeling for Better Representation Learning
From the base model, we introduce a semantic noise modeling method which enables class-conditional perturbation on latent space to enhance the representational power of learned latent feature.
QCD-Aware Recursive Neural Networks for Jet Physics
Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images.
Trainable Greedy Decoding for Neural Machine Translation
Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding objective.
Learning to Parse and Translate Improves Neural Machine Translation
There has been relatively little attention to incorporating linguistic prior to neural machine translation.
Boundary-Seeking Generative Adversarial Networks
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
Nematus: a Toolkit for Neural Machine Translation
We present Nematus, a toolkit for Neural Machine Translation.
High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks
In our work, we propose to use a multi-view deep convolutional neural network that handles a set of high-resolution medical images.
Transfer learning for music classification and regression tasks
In this paper, we present a transfer learning approach for music classification and regression tasks.
Task-Oriented Query Reformulation with Reinforcement Learning
In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned.
Does Neural Machine Translation Benefit from Larger Context?
We propose a neural machine translation architecture that models the surrounding text in addition to the source sentence.
SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering.
Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks
However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice.
Search Engine Guided Non-Parametric Neural Machine Translation
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training.
Emergent Communication in a Multi-Modal, Multi-Step Referential Game
Inspired by previous work on emergent communication in referential games, we propose a novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information exchange is bidirectional and of arbitrary duration.
The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging
The results highlight several important aspects of music tagging and neural networks.
Zero-Shot Transfer Learning for Event Extraction
Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort.
Strawman: an Ensemble of Deep Bag-of-Ngrams for Sentiment Analysis
This paper describes a builder entry, named "strawman", to the sentence-level sentiment analysis task of the "Build It, Break It" shared task of the First Workshop on Building Linguistically Generalizable NLP Systems.
Neural Machine Translation for Cross-Lingual Pronoun Prediction
In this paper we present our systems for the DiscoMT 2017 cross-lingual pronoun prediction shared task.
A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks.
A Tutorial on Deep Learning for Music Information Retrieval
Following their success in Computer Vision and other areas, deep learning techniques have recently become widely adopted in Music Information Retrieval (MIR) research.
Attention-based Mixture Density Recurrent Networks for History-based Recommendation
The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user.
Graph Convolutional Networks for Classification with a Structured Label Space
It is a usual practice to ignore any structural information underlying classes in multi-class classification.
Emergent Translation in Multi-Agent Communication
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans.
Unsupervised Neural Machine Translation
In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs.
Ranked #6 on
Machine Translation
on WMT2015 English-German
Breast density classification with deep convolutional neural networks
Breast density classification is an essential part of breast cancer screening.
Loss Functions for Multiset Prediction
In this paper, we propose a novel multiset loss function by viewing this problem from the perspective of sequential decision making.
Saliency-based Sequential Image Attention with Multiset Prediction
Humans process visual scenes selectively and sequentially using attention.
Simple Nearest Neighbor Policy Method for Continuous Control Tasks
As this policy does not require any optimization, it allows us to investigate the underlying difficulty of a task without being distracted by optimization difficulty of a learning algorithm.
Boundary Seeking GANs
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
We propose a conditional non-autoregressive neural sequence model based on iterative refinement.
Ranked #5 on
Machine Translation
on IWSLT2015 German-English
Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm.
Controlling Decoding for More Abstractive Summaries with Copy-Based Networks
Attention-based neural abstractive summarization systems equipped with copy mechanisms have shown promising results.
Fine-Grained Attention Mechanism for Neural Machine Translation
Neural machine translation (NMT) has been a new paradigm in machine translation, and the attention mechanism has become the dominant approach with the state-of-the-art records in many language pairs.
Training a Ranking Function for Open-Domain Question Answering
In recent years, there have been amazing advances in deep learning methods for machine reading.
Vehicle Communication Strategies for Simulated Highway Driving
Interest in emergent communication has recently surged in Machine Learning.
Dynamic Meta-Embeddings for Improved Sentence Representations
While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves.
Ranked #52 on
Natural Language Inference
on SNLI
A Stable and Effective Learning Strategy for Trainable Greedy Decoding
Beam search is a widely used approximate search strategy for neural network decoders, and it generally outperforms simple greedy decoding on tasks like machine translation.
Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages.
Conditional molecular design with deep generative models
Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently.
Classifier-agnostic saliency map extraction
To address this problem, we propose classifier-agnostic saliency map extraction, which finds all parts of the image that any classifier could use, not just one given in advance.
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling.
Learning Distributed Representations from Reviews for Collaborative Filtering
However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model's ability to act as a regularizer of the product representations.
Code-Switched Named Entity Recognition with Embedding Attention
We describe our work for the CALCS 2018 shared task on named entity recognition on code-switched data.
Backplay: "Man muss immer umkehren"
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
Grammar Induction with Neural Language Models: An Unusual Replication
A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree structure.
Jump to better conclusions: SCAN both left and right
Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple commands paired with action sequences and is intended to test the strong generalization abilities of recurrent sequence-to-sequence models.
Learning with Reflective Likelihoods
Furthermore, the reflective likelihood objective prevents posterior collapse when used to train stochastic auto-encoders with amortized inference.
Countering Language Drift via Grounding
While reinforcement learning (RL) shows a lot of promise for natural language processing—e. g.
Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep learning
We empirically verify our result using deep convolutional networks and observe a higher correlation between the gradient stochasticity and the proposed directional uniformity than that against the gradient norm stochasticity, suggesting that the directional statistics of minibatch gradients is a major factor behind SGD.
Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop
Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty.
Importance of Search and Evaluation Strategies in Neural Dialogue Modeling
We investigate the impact of search strategies in neural dialogue modeling.
Passage Re-ranking with BERT
Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference.
Ranked #3 on
Passage Re-Ranking
on MS MARCO
(using extra training data)
Emergent Linguistic Phenomena in Multi-Agent Communication Games
In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning.
Insertion-based Decoding with automatically Inferred Generation Order
Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal.
Non-Monotonic Sequential Text Generation
Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right.
BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model
We show that BERT (Devlin et al., 2018) is a Markov random field language model.
Augmentation for small object detection
We evaluate different pasting augmentation strategies, and ultimately, we achieve 9. 7\% relative improvement on the instance segmentation and 7. 1\% on the object detection of small objects, compared to the current state of the art method on
Continual Learning via Neural Pruning
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification.
Context-Aware Learning for Neural Machine Translation
By comparing performance using actual and random contexts, we show that a model trained with the proposed algorithm is more sensitive to the additional context.
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
We present a deep convolutional neural network for breast cancer screening exam classification, trained and evaluated on over 200, 000 exams (over 1, 000, 000 images).
Molecular geometry prediction using a deep generative graph neural network
Conventional conformation generation methods minimize hand-designed molecular force field energy functions that are often not well correlated with the true energy function of a molecule observed in nature.
Document Expansion by Query Prediction
One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, this might comprise questions the document can potentially answer.
Ranked #1 on
Passage Re-Ranking
on TREC-PM
Advancing GraphSAGE with A Data-Driven Node Sampling
As an efficient and scalable graph neural network, GraphSAGE has enabled an inductive capability for inferring unseen nodes or graphs by aggregating subsampled local neighborhoods and by learning in a mini-batch gradient descent fashion.
Gradient-based learning for F-measure and other performance metrics
Many important classification performance metrics, e. g. $F$-measure, are non-differentiable and non-decomposable, and are thus unfriendly to gradient descent algorithm.
Backplay: 'Man muss immer umkehren'
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
Task-Driven Data Verification via Gradient Descent
We introduce a novel algorithm for the detection of possible sample corruption such as mislabeled samples in a training dataset given a small clean validation set.
Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar
Automatic machine learning is an important problem in the forefront of machine learning.
Sequential Graph Dependency Parser
We propose a method for non-projective dependency parsing by incrementally predicting a set of edges.
Using local plasticity rules to train recurrent neural networks
To learn useful dynamics on long time scales, neurons must use plasticity rules that account for long-term, circuit-wide effects of synaptic changes.
A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
We investigate this problem by proposing a generalized model of sequence generation that unifies decoding in directed and undirected models.
Multi-Turn Beam Search for Neural Dialogue Modeling
We propose a novel approach for conversation-level inference by explicitly modeling the dialogue partner and running beam search across multiple conversation turns.
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings.
Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
Moreover, both the global structure and local details play important roles in medical image analysis tasks.
Deep Unsupervised Drum Transcription
We introduce DrummerNet, a drum transcription system that is trained in an unsupervised manner.
Sound Audio and Speech Processing
Generating Diverse Translations with Sentence Codes
In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation.
A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks
We present a framework for compactly summarizing many recent results in efficient and/or biologically plausible online training of recurrent neural networks (RNN).
Can Unconditional Language Models Recover Arbitrary Sentences?
We then investigate the conditions under which a language model can be made to generate a sentence through the identification of a point in such a space and find that it is possible to recover arbitrary sentences nearly perfectly with language models and representations of moderate size without modifying any model parameters.
Screening Mammogram Classification with Prior Exams
Radiologists typically compare a patient's most recent breast cancer screening exam to their previous ones in making informed diagnoses.
Improving localization-based approaches for breast cancer screening exam classification
We trained and evaluated a localization-based deep CNN for breast cancer screening exam classification on over 200, 000 exams (over 1, 000, 000 images).
Neural Text Generation with Unlikelihood Training
Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core.
Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
By decoding multiple initial latent variables in parallel and rescore using a teacher model, the proposed model further brings the gap down to 1. 0 BLEU point on WMT'14 En-De task with 6. 8x speedup.
Dynamics-aware Embeddings
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL).
Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages?
Neural Machine Translation with Byte-Level Subwords
Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue.
Countering Language Drift via Visual Grounding
Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans.
Evaluating biological plausibility of learning algorithms the lazy way
To which extent can successful machine learning inform our understanding of biological learning?
Finding Generalizable Evidence by Learning to Convince Q&A Models
We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed.
Inducing Constituency Trees through Neural Machine Translation
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task.
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
We empirically evaluate the proposed mixout and its variants on finetuning a pretrained language model on downstream tasks.
Generalized Inner Loop Meta-Learning
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem.
Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Capacity, Bandwidth, and Compositionality in Emergent Language Learning
In this paper, we investigate the learning biases that affect the efficacy and compositionality of emergent languages.
Multi-Stage Document Ranking with BERT
The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing.
Finding Generalizable Evidence by Learning to Convince Q\&A Models
We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed.
Neural Unsupervised Parsing Beyond English
Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results.
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address.
Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation
Citation recommendation systems for the scientific literature, to help authors find papers that should be cited, have the potential to speed up discoveries and uncover new routes for scientific exploration.
Improving the Ability of Deep Neural Networks to Use Information From Multiple Views in Breast Cancer Screening
In breast cancer screening, radiologists make the diagnosis based on images that are taken from two angles.
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition.
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images.
On the Discrepancy between Density Estimation and Sequence Generation
In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared.
The Break-Even Point on Optimization Trajectories of Deep Neural Networks
We argue for the existence of the "break-even" point on this trajectory, beyond which the curvature of the loss surface and noise in the gradient are implicitly regularized by SGD.
Unsupervised Question Decomposition for Question Answering
We aim to improve question answering (QA) by decomposing hard questions into simpler sub-questions that existing QA systems are capable of answering.
Understanding the robustness of deep neural network classifiers for breast cancer screening
Deep neural networks (DNNs) show promise in breast cancer screening, but their robustness to input perturbations must be better understood before they can be clinically implemented.
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
QAGS is based on the intuition that if we ask questions about a summary and its source, we will receive similar answers if the summary is factually consistent with the source.
Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned
We present the Neural Covidex, a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.
Rapidly Bootstrapping a Question Answering Dataset for COVID-19
We present CovidQA, the beginnings of a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered from Kaggle's COVID-19 Open Research Dataset Challenge.
Learning to Learn Morphological Inflection for Resource-Poor Languages
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem.
Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings
Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation.
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
We show that by separating the two stages, i. e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner.
MLE-guided parameter search for task loss minimization in neural sequence modeling
Typical approaches to directly optimizing the task loss such as policy gradient and minimum risk training are based around sampling in the sequence space to obtain candidate update directions that are scored based on the loss of a single sequence.
Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset
The Neural Covidex is a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset (CORD-19) curated by the Allen Institute for AI.
Compositionality and Capacity in Emergent Languages
Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization.
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.
AdapterHub: A Framework for Adapting Transformers
We propose AdapterHub, a framework that allows dynamic "stitching-in" of pre-trained adapters for different tasks and languages.
VisualSem: A High-quality Knowledge Graph for Vision and Language
We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG.
A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
Contrastive self-supervised learning (CSL) is an approach to learn useful representations by solving a pretext task that selects and compares anchor, negative and positive (APN) features from an unlabeled dataset.
Ranked #26 on
Image Classification
on STL-10
A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
On the other hand, we find that the set of sampling algorithms that satisfies these properties performs on par with the existing sampling algorithms.
Evaluating representations by the complexity of learning low-loss predictors
We consider the problem of evaluating representations of data for use in solving a downstream task.
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using only the latent variable as input.
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
Vision-and-language navigation (VLN) is a task in which an agent is embodied in a realistic 3D environment and follows an instruction to reach the goal node.
Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Breast cancer is the most common cancer in women, and hundreds of thousands of unnecessary biopsies are done around the world at a tremendous cost.
SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples.
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
We then conduct a multi-objective evolutionary search to find a length configuration that maximizes the accuracy and minimizes the efficiency metric under any given computational budget.
Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning
The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility.
Learned Equivariant Rendering without Transformation Supervision
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.
Differences between human and machine perception in medical diagnosis
We compare the two with respect to their robustness to Gaussian low-pass filtering, performing a subgroup analysis on microcalcifications and soft tissue lesions.
A Study on the Autoregressive and non-Autoregressive Multi-label Learning
These tasks are hard because the label space is usually (i) very large, e. g. thousands or millions of labels, (ii) very sparse, i. e. very few labels apply to each input document, and (iii) highly correlated, meaning that the existence of one label changes the likelihood of predicting all other labels.
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function.
Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
This causes BBE to be actively detrimental to policy learning in many control tasks.
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.
Online hyperparameter optimization by real-time recurrent learning
Conventional hyperparameter optimization methods are computationally intensive and hard to generalize to scenarios that require dynamically adapting hyperparameters, such as life-long learning.
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
We introduce a method to determine if a certain capability helps to achieve an accurate model of given data.
NaturalProofs: Mathematical Theorem Proving in Natural Language
Understanding and creating mathematics using natural mathematical language - the mixture of symbolic and natural language used by humans - is a challenging and important problem for driving progress in machine learning.
