Search Results for author:
Found 276 papers, 134 papers with code
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.
Vehicle Communication Strategies for Simulated Highway Driving
Interest in emergent communication has recently surged in Machine Learning.
Training a Ranking Function for Open-Domain Question Answering
In recent years, there have been amazing advances in deep learning methods for machine reading.
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.
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.
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.
Controlling Decoding for More Abstractive Summaries with Copy-Based Networks
Attention-based neural abstractive summarization systems equipped with copy mechanisms have shown promising results.
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.
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.
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.
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.
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.
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.
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.
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
Towards Music Captioning: Generating Music Playlist Descriptions
Descriptions are often provided along with recommendations to help users' discovery.
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.
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).
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).
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.
First Result on Arabic Neural Machine Translation
Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation.
Can neural machine translation do simultaneous translation?
We investigate the potential of attention-based neural machine translation in simultaneous translation.
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.)
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.
Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
Document classification tasks were primarily tackled at word level.
Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
We propose multi-way, multilingual neural machine translation.
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.
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.
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.
Gated Feedback Recurrent Neural Networks
In this work, we propose a novel recurrent neural network (RNN) architecture.
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.
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.
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.
Not All Neural Embeddings are Born Equal
Neural language models learn word representations that capture rich linguistic and conceptual information.
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 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.
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.
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
Contextualized Role Interaction for Neural Machine Translation
Word inputs tend to be represented as single continuous vectors in deep neural networks.
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.
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.
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.
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.
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.
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.
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.
Generating Diverse Translations with Sentence Codes
In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation.
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).
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?
Countering Language Drift via Visual Grounding
Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans.
Inducing Constituency Trees through Neural Machine Translation
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task.
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.
Neural Unsupervised Parsing Beyond English
Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling
Event schemas can guide our understanding and ability to make predictions with respect to what might happen next.
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.
Comparing Test Sets with Item Response Theory
Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks.
Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Stereo Video Reconstruction Without Explicit Depth Maps for Endoscopic Surgery
In the first reader study, a variant of the U-Net that takes as input multiple consecutive video frames and outputs the missing view performs best.
Recognizing and overcoming the greedy nature of learning in multi-modal deep neural networks
We refer to this gain as the conditional utilization rate of the modality.
AAVAE: Augmentation-Augmented Variational Autoencoders
We empirically evaluate the proposed AAVAE on image classification, similar to how recent contrastive and non-contrastive learning algorithms have been evaluated.
Causal Scene BERT: Improving object detection by searching for challenging groups
We verify that the prioritized groups found via intervention are challenging for the object detector and show that retraining with data collected from these groups helps inordinately compared to adding more IID data.
Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ.
Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation
We seek to maximally use various data sources, such as parallel and monolingual data, to build an effective and efficient document-level translation system.
AlphaD3M: Machine Learning Pipeline Synthesis
We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play.
DEEP: DEnoising Entity Pre-training for Neural Machine Translation
It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus.
Causal Effect Variational Autoencoder with Uniform Treatment
In this paper, we introduce uniform treatment variational autoencoders (UTVAE) that are trained with uniform treatment distribution using importance sampling and show that using uniform treatment over observational treatment distribution leads to better causal inference by mitigating the distribution shift that occurs from training to test time.
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.
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.
Evaluating biological plausibility of learning algorithms the lazy way
To which extent can successful machine learning inform our understanding of biological learning?
LINDA: Unsupervised Learning to Interpolate in Natural Language Processing
Despite the success of mixup in data augmentation, its applicability to natural language processing (NLP) tasks has been limited due to the discrete and variable-length nature of natural languages.
Amortized Noisy Channel Neural Machine Translation
For all three approaches, the generated translations fail to achieve rewards comparable to BSR, but the translation quality approximated by BLEU and BLEURT is similar to the quality of BSR-produced translations.
Causal Scene BERT: Improving object detection by searching for challenging groups of data
Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes.
On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Many recent studies on large-scale language models have reported successful in-context zero- and few-shot learning ability.
Training Language Models with Language Feedback
We learn from language feedback on model outputs using a three-step learning algorithm.
Multi-segment preserving sampling for deep manifold sampler
We introduce an alternative approach to this guided sampling procedure, multi-segment preserving sampling, that enables the direct inclusion of domain-specific knowledge by designating preserved and non-preserved segments along the input sequence, thereby restricting variation to only select regions.
Translating Hanja Historical Documents to Contemporary Korean and English
Built on top of multilingual neural machine translation, H2KE learns to translate a historical document written in Hanja, from both a full dataset of outdated Korean translation and a small dataset of more recently translated contemporary Korean and English.
Predicting Out-of-Domain Generalization with Neighborhood Invariance
Developing and deploying machine learning models safely depends on the ability to characterize and compare their abilities to generalize to new environments.
Towards Disentangled Speech Representations
In this paper, we construct a representation learning task based on joint modeling of ASR and TTS, and seek to learn a representation of audio that disentangles that part of the speech signal that is relevant to transcription from that part which is not.
PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design
Bayesian optimization offers a sample-efficient framework for navigating the exploration-exploitation trade-off in the vast design space of biological sequences.
A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences.
Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?
Task-oriented dialogue (TOD) systems are mainly based on the slot-filling-based TOD (SF-TOD) framework, in which dialogues are broken down into smaller, controllable units (i. e., slots) to fulfill a specific task.
Dual Learning for Large Vocabulary On-Device ASR
Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once.
Unsupervised Learning of Initialization in Deep Neural Networks via Maximum Mean Discrepancy
We first notice that each parameter configuration in the parameter space corresponds to one particular downstream task of d-way classification.
A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale
Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus.
Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency.
BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
At the heart of MOBO is the acquisition function, which determines the next candidate to evaluate by navigating the best compromises among the objectives.
System-Level Natural Language Feedback
Natural language (NL) feedback offers rich insights into user experience.
Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section
Recent advances in large language models have led to renewed interest in natural language processing in healthcare using the free text of clinical notes.
Leveraging Implicit Feedback from Deployment Data in Dialogue
We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations.
AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodies
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences.
Improving Joint Speech-Text Representations Without Alignment
The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly.
Active and Passive Causal Inference Learning
This paper serves as a starting point for machine learning researchers, engineers and students who are interested in but not yet familiar with causal inference.
Blind Biological Sequence Denoising with Self-Supervised Set Learning
This set embedding represents the "average" of the subreads and can be decoded into a prediction of the clean sequence.
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model.
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs).
Perspectives on the State and Future of Deep Learning -- 2023
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time.
Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding
Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collecting processes.
Hyperparameters in Continual Learning: a Reality Check
In the Hyperparameter Tuning phase, each algorithm is iteratively trained with different hyperparameter values to find the optimal hyperparameter values.
HyperCLOVA X Technical Report
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding.
Generalization Measures for Zero-Shot Cross-Lingual Transfer
A model's capacity to generalize its knowledge to interpret unseen inputs with different characteristics is crucial to build robust and reliable machine learning systems.
Iterative Reasoning Preference Optimization
Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024).
On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis
However, the image reconstruction process within the MRI pipeline, which requires the use of complex hardware and adjustment of a large number of scanner parameters, is highly susceptible to noise of various forms, resulting in arbitrary artifacts within the images.
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
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.
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.
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.
Mode recovery in neural autoregressive sequence modeling
We propose to study these phenomena by investigating how the modes, or local maxima, of a distribution are maintained throughout the full learning chain of the ground-truth, empirical, learned and decoding-induced distributions, via the newly proposed mode recovery cost.
Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction
We assess the sensitivity score on a set of representative words in the test set using two classifiers trained for hospital readmission classification with similar performance statistics.
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.
Generative multitask learning mitigates target-causing confounding
We propose generative multitask learning (GMTL), a simple and scalable approach to causal representation learning for multitask learning.
Latent State Models of Training Dynamics
We use the HMM representation to study phase transitions and identify latent "detour" states that slow down convergence.
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.
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.
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.
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.
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.
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.
Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
From these observations, we conclude that the high degree of oversmoothing is the main reason behind the degenerate case of overly probable short sequences in a neural autoregressive model.
An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models.
A Non-monotonic Self-terminating Language Model
We then propose a non-monotonic self-terminating language model, which significantly relaxes the constraint of monotonically increasing termination probability in the originally proposed self-terminating language model by Welleck et al. (2020), to address the issue of non-terminating sequences when using incomplete probable decoding algorithms.
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.
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.
Protein Discovery with Discrete Walk-Jump Sampling
We resolve difficulties in training and sampling from a discrete generative model by learning a smoothed energy function, sampling from the smoothed data manifold with Langevin Markov chain Monte Carlo (MCMC), and projecting back to the true data manifold with one-step denoising.
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.
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.
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.
HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea
Historical records in Korea before the 20th century were primarily written in Hanja, an extinct language based on Chinese characters and not understood by modern Korean or Chinese speakers.
Importance of Search and Evaluation Strategies in Neural Dialogue Modeling
We investigate the impact of search strategies in neural dialogue modeling.
Towards Understanding and Improving GFlowNet Training
We investigate how to learn better flows, and propose (i) prioritized replay training of high-reward $x$, (ii) relative edge flow policy parametrization, and (iii) a novel guided trajectory balance objective, and show how it can solve a substructure credit assignment problem.
Show Your Work with Confidence: Confidence Bands for Tuning Curves
We present the first method to construct valid confidence bands for tuning curves.
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.
Linear Connectivity Reveals Generalization Strategies
It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space over which test set accuracy is maintained.
Joint Embedding Predictive Architectures Focus on Slow Features
Many common methods for learning a world model for pixel-based environments use generative architectures trained with pixel-level reconstruction objectives.
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation
In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data.
Learning to Parse and Translate Improves Neural Machine Translation
There has been relatively little attention to incorporating linguistic prior to neural machine translation.
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.
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.
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning.
Training Language Models with Language Feedback at Scale
Third, finetuning the language model to maximize the likelihood of the chosen refinement given the input.
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.
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
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
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.
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.
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.
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.
Learning to Translate in Real-time with Neural Machine Translation
Translating in real-time, a. k. a.
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.
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.
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.
Dynamics-aware Embeddings
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL).
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.
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.
AASAE: Augmentation-Augmented Stochastic Autoencoders
We empirically evaluate the proposed AASAE on image classification, similar to how recent contrastive and non-contrastive learning algorithms have been evaluated.
AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models
We present AstroCLIP, a strategy to facilitate the construction of astronomical foundation models that bridge the gap between diverse observational modalities.
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.
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.
