A novel conLSH algorithm improves alignment of noisy SMRT reads.
problem High error probability in SMRT sequencing data.
method Context-based Locality Sensitive Hashing (conLSH) for efficient alignment.
result Comprehensive improvement in speed and memory requirements compared to rHAT.
In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules. This paper introduces a novel method of dialog state t…
Structural-Jump-LSTM speeds up reading by skipping and jumping text.
problem Sequential inference in RNNs makes reading time linearly dependent on input length.
method Introduces a novel LSTM model with agents for skipping and jumping text.
result Structural-Jump-LSTM achieves best FLOP reduction and maintains or improves accuracy.
Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.
problem Neural models' oversensitivity to adversarial question changes.
method Formulated a noisy adversarial attack to identify and exploit undersensitivity, tested with data augmentation and adversarial training.
result Undersensitivity can be exploited to mislead models, and addressing it improves model performance and robustness.
Paper uses genome Markov structure for outlier detection and read classification.
problem Identifying outliers and classifying reads in genome databases.
method Applying second-order Markov models to triplet base distributions.
result Improved accuracy in outlier identification and read classification.
Semi-supervised deep learning detects problematic reads for genome assembly.
problem De novo genome assembly is hindered by specific types of reads.
method Analysis of coverage graphs converted to 1D-signals using semi-supervised deep learning models.
result Semi-supervised deep learning models can detect problematic reads with minimal labeled data.
Dataset for measuring reading levels in India's children.
problem Measuring reading levels in India's vast population.
method Developed ASER dataset with 5,301 subjects in Hindi, Marathi, and English.
result Achieved 86% accuracy in English language classification.
Dead-Direction Signatures (DDS) provide a cheap, closed-form spectral reading of a network's singular complexity.
problem Estimating the complexity of deep networks through their loss singularities.
method DDS replaces the SGLD posterior chain with spectral linear algebra.
result DDS observables rank-track the network's singular complexity at the framework-predicted sign.
Paper explores zero-shot cross-lingual reading comprehension using pre-trained multi-lingual model.
problem Lack of training data for every language in reading comprehension tasks.
method Systematic exploration of zero-shot cross-lingual transfer learning with a multi-lingual language representation model.
result Zero-shot cross-lingual transfer learning is feasible and translating source data into target language is not necessary.
QAInfomax improves reading comprehension by maximizing mutual information, achieving state-of-the-art performance.
problem Distractor sentences in question answering datasets are hard to distinguish from relevant ones.
method QAInfomax regularizes reading comprehension models to learn mutual information among passages, questions, and answers.
result QAInfomax achieves state-of-the-art performance on Adversarial-SQuAD dataset.
Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as question…
META2 improves taxonomic classification and abundance estimation in metagenomics with deep learning and memory efficiency.
problem Memory constraints and inefficiencies in taxonomic classification and abundance estimation for metagenomics.
method Developed a novel memory-efficient read classification technique combining deep learning and locality-sensitive hashing, and formulated abundance estimation as a Multiple Instance Learning problem.
result Our approach outperforms conventional methods in both single-read taxonomic classification and abundance estimation, especially when memory is limited.
Shannon's mathematical theory of communication defines fundamental limits on how much information can be transmitted between the different components of any man-made or biological system. This paper is an informal but rigorous introduction to the main ideas implicit in Shannon's theory. An annotated reading list is pro…
We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictiv…
New approach speeds up DNA sequence alignment.
problem Efficiently estimating alignment scores for large sets of reads.
method Rank-one crowdsourcing models and multi-armed bandit algorithm.
result Adaptive algorithm identifies pairs with large alignment scores.
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with …
Semi-supervised model removes noisy content from webpages.
problem Extracting relevant content from webpages with ads and noise.
method Graph representation of webpage, semi-supervised learning with Gaussian Random Fields.
result Preliminary results show successful extraction of relevant content.
Robo-PlaNet learns robot tasks faster than PlaNet.
problem Training robot tasks with limited or noisy sensor data.
method Asynchronous version of PlaNet that interleaves dynamics model training and data collection.
result Robo-PlaNet achieves higher performance in less time.
Neural network optimizes learning sequence for reading words.
problem Children struggle with learning to read words due to inconsistent spelling-sound correspondences.
method Used a neural network to structure learning trials to optimize generalization accuracy.
result Significant improvement in generalization accuracy compared to random or frequency-based sequences.
Many recent papers address reading comprehension, where examples consist of (question, passage, answer) tuples. Presumably, a model must combine information from both questions and passages to predict corresponding answers. However, despite intense interest in the topic, with hundreds of published papers vying for lead…
BIOMRC dataset improves MRC performance, especially for non-experts.
problem Improving machine reading comprehension in biomedical texts.
method Developed a new dataset and tested two neural models, along with a BERT-based model.
result BERT-based model outperforms all other methods and reaches expert-level accuracy.
We show how the rotation and translation fields of a surface, introduced by G. Darboux, may be used to obtain short proofs of a well-known theorem (that reads that the total mean curvature of a surface is stationary under an infinitesimal bending) and a new theorem (that reads that every infinitesimal flex of any simpl…
This work tackles missing annotations in large sensor datasets.
problem Missing annotations in large sensor datasets negatively affect supervised learning system performance.
method Proposes and evaluates three paradigms to handle gaps: dropping, single label, and unique label, along with a hybrid combination.
result Evaluation of proposed paradigms and hybrid combination shows significant performance improvement.
EMR learns to read and remember from streaming data for QA.
problem Scalable QA from streaming data without knowing questions.
method End-to-end deep network model (EMR) with RL agent for memory management.
result EMR achieves significant improvements over existing methods on synthetic and real-world datasets.
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the required memory. We present Bandana, a storage system that reduces the DRAM footprint of embeddings, by using Non-volatile Memory (NVM) as the prim…
With an aging and growing population, the number of women requiring either screening or symptomatic mammograms is increasing. To reduce the number of mammograms that need to be read by a radiologist while keeping the diagnostic accuracy the same or better than current clinical practice, we develop Man and Machine Mammo…
Study prenatal PM2.5 exposure and 4th grade reading scores, identifying critical windows of susceptibility.
problem Understanding the impact of prenatal PM2.5 exposure on educational outcomes.
method Developed a locally adaptive Bayesian regression model with B-spline basis expansion and dynamic shrinkage priors.
result Prenatal PM2.5 exposure during early and late pregnancy is most adverse for 4th grade reading scores.
The covariance graph (aka bi-directed graph) of a probability distribution p is the undirected graph G where two nodes are adjacent iff their corresponding random variables are marginally dependent in p. In this paper, we present a graphical criterion for reading dependencies from G, under the assumption that $…
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.
Scarcity of labeled data is one of the most frequent problems faced in machine learning. This is particularly true in relation extraction in text mining, where large corpora of texts exists in many application domains, while labeling of text data requires an expert to invest much time to read the documents. Overall, st…
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
Proposes a framework to adjust quotes for informational risk in markets with informed traders and price-revealing quotes.
problem Informational risk in markets with informed traders and price-revealing quotes.
method Proposes a tractable framework to adjust quotes considering adverse selection and price reading.
result Market makers can adjust their quotes to better manage informational risk.
Model learns to discover and disambiguate entities and relations in text streams.
problem Learning to follow and resolve mentions in a continuous text stream.
method End-to-end trainable memory network for online, one-shot learning.
result Improves disambiguation and discovery skills with minimal supervision.
Paper tackles non-convex constrained DRO with a stochastic algorithm for large-scale applications.
problem Training robust models against data distribution shifts with non-convex loss functions.
method Developed a stochastic algorithm for non-convex constrained DRO with a complexity independent of dataset size.
result Algorithm finds ε-stationary points with computational complexity of O(ε^(-3k_*-5)) for general Cressie-Read divergence.
We prove that the Garside length a braid is equal to a winding-number type invariant of the curve diagram of the braid.
Estimates latent dimensionality for prediction tasks using mutual information.
problem Estimating the latent dimensionality needed for accurate prediction.
method Formulates the problem as an Information Bottleneck question and uses neural mutual information estimators with a hybrid critic to preserve latent geometry.
result The hybrid critic method provides a more accurate estimation of task-relevant dimensionality.
A framework for navigating environments with spatially correlated obstacles and uncertain blockage status.
problem Navigation in environments with spatially correlated obstacles of uncertain blockage status.
method Modeling spatial correlation with Gaussian Random Field, developing Bayesian belief updates, proposing a two-stage learning framework with offline and online phases.
result Consistent performance gains over baselines in environments with adversarial interruptions or clustered natural hazards.
Metagenomics characterizes the taxonomic diversity of microbial communities by sequencing DNA directly from an environmental sample. One of the main challenges in metagenomics data analysis is the binning step, where each sequenced read is assigned to a taxonomic clade. Due to the large volume of metagenomics datasets,…
Due to limited metering infrastructure, distribution grids are currently challenged by observability issues. On the other hand, smart meter data, including local voltage magnitudes and power injections, are communicated to the utility operator from grid buses with renewable generation and demand-response programs. This…
Study shows context-specific models improve swipe gesture authentication for smartphone users.
problem Improving swipe gesture-based continuous authentication for smartphones.
method Conducted experiments on HMOG dataset with 100 subjects, analyzing authentication error in different scenarios.
result Context-specific models are needed for different smartphone usage and human activity scenarios.
Model generates label-dependent paraphrases for NLP tasks.
problem Generating semantically different paraphrases for NLP tasks.
method Deep variational model with label-dependent generation.
result Model improves generative power of paraphrasing models.
LayerNorm transformers have dead directions that can be read from their parameters alone.
problem Locating dead directions in LayerNorm transformers
method Using the inverse-scale direction of LayerNorm affine parameters
result Predicted dead direction matches measured bottom singular direction
These notes have been prepared as reading material for the mini-course that the author gave at IMS, National University of Singapore, as part of the "Summer school on the moduli space of Higgs bundles".
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforce…
This note is purely expository. In the course of the Kolmogorov-Arnold solution of Hilbert's 13th problem on superpositions there appeared the notion of basic embedding. A subset K of R^2 is basic if for each continuous function f:K->R there exist continuous functions g,h:R->R such that f(x,y)=g(x)+h(y) for each point …
Proposes a graph neural network for personalized news recommendation.
problem Data sparsity in news recommendation systems.
method Heterogeneous graph model + Graph Neural Networks + LSTM attention mechanism.
result Significantly outperforms state-of-the-art methods on news recommendation datasets.
New metrics predict human sentence comprehension across languages.
problem Predicting human sentence comprehension using computational models.
method Developed sentence-level metrics using multilingual large language models.
result Achieved high accuracy in predicting human sentence reading speeds.
CopyCAT attacks neural policies by manipulating observations, not states.
problem Adversarial attacks on neural reinforcement learning agents.
method CopyCAT is a targeted attack that lures agents into following outsider policies.
result CopyCAT is effective in a read-only setting where adversaries can only manipulate observations.