AclNet improves audio classification with high accuracy and reduced complexity.
problem Efficiently classifying audio data with high accuracy.
method Proposed AclNet architecture with data augmentation and regularization.
result Achieved state-of-the-art performance on ESC-50 corpus with 85.65% accuracy.
Model classifies environment sounds using multiple feature channels and attention mechanisms.
problem Environment sound classification task.
method Multiple feature channels (MFCC, GFCC, CQT, Chromagram) and attention mechanism in a deep CNN.
result Achieves state-of-the-art performance on three benchmark datasets.
We introduce the TUH EEG Seizure Corpus (TUSZ), which is the largest open source corpus of its type, and represents an accurate characterization of clinical conditions. In this paper, we describe the techniques used to develop TUSZ, evaluate their effectiveness, and present some descriptive statistics on the resulting …
End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used l…
RUSLAN is a large Russian speech corpus for text-to-speech.
problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.
Study examines market risks on pension system sustainability.
problem Impact of market risks on pension corpus sustainability.
method Monte Carlo simulations with historical data.
result Market risks significantly impact pension corpus sustainability.
Quantum analysis tags news for sentiment and entities.
problem Identifying bias in news reporting.
method Continuous data collection, NER and sentiment analysis.
result A corpus of tagged news articles for public use.
ClovaCall introduces a new Korean call speech corpus for contact centers.
problem Lack of large-scale call-based speech corpora for Korean dialog scenarios.
method Development of a new large-scale Korean call-based speech corpus (ClovaCall) in a restaurant reservation domain.
result Validation of the dataset with ASR models shows its effectiveness.
Corpus poisoning can manipulate word meanings in word embeddings, affecting natural language processing tasks.
problem Controlling word meanings via corpus modifications.
method Developed an explicit expression over corpus features to control word embeddings.
result Demonstrated the ability to manipulate word meanings in word embeddings, affecting various downstream tasks.
Challenge evaluates semantic code search using annotated corpus.
problem Evaluating relevant code from natural language queries.
method Release of CodeSearchNet Corpus and expert annotations.
result 99 queries with 4k relevance annotations for evaluation.
Improved embeddings by topic-sensitive attention on large corpora.
problem Capturing sense of words in limited corpora using pretrained embeddings.
method Topic-sensitive attention on large topic-rich corpora to correct sense drift in pretrained embeddings.
result Limited corpus augmentation is more effective than adapting pretrained embeddings.
New Polish word embeddings improve temporal expression recognition.
problem Recognizing temporal expressions in Polish text.
method Created KGR10 corpus, used BiLSTM-CRF model with custom embeddings.
result Custom embeddings enhance BiLSTM-CRF model's performance.
Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.
problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural N…
End-to-end models classify composers from musical scores.
problem Classifying composers from musical scores using machine learning.
method Pooled and convolutional architectures for feature extraction.
result Models achieve high accuracy on a large corpus of scores.
In the field of Natural Language Processing (NLP), we revisit the well-known word embedding algorithm word2vec. Word embeddings identify words by vectors such that the words' distributional similarity is captured. Unexpectedly, besides semantic similarity even relational similarity has been shown to be captured in word…
FairGround offers a diverse dataset corpus for fair ML research.
problem Lack of diverse, well-annotated datasets in fair ML research.
method Unified framework and Python package for reproducible fair ML research.
result Advances reproducibility and generalizability of fair ML research.
Paper proposes continual learning for sentence encoders.
problem Optimize sentence encoders for new corpora while maintaining old corpus accuracy.
method Initialize encoders with corpus-independent features, update using Boolean operations of conceptor matrices.
result Proposed sentence encoder can continually learn features from new corpora.
Modeling lead-lag relationship between two text corpora for improved topic modeling.
problem Recognizing the relationship between multiple text corpora for better topic modeling.
method Proposed a jointly dynamic topic model and embedding extension for large-scale text corpus.
result The proposed model can well recognize the lead-lag relationship between two text corpora and improve topic learning.
Automated seizure detection using clinical electroencephalograms is a challenging machine learning problem because the multichannel signal often has an extremely low signal to noise ratio. Events of interest such as seizures are easily confused with signal artifacts (e.g, eye movements) or benign variants (e.g., slowin…
Zero-shot audio classification using class label embeddings.
problem Classifying audio without labeled data.
method Bilinear model with audio feature embeddings and class label embeddings.
result Achieved accuracy up to 39.7% for natural audio categories.
Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. This may not efficiently harness the time-frequency repr…
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
New method to understand bias in word embeddings.
problem Understanding and mitigating bias in word embeddings.
method Developed a technique to trace bias origins back to training documents.
result Accurate approximations of bias reduction can be made.
Synthetic continued pretraining enhances model performance with synthetic data.
problem Data inefficiency in pretrained models when adapting to domain-specific documents.
method Synthetic data augmentation using EntiGraph to create a large synthetic corpus.
result Language models can answer questions and follow instructions without access to domain-specific documents.
Large-scale automated meta-analysis of neuroimaging data has recently established itself as an important tool in advancing our understanding of human brain function. This research has been pioneered by NeuroSynth, a database collecting both brain activation coordinates and associated text across a large cohort of neuro…
Paper proposes FOFE for efficient WSD.
problem Word sense disambiguation (WSD) problem.
method Fixed-size ordinally forgetting encoding (FOFE) combined with FFNN.
result FOFE-based FFNN achieves comparable performance to state-of-the-art at lower cost.
Enhances persona-based conversation model for multi-turn dialogue.
problem Improving persona-based conversation models for multi-turn dialogue.
method Introduced additional input modality into hredGAN to capture external attributes.
result Persona hredGAN (phredGAN) outperforms existing models in multi-turn dialogue corpora. The paper creates a language evolution tree using word vectors from historical novels.
problem Exploring the evolution of language through historical texts.
method Constructed word vectors from novels, combined them, and used hierarchical clustering.
result Discovered a specific language evolution tree that reflects the year of the corpus.
Model-based methods for recommender systems have been studied extensively in recent years. In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult. To overcome the calculation barriers, mod…
In the probabilistic topic models, the quantity of interest---a low-rank matrix consisting of topic vectors---is hidden in the text corpus matrix, masked by noise, and the Singular Value Decomposition (SVD) is a potentially useful tool for learning such a low-rank matrix. However, the connection between this low-rank m…
Bayesian SHMM discovers acoustic units from unlabeled speech.
problem Discovering language-specific acoustic units from unlabeled speech.
method Bayesian Subspace Hidden Markov Model (SHMM) trained on labeled data to find new acoustic units on target language.
result Significantly outperforms previous HMM-based systems and compares favorably with Variational Auto Encoder-HMM.
User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The ABUS is based on hand-crafted rules and its output is in semantic form. Issues arise from both properties such as limited diversity and the i…
Imaging neuroscience links brain activation maps to behavior and cognition via correlational studies. Due to the nature of the individual experiments, based on eliciting neural response from a small number of stimuli, this link is incomplete, and unidirectional from the causal point of view. To come to conclusions on t…
A model for entity relatedness considering time and context.
problem Time and context influence entity relatedness.
method Flexible model using time-aware and corpus-specific word embeddings.
result The model generates accurate entity relatedness lists.
New topic modeling method scales to large datasets.
problem Large-scale topic modeling with high co-occurrence data.
method Introduced Full Dependence Mixture (FDM) model for direct topic learning.
result FDM model performs comparably or better than benchmarks on large datasets.
Every year at the United Nations, member states deliver statements during the General Debate discussing major issues in world politics. These speeches provide invaluable information on governments' perspectives and preferences on a wide range of issues, but have largely been overlooked in the study of international pol…
New corpus improves coreference resolution by removing gender and number cues.
problem Challenges in resolving ambiguous pronoun references.
method Developed a new annotated corpus, introduced antecedent switching technique.
result Models perform poorly on ambiguous pronoun references, but antecedent switching improves performance.
ProxiModel extracts high-quality news events from news corpora.
problem Mining high-quality structured event knowledge from noisy news data.
method ProxiModel uses a proximity-network to model event correlation within and across news corpora.
result ProxiModel efficiently and effectively extracts high-quality event descriptors and attributes.
Paper uses NLP to cluster patient visits for diagnosis validation.
problem Validating if similar patients receive similar diagnoses.
method Representation of medical visits using word embeddings, clustering patients' visits.
result Stable and separated segments of visits positively validated against diagnoses.
Improved GEC with weakly supervised data and iterative decoding.
problem Grammatical error correction using limited labeled data.
method Transformer model trained on weakly supervised bitext, iterative decoding.
result Iterative decoding improves GEC performance on CoNLL'14 benchmark.
Naive Bayes model performs best in classifying seismological articles about precursory seismicity.
problem Classifying seismological articles about precursory seismicity using machine learning.
method Various supervised machine learning classifiers (Naive Bayes, k-Nearest Neighbors, Support Vector Machines, Random Forests) were tested on a seismological corpus of 100 articles.
result Naive Bayes model performs best with cross-validation accuracies of 86% for binary classification and up to 78% for multiclass classification.
Nested Chinese Restaurant Process (nCRP) topic models are powerful nonparametric Bayesian methods to extract a topic hierarchy from a given text corpus, where the hierarchical structure is automatically determined by the data. Hierarchical Latent Dirichlet Allocation (hLDA) is a popular instance of nCRP topic models. H…
Experiment tested active learning for Thai text segmentation.
problem Using active learning for text annotation in machine learning.
method Live experiment with two sampling methods: random and model-based.
result Active learning strategy interacted with real-world changes.
Study finds stocks with higher cyber risk scores outperform others, indicating a market-wide cyber risk premium.
problem Identifying and quantifying firms' cyber risks and their impact on stock performance.
method Machine learning algorithm to analyze disclosures and a dedicated cyber corpus.
result High cyber risk stocks significantly outperform others, indicating a market-wide cyber risk premium.
Paper proposes a novel unsupervised feature learning approach for environmental sound classification.
problem Classifying environmental sounds without labeled data.
method Cycle-consistent GAN for high-level data augmentation, unsupervised feature learning, codebook construction.
result Improves classification rate by 3.51% to 14.34% compared to state-of-the-art classifiers.
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by usi…
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training loss function. This paper offers an empirical investigation on which aspects of …