The paper uses attention networks for character-based handwritten text transcription.
problem Handwritten text recognition with improved character-level alignment.
method Attentional encoder-decoder networks trained on character sequences, comparing different activation functions.
result Softmax attention provides more precise character alignment than sigmoid attention.
Dynamic segmentation algorithm improves NMT performance by favoring character-level processing.
problem Suboptimal static segmentation choices in NMT systems.
method Adaptive Computation Time algorithm for dynamic segmentation, trainable end-to-end.
result The model prefers character-level processing when given the freedom to navigate different segmentation levels.
Deep transformer models outperform RNNs in character-level language modeling.
problem Improving character-level language modeling performance.
method A deep (64-layer) transformer model with fixed context and auxiliary losses.
result Achieved state-of-the-art performance on text8 and enwik8 benchmarks.
End-to-end ASR model combines word and character representation for improved performance.
problem Difficulty in training with word-level supervision due to sparsity of examples.
method Multi-task learning framework combining word and character representations.
result Improved word-error rate (WER) by interpolating between word-level and character-level models.
Charmer improves character-level adversarial attacks for language models.
problem Efficiency and effectiveness of character-level adversarial attacks for language models.
method Query-based adversarial attack method that maintains semantic similarity.
result Charmer achieves high attack success rate and similar adversarial examples.
This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNN…
The paper improves part-of-speech tagging with multi-task learning and character-level word representations.
problem Improving part-of-speech tagging accuracy.
method Developed a new character-level word representation using feedforward neural network, pretraining with existing word vectors, and an additional prediction of neighbour labels as an auxiliary loss.
result The methods significantly improved POS tagging performance on English and Russian languages.
Recent advances in high-throughput cDNA sequencing (RNA-Seq) technology have revolutionized transcriptome studies. A major motivation for RNA-Seq is to map the structure of expressed transcripts at nucleotide resolution. With accurate computational tools for transcript reconstruction, this technology may also become us…
End-to-end ASR error detection using audio-transcript entailment.
problem Detecting transcription errors in ASR systems to prevent error propagation.
method Proposes a novel end-to-end approach using audio-transcript entailment, with acoustic and linguistic encoders.
result Achieves CER of 26.2% on all transcription errors and 23% on medical errors specifically, improving by 12% and 15.4% respectively over a strong baseline.
TF-MoDISco finds transcription factor motifs from genomic data.
problem Identifying transcription factor motifs from genomic sequence data.
method Algorithm for motif discovery from basepair-level importance scores.
result Improved version v0.5.6.5 of TF-MoDISco.
Adversarial learning improves music transcription accuracy.
problem Conditional independence of labels in deep learning models limits transcription performance.
method Adversarial training scheme operating on time-frequency representations to reduce inter-label dependencies.
result Adversarial learning reduces error rate and increases model confidence.
Paper compares training and sampling schemes for character-level RNNs.
problem Optimizing training and sampling schemes for character-level RNNs.
method Tested various training and sampling schemes on different datasets and architectures.
result The choice of training and sampling scheme affects stability, performance, and implementation effort.
siRF identifies transcription factor binding near enhancers in flies.
problem Identifying functional transcription factor binding near enhancers.
method Signed iterative random forests (siRF) for machine learning.
result Infers regulatory interactions among transcription factors and enhancers.
Computational approaches to transcription factor binding site identification have been actively researched for the past decade. Negative examples have long been utilized in de novo motif discovery and have been shown useful in transcription factor binding site search as well. However, understanding of the roles of nega…
This study identifies sentence relationships in legal transcripts.
problem Improving understanding of legal case proceedings through sentence relationships.
method Combining machine learning and rule-based approach to classify sentence relationships.
result First study to use discourse relationships for legal court case transcripts.
Inverse Drum Machine separates drum mixes using transcription and synthesis.
problem Separating individual drum tracks from mixed recordings.
method Analysis-by-synthesis framework combining deep learning and automatic transcription.
result Separation quality comparable to supervised methods requiring isolated stems.
Predicting the click-through rate of an advertisement is a critical component of online advertising platforms. In sponsored search, the click-through rate estimates the probability that a displayed advertisement is clicked by a user after she submits a query to the search engine. Commercial search engines typically rel…
Improves audio transcription on scarce data with factorized tasks.
problem Weakly labelled data and lack of training samples.
method Factorizing audio transcription into multiple tasks and training a stacked CNN-RNN model.
result Different training methods for intermediate tasks have varying advantages and disadvantages.
Improved piano transcription by predicting onsets and frames together.
problem Polyphonic piano music transcription accuracy.
method Deep convolutional and recurrent neural network trained to predict pitch onsets and frames.
result Over 100% relative improvement in note F1 score on MAPS dataset.
New method synthesizes piano training data, improving transcription performance.
problem Lack of large piano datasets limits note onset transcription models.
method Synthesizes arbitrary training data, models piano dynamics, avoids disentanglement problem.
result Achieves good transcription performance on MAPS dataset and excellent generalization.
Physically-inspired Gaussian process models study post-transcriptional regulation in Drosophila.
problem Understanding spatiotemporal interactions between mRNAs and gap proteins in post-transcriptional regulation.
method Two physically-inspired Gaussian process models based on reaction-diffusion equations, tested with mRNA expression data.
result Novel GP model requires only kernel function differentiation, simplifying spatial discretisation.
Paper improves music transcription models with invariance and data augmentation.
problem Improving accuracy of frame-based music transcription models.
method Translation-invariant network combining filterbank and CNN, trained with pitch-shift augmented data.
result Top-performing model in MIREX evaluation, reducing model complexity and avoiding overfitting.
Motivation: Cell-biological processes are regulated through a complex network of interactions between genes and their products. The processes, their activating conditions, and the associated transcriptional responses are often unknown. Organism-wide modeling of network activation can reveal unique and shared mechanisms…
Paper proposes M2H-GAN to improve speech theme identification.
problem Limited ASR transcripts for speech theme identification.
method Uses M2H-GAN, a GAN-based approach, to generate TRS-like ASR transcripts.
result Improves speech theme identification performance close to human levels.
New models improve language generation by sharing intermediate states.
problem Language models struggle with past mistakes in sequence generation.
method Integrate second-order terms in hidden-state update, sharing intermediate states.
result Shared parametrization improves language modeling performance.
Study of SK-N-AS cells' response to methamidophos using transcriptomics.
problem Understanding the transcriptional response of SK-N-AS cells to methamidophos exposure.
method Combination of statistical and machine learning methods for anomaly detection and causal network inference.
result Identification of key processes and transcripts involved in the response to methamidophos.
Generative AI predicts economic activity from corporate transcripts.
problem Predicting economic activity using existing measures like surveys.
method Extracted managerial expectations from transcripts using generative AI.
result AI Economy Score predicts economic activity up to 10 quarters ahead.
Synthetic noise training improves machine translation robustness to spelling mistakes.
problem Making machine translation robust to spelling mistakes and natural noise.
method Training on synthetic noise to improve robustness to natural noise.
result Training on synthetic noise improves robustness to natural noise without diminishing performance on clean text.
We introduce multiplicative LSTM (mLSTM), a recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by its ability to have different recurrent transition functions for each possible inp…
Study detects SLI in children from spontaneous narrative transcripts.
problem Detecting Specific Language Impairment (SLI) in children.
method Three-stage pipeline: feature extraction, dimensionality reduction, and classification.
result 97.13% accuracy in identifying SLI from transcripts.
Model earnings call transcripts for better stock price prediction.
problem Predicting future stock price movements using earnings call transcripts.
method Deep learning framework with an attention mechanism to encode text data into vectors for predicting stock price movements.
result The proposed model outperforms traditional machine learning methods in stock price prediction.
To survive environmental conditions, cells transcribe their response activities into encoded mRNA sequences in order to produce certain amounts of protein concentrations. The external conditions are mapped into the cell through the activation of special proteins called transcription factors (TFs). Due to the difficult …
Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to the existing state-of-the-art phrase-based systems on the task of English-to-Fr…
Study analyzes deep learning models for financial sentiment in earnings calls.
problem Leveraging NLP for sentiment analysis in financial transcripts.
method Comparative analysis of BERT, FinBERT, and ULMFiT models.
result Models' strengths and limitations in financial sentiment analysis.
End-to-end character-level model for text generation without delexicalization.
problem Generating text without delexicalization and tokenization.
method Character-level sequence-to-sequence model with attention mechanism, copy mechanism, and transfer learning.
result Competitive performance in text generation metrics.
We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our…
Neural networks predict TED Talk ratings from transcripts, removing bias.
problem Predicting public speaking performance from speech transcripts.
method Causal diagram modeling, word sequence and dependency tree based neural networks.
result Average F-score of 0.77, significantly outperforming baseline methods.
New task aligns molecular structure with gene expression changes.
problem Modeling the relationship between chemical structure and gene expression changes.
method Developed a cross-modal small molecule retrieval task and a coordinated deep learning approach to align chemical structure and gene expression profiles.
result Demonstrated the feasibility of the new task and highlighted the limitations of current data and systems.
Hidden Markov Models (HMMs) are a ubiquitous tool to model time series data, and have been widely used in two main tasks of Automatic Music Transcription (AMT): note segmentation, i.e. identifying the played notes after a multi-pitch estimation, and sequential post-processing, i.e. correcting note segmentation using tr…
The paper improves ASR accuracy using semi-supervised learning and dropout.
problem Improving ASR accuracy with limited labeled data.
method Training a seed model on limited labeled data, using dropout for uncertainty, and data selection for diversity.
result The approach significantly reduces ASR errors compared to baseline.
Predicts customer call intent for auto dealerships using CNN.
problem Understanding customer intent from phone calls for better service.
method Developed a CNN-based supervised learning model for multi-class classification.
result CNN model performs well on customer call intent classification.
Neural network generates music scores directly from polyphonic audio.
problem Transcribing music scores directly from polyphonic audio.
method Convolutional Recurrent Neural Network (CRNN) with CTC loss function.
result Model can learn to transcribe scores directly from audio signals.
Study combines speaker verification and voice trigger detection in a single network.
problem Separate training for speaker verification and voice trigger detection.
method Multi-task learning with a single network trained on both tasks.
result Single network achieves comparable accuracy to independent models for each task.
Model predicts active and passive cosponsorship motivations in Congress.
problem Identifying motivations behind cosponsorship in U.S. Congress.
method Encoder+RGCN model learning from bill texts and speeches.
result F1-score of 0.88 for predicting active and passive cosponsorship.
Automatic Music Transcription (AMT) consists in automatically estimating the notes in an audio recording, through three attributes: onset time, duration and pitch. Probabilistic Latent Component Analysis (PLCA) has become very popular for this task. PLCA is a spectrogram factorization method, able to model a magnitude …
Anonymization reduces economic signal extraction from financial texts.
problem Reducing meaningful economic signals from financial texts due to anonymization.
method Analyzed the impact of anonymization on textual understanding and economic signal extraction.
result Information loss due to anonymization is severe and pervasive, outweighing its benefits in certain financial applications.
Black-box adversarial examples improve ASR system accuracy.
problem Improving ASR system accuracy through targeted adversarial examples.
method Combining genetic algorithms and gradient estimation for black-box attacks.
result Achieved 89.25% targeted attack similarity with 94.6% audio file similarity.
Framework ranks sectors influenced by Indian Union Budgets.
problem Real-time analysis of budgetary impacts on sector-specific equity performance.
method Fine-tuned embeddings and language models for sector identification and performance ranking.
result 0.997 NDCG score in predicting sector ranks based on post-budget performances.