Models predict race and ethnicity from names, improving accuracy over census data.
problem Inferring race and ethnicity from names, especially when first names are available.
method Modeling the relationship between characters in a name and race/ethnicity using Long Short-Term Memory.
result Long Short-Term Memory model achieves out-of-sample accuracy of 0.85.
A new RNN architecture 'deductron' for complex character sequences.
problem Complex character sequences requiring long-term memory.
method Constructed a simple writing system and guessed RNN weights.
result Demonstrated that a 3-layer deductron can be trained.
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
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…
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.
Neural model improves text normalization for non-English languages.
problem Improving text normalization in non-English languages with limited data.
method Sequence-to-sequence model with character and word embeddings, using pre-trained word embeddings with subword information.
result Achieved state-of-the-art F1 score on Arabic language correction dataset.
Formula for colored invariants of torus knots linked to Wr algebras.
problem Calculating colored slr invariants of torus knots. method Generalizing Morton's work, formula derivation for invariants and their limits to Wr characters. result Limits of invariants are essentially characters of Wr algebras, modular up to factors. RNN model predicts handwritten characters from accelerometer and gyroscope data.
problem Online handwritten character recognition using sensor data.
method RNN-based neural network trained on gyroscope and accelerometer data.
result High accuracy on test data, achieving character prediction.
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.
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.
Improves text-to-speech speed by interleaving character reading and audio synthesis.
problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.
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.
Develops axiomatic framework for differential cohomology and constructs generalized Cheeger-Simons characters.
problem Differential cohomology in the relative case.
method Axiomatic framework and construction of generalized Cheeger-Simons characters.
result Definition of integration map for fibre with boundary.
A multi-task learning framework improves BioNER performance across different entity types.
problem Limited performance of BioNER systems due to lack of training data for each entity type.
method Multi-task learning framework that collectively uses training data of different entity types.
result Substantially better performance on 15 benchmark BioNER datasets compared to state-of-the-art systems.
Classifies invariant measures on specific character varieties.
problem Classifying invariant probability measures on character varieties.
method Measure disintegration along transverse Lagrangian tori fibrations.
result Ergodic measures are either counting measures on finite orbits or Liouville measures.
Unsupervised model learns word and context embeddings from character sequences.
problem Learning meaningful word and context embeddings from unlabeled data.
method Character-aware neural architecture that jointly learns word and context embeddings.
result Compact encoders achieve high performance in downstream tasks.
Representation mixing combines character and phoneme inputs for flexible TTS synthesis.
problem Limited control over pronunciation in character or phoneme-based TTS systems.
method Representation mixing combines multiple linguistic inputs in a single encoder.
result Flexibility in choosing between character, phoneme, or mixed representations during inference.
In the paper [1] (arXiv:math/0408333) the authors discuss two possible definitions of the relative Cheeger-Simons characters, the second one fitting into a long exact sequence. Here we relate that picture to the one of the relative Deligne cohomology groups, defined via the mapping cone: we show that there are three me…
Study Morse representations in Lie groups, showing specific group structures.
problem Understanding Morse representations in Lie groups.
method Analyzing sequences of Morse representations and their unboundedness.
result Groups with unbounded Morse representations have specific structures.
Researchers describe character varieties for Hopf links, proving geometric properties.
problem Character variety geometry of Hopf links with n twists. method Geometric descriptions of irreducible and totally reducible representations.
result Complete geometric description of SU(2)-character variety for r=2. WideDTA predicts drug-target binding affinity using text-based information.
problem Predicting drug-target binding affinity is a major challenge in drug discovery.
method WideDTA uses chemical and biological textual sequence information, including protein sequence, ligand SMILES, protein domains and motifs, and maximum common substructure words.
result WideDTA outperformed DeepDTA on the KIBA dataset, indicating the word-based sequence representation is a promising alternative.
Paper proposes SA-VAE for generating stylized Chinese characters.
problem Automatic generation of stylized Chinese characters is challenging.
method Proposes Style-Aware Variational Auto-Encoder (SA-VAE) to capture content and style components.
result Shows powerful one-shot/low-shot generalization ability.
The paper certifies projective rigidity for once-punctured torus bundles using twisted Alexander polynomials.
problem Certifying infinitesimal projective rigidity for hyperbolic once-punctured torus bundles.
method Using twisted Alexander polynomials of representations associated with the holonomy.
result The induced action on the tangent space of the character variety matches the group theoretic action.
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.
New method reduces copyright risks in AI-generated images.
problem Copyright issues in AI-generated images.
method Genericization method using originality estimation and PREGen technique.
result PREGen reduces likelihood of generating copyrighted characters by over half.
Unified approach to representation stability and character polynomials.
problem Generalizing representation stability across different groups.
method Axiomatic approach to categories of FI type.
result New types of categories (e.g. FIm) that exhibit stabilization. A theory of differential characters is developed for manifolds with boundary. This is done from both the Cheeger-Simons and the deRham-Federer viewpoints. The central result of the paper is the formulation and proof of a Lefschetz-Pontrjagin Duality Theorem, which asserts that the pairing: Ch^k(X,dX) x Ch^{n-k-1}(X) --…
The paper extends rigidity results for hyperbolic 3-manifolds to ideal points.
problem Volume rigidity at ideal points of character varieties.
method Generalization of rigidity results to ideal points and higher dimensions.
result If a sequence of representations converges to an ideal point, the volumes must stay away from the maximum.
Improved online AED models with multi-stage training and multi-task learning.
problem Enhance performance of online attention-based encoder-decoder models.
method Three-stage training with character encoder, BPE encoder, and attention decoder; multi-task learning at character and BPE levels; transfer learning from bidirectional encoder.
result 35% and 10% relative improvement over baselines for smaller and bigger models, respectively.
LSD framework decomposes variable-length sequences.
problem Sequence recognition with variable-length outputs.
method Training algorithm samples valid extensions; approximate decoding algorithm.
result LSD model reduces WER to 12.9% on Wall Street Journal task.
For three classes of elliptic pseudodifferential operators on a compact manifold with boundary which have `geometric K-theory', namely the `transmission algebra' introduced by Boutet de Monvel, the `zero algebra' introduced by Mazzeo and the `scattering algebra' from [MR95k:58168] we give explicit formulae for the Cher…
We study two notions of relative differential cohomology, using the model of differential characters. The two notions arise from the two options to construct relative homology, either by cycles of a quotient complex or of a mapping cone complex. We discuss the relation of the two notions of relative differential cohomo…
Sum-product networks enhance sequence modeling with higher-order factors.
problem Modeling complex relations in sequence data with first-order models.
method Combining sum-product networks with higher-order linear-chain conditional random fields.
result Improved performance in sequence labeling tasks compared to state-of-the-art methods.
mLSTM improves sequence modeling with better autoregressive density estimation.
problem Improving autoregressive density estimation in sequence modeling.
method Introduces mLSTM, a recurrent neural network combining LSTM and multiplicative recurrent networks.
result mLSTM outperforms standard LSTM and its variants in character-level language modeling tasks.
Develops quantum character theory for complex reductive groups.
problem Quantum analogue of conjugation equivariant D-modules. method Schur-Weyl functor and double affine Hecke algebra.
result Computes endomorphism algebras of quantum Hotta-Kashiwara modules.
A transformer model improves spell correction with hierarchical attention.
problem Improving spell correction accuracy and speed.
method Multi encoder-single decoder transformer architecture with hierarchical attention.
result Significant improvement in CER, WER, and SER error rates.
Study SL(2,C) connections on Seifert-fibered spaces using gauge theory.
problem Counting SL(2,C) connections on Seifert-fibered spaces. method Introduced perturbations of the SL(2,C) Chern--Simons functional and proved a localisation result. result Formulae for the Euler characteristic and Poincaré polynomial of the stable locus of the SL(2,C) character variety of a Seifert-fibered homology 3-sphere. Grapheme ASR improves with G2G model that corrects spelling errors.
problem Rare long-tail words in non-phonemic languages like English.
method Train G2G model on text-to-speech data to rewrite character sequences into phonetically consistent forms.
result Reduces Word Error Rate by 3% to 11% over a strong graphemic baseline.
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.
We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent ne…
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.
The paper studies neck-pinching of CP1-structures on surfaces, describing their limits.
problem Characterizing the degeneration of CP1-structures on surfaces. method Analyzing a path of CP1-structures leaving every compact subset, converging holonomy in the PSL(2, C)-character variety. result The limit of the path Ct is described in terms of developing maps, holomorphic quadratic differentials, and pleated surfaces. We show that the Korevaar-Schoen limit of the sequence of equivariant harmonic maps corresponding to a sequence of irreducible SL2(C) representations of the fundamental group of a compact Riemannian manifold is an equivariant harmonic map to an R-tree which is minimal and whose length function …
Classifies CAD model descriptions and names from product websites.
problem Distinguishing product descriptions from other text and identifying product names.
method Paragraph vectors, character-level LSTM, word embeddings LSTM tagger.
result Promising results for distinguishing product descriptions and names.
A mapping bends Teichmüller spaces into character varieties, preserving symplectic structure.
problem Mapping Fricke-Teichmüller space to character variety of surface representations.
method Bending Fuchsian representations along a fixed measured lamination, proving equivariant symplectic embedding and properness.
result Continuous extension of bending map to Thurston boundary and geometric complexification.
Compact model uses RBMs for sequence classification with fewer parameters.
problem Sequence classification with dynamic models and complex neural networks.
method Rolling RBMs over time for representation learning and temporal inference.
result Outperforms state-of-the-art models in melody and character recognition.
System solves author name ambiguity in e-commerce catalogs.
problem Finding correct author names in e-commerce catalogs with abbreviations and spelling variants.
method Composite system using open data sources and machine learning techniques for natural language processing.
result Top proposal of the system is the normalized author name with 72% accuracy.
We give a surgery formula for the asymptotic behavior of the sequence given by the logarithm of the higher dimensional Reidemeister torsion. Applying the resulting formula to Seifert fibered spaces, we show that the growth of the sequences has the same order as the indices and we give the explicit values for the limits…