End-to-end neural network improves QbE-STD in multilingual speech search.
problem Query by example spoken term detection in zero-resource scenarios.
method Use of multilingual bottleneck features and CNN for pattern matching, integrated into a fully neural network framework.
result CNN-based matching outperforms DTW-based matching using bottleneck features.
CNN-DTW system improves keyword spotting in under-resourced languages.
problem Keyword spotting in nearly zero-resource languages.
method Multilingual bottleneck features, CNN-DTW, DTW template matching, convolutional neural network.
result Multilingual BNFs improve CNN-DTW by 10.9%.
Improved ASR-free keyword spotting in under-resourced languages.
problem Dynamic time warping for keyword spotting in languages with limited resources.
method Multilingual bottleneck extractor and correspondence autoencoder integration.
result More than 11% absolute improvement in ROC AUC over MFCCs.
HMS-BERT detects cyberbullying in multiple languages and labels.
problem Multilingual and multi-label cyberbullying detection challenges.
method Hybrid multi-task self-training framework using BERT.
result Strong performance on multi-label and main classification tasks.
BERT models can classify multilingual party manifestos across different dimensions.
problem Costly manual annotation of large corpora in social science.
method Domain transfer across geographical locations, languages, time, and genre using fine-tuned transformer models.
result BERT models can be applied to future data with similar performance.
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora…
Model learns multilingual word representations robust to noise.
problem Learning multilingual word representations in noisy environments.
method Fit a generative latent variable model to a multilingual dictionary.
result Competitive multilingual embeddings across various tasks.
Unified pipeline predicts equipment anomalies with high precision and reduced false positives.
problem Predicting equipment anomalies before failures using small models.
method Triplet Feature Fusion combining statistical, time-series, and text embeddings.
result Achieves high precision and reduced false positives.
Proposes a multilingual email segmentation benchmark and model.
problem Lack of multilingual email zoning corpora and models.
method Analysis of existing corpora, development of multilingual benchmark, introduction of OKAPI model.
result OKAPI model achieves state-of-the-art performance in English and generalizes well to unseen languages.
Multilingual LM improves low-resource language modeling.
problem Lack of data for many languages and domains.
method Jointly trained multilingual neural language model with shared parameters.
result Significant improvements in conversational data domain with limited training data.
We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously discover both a matching between the languages and multilingual latent topics. We d…
New ASR system handles multiple languages without needing language-specific encoding.
problem Joint training of data-rich and data-scarce languages in a single model.
method Transforms all languages to a single writing system through transliteration, separating modeling and rendering.
result Language-agnostic multilingual ASR system reduces WER up to 10% over language-dependent models.
This study compares traditional ML and deep learning for classifying multilingual user feedback.
problem Classifying multilingual user feedback for software development teams.
method Comparison of traditional machine learning and deep learning approaches.
result Traditional machine learning can achieve comparable results to deep learning for multilingual user feedback classification.
Simple framework decouples word alignment and multilingual embedding mapping.
problem Learning multilingual embeddings without supervision.
method Two-stage approach: 1) unsupervised word alignment, 2) mapping embeddings to shared space.
result Robust performance across various multilingual tasks, including distant languages.
Improved multilingual speech recognition with low latency for nine Indic languages.
problem Imbalance in training data across languages and low latency in interactive applications.
method Conditioning on a language vector and training language-specific adapter layers.
result Lower word error rate than monolingual E2E models and conventional systems.
Effective multilingual search with instance-based transfer learning.
problem Search in multilingual setting, especially next-sentence prediction and inverse cloze.
method Instance-based transfer learning, analyzing vocabulary overlaps and transitive overlaps.
result Positive transfer on all 35 target languages and two tasks, even with no vocabulary overlap.
Study shows multilingual LLM calibration effects improve model confidence but not accuracy.
problem Improving multilingual language model calibration in low-resource settings.
method Analysis of two multilingual benchmarks using instruction-tuning and label smoothing.
result Model confidence increases in low-resource languages after instruction-tuning but accuracy improvements are marginal.
Despite the growing importance of multilingual aspect of web search, no appropriate offline metrics to evaluate its quality are proposed so far. At the same time, personal language preferences can be regarded as intents of a query. This approach translates the multilingual search problem into a particular task of searc…
Proposes using Wasserstein barycenter for better multilingual alignment.
problem Finding word-to-word translations between multiple languages without parallel data.
method Uses Wasserstein barycenter as a more informative pivot language, minimizing pairwise transportation costs.
result Demonstrates state-of-the-art performances on standard benchmarks.
Method aligns multilingual news for better stock return prediction.
problem Losing nuances in multilingual news translations.
method Optimal transport for sentence alignment.
result Aligned sentences correlate better with stock returns.
Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e.g. infered with the help of GIZA++) between translated sentences, in order to align the word embeddings in different languages. In this workshop paper, we investigate an autoencoder model for learning multil…
Proposes a method to extract robust features that improve classifier robustness.
problem Improving classifier robustness to small perturbations in input space.
method Introduces an additional penalty term in the information bottleneck framework to minimize Fisher information, optimizing a variational bound using stochastic gradient descent.
result Optimally robust features are jointly Gaussian, and the method produces classifiers with increased robustness to perturbations.
Scientific publications have evolved several features for mitigating vocabulary mismatch when indexing, retrieving, and computing similarity between articles. These mitigation strategies range from simply focusing on high-value article sections, such as titles and abstracts, to assigning keywords, often from controlled…
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is …
ATD measures language distance using neural models, recovering linguistic groupings.
problem Lack of a unified quantitative measure for cross-linguistic distance.
method Pretrained multilingual language models, attention mechanisms, optimal transport.
result ATD quantifies representational distance between languages, recovering linguistic groupings.
Improved LID for multilingual speakers using context-aware models.
problem Low accuracy for languages spoken by multilingual speakers, especially with accented speech.
method Coarser-grained acoustic model and integration with interaction context signals.
result Average 97% accuracy across all language combinations, 60% improvement in worst-case accuracy.
Paper develops multilingual job classification for ISCO and KZiS.
problem Classifying job advertisements for accurate occupation coding.
method Transformer architecture for hierarchical multi-class classification.
result Hierarchical structure improves prediction accuracy by 1-2 percentage points.
mGENRE improves multilingual entity linking with autoregressive sequence prediction.
problem Multilingual Entity Linking (MEL) task of resolving language-specific mentions to a multilingual Knowledge Base.
method Autoregressive sequence-to-sequence system that cross-encodes mention strings and entity names.
result Over 50% improvement in average accuracy in zero-shot settings.
Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.
problem Challenges in learning graph representations due to structure and feature information.
method GIB is an information-theoretic principle that balances expressiveness and robustness by maximizing mutual information between representation and target, while constraining mutual information with input data.
result GIB-based models are more robust to adversarial attacks, achieving up to 31% improvement.
Efficient DSP features reduce speech recognition memory usage.
problem Limited memory on DSPs for speech recognition.
method Developed efficient bottleneck features (BNFs) for DSPs.
result Reduced speech recognition memory usage by 10x with minimal accuracy loss.
Triangulation filters spurious circuits in multilingual models.
problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.
Survey reviews code-switched speech and language processing.
problem Processing code-switched text and speech for multilingual communities.
method Reviews computational approaches and lists available resources.
result Essential for building intelligent agents that interact in multilingual settings.
Adaptive scheduling improves multilingual neural machine translation models.
problem Training models on multiple tasks with uniform or proportional sampling leads to poor performance trade-offs.
method Exploring non-adaptive and adaptive task scheduling, including implicit schedules.
result Adaptive schedules improve model performance for low-resource tasks without negatively affecting high-resource tasks.
Improves unsupervised domain adaptation by enforcing feature extractor to focus on task-relevant information.
problem Leveraging label information from source domain for accurate target domain models without labels.
method Variational Information Bottleneck (VBDA) method that explicitly enforces feature extractor to ignore irrelevant task factors.
result Significantly outperforms state-of-the-art methods across three domain adaptation benchmark datasets.
GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.
problem Poor generalization of deep neural networks to unseen environments.
method Proposes a gated information bottleneck (GIB) approach that dynamically drops spurious correlations and selects task-relevant features.
result GIB outperforms other IB approaches in adversarial robustness and OOD detection.
This paper tackles multilingual speech processing by optimizing conflicting objectives hierarchically.
problem Training models for multilingual, multi-task speech processing is hampered by conflicting objectives.
method Investigates three multi-objective MSP formulations and introduces a lightweight layer-selection mechanism.
result A bi-level recipe outperforms standard flat optimization in state-of-the-art MSP models.
EvoMSA unifies multilingual sentiment analysis systems.
problem Multilingual sentiment analysis in various languages.
method Genetic Programming-based classifier combining multiple text classifiers.
result EvoMSA performs competitively in multiple sentiment analysis competitions.
Proposes a multi-task learning model using variational information bottleneck.
problem Balancing performance and robustness across different tasks in multi-task learning.
method Variational Information Bottleneck (VIB) architecture for multi-task learning.
result The proposed model achieves competitive prediction accuracy under adversarial attacks.
MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.
problem Performance limitations of MPNNs under heterophily and structural bottlenecks.
method A statistical framework decomposing model performance into SNR components and proving bounds on sensitivity.
result Optimal graph structures for maximizing higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.
Study on feature learning in Leaky ResNets, explaining bottleneck structure.
problem Understanding feature learning in deep neural networks.
method Lagrangian and Hamiltonian reformulation of representation geodesics.
result Emergence of a bottleneck structure in large effective depth networks.
VIBI interprets black-box systems by selecting key features that are both brief and comprehensive.
problem Lack of concise and comprehensive explanations for black-box decision systems.
method VIBI uses the information bottleneck principle to select key features that are maximally compressed and informative.
result VIBI provides more concise and comprehensive explanations compared to existing methods.
CNNs use a bottleneck structure to focus on a few frequencies, affecting function representation.
problem Understanding how CNNs focus on specific frequencies in their feature learning.
method Defined Convolution Bottleneck (CBN) structure, measured CBN rank, and analyzed parameter norms.
result Parameter norm scales with depth and CBN rank, and networks with optimal parameters exhibit this structure.
Paper tackles zero-shot translation by encouraging consistent agreement in models.
problem Challenges of generalizing multilingual translation without parallel data.
method Reformulated as probabilistic inference, introduced consistent agreement-based training.
result Agreement-based learning improves zero-shot translation by 2-3 BLEU points.
New method uses information bottleneck to quantify variable importance in neural networks.
problem Quantifying the importance of individual input variables in neural networks.
method Restricting the flow of information by adding noise to intermediate feature maps.
result Our method outperforms all baselines in five out of six settings.
Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information b…
Large neural networks learn low-dimensional representations that balance complexity and regularity.
problem Understanding the tradeoff between low-dimensional representations and complexity in deep neural networks.
method Computed finite depth corrections to reveal a measure of regularity that bounds the pseudo-determinant of the Jacobian.
result Proved the conjectured bottleneck structure in learned features as network depth increases, showing almost all hidden representations are approximately low-dimensional and weight matrices have singular values close to 1.
A graph neural network detects beneficial feature interactions for recommender systems.
problem Feature interactions are crucial but not all are beneficial for recommendation accuracy.
method Graph neural network with L0 activation regularization for edge prediction.
result The model outperforms baselines and automatically identifies beneficial feature interactions.
In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the voca…