Expanding spoken language understanding to handle complex entities and intents.
problem Handling compound entities and intents in spoken language understanding.
method Introducing a domain-agnostic shallow parser that handles linguistic coordination, learning domain-independent and slot-independent features.
result The model learns to segment conjunct boundaries of various phrasal categories and improves generalization across different slot types using adversarial training.
Improves domain classification across multiple locales with shared language.
problem Improves domain classification accuracy in Spoken Language Understanding across multiple locales with shared language.
method Selective multi-task learning to create a joint representation of utterances over locales with different sets of domains.
result The proposed approach outperforms other baselines models especially when classifying locale-specific domains and low-resourced domains.
New model learns coupled representations for domains, intents, and slots.
problem Representation learning for domains, intents, and slots in spoken language understanding.
method Proposes a model that learns coupled representations by aggregating slot and intent representations based on their hierarchical relationships.
result Improved performance on contextual cross-domain reranking task.
The paper provides theoretical insights into deep domain adaptation.
problem Closing the gap between source and target domains in deep domain adaptation.
method A rigorous framework to explain transfer learning and minimize loss.
result First theoretical result characterizing joint space and transfer learning gain.
Develops a logifold structure for understanding datasets.
problem Understanding and classifying complex datasets.
method Local-to-global approach using measure-theoretical models.
result Improves accuracy in data classification problems.
Efficient model for foggy scene understanding in vehicles.
problem Challenging scene understanding and segmentation under foggy conditions.
method Domain adaptation and illumination-invariant image transformation.
result Outperforms state-of-the-art models in foggy scene understanding.
ELICA helps analysts understand unfamiliar domains by extracting relevant terms.
problem Communication barriers between analysts and stakeholders in unfamiliar domains.
method ELICA uses WFSTs to dynamically extract and label requirements-relevant knowledge from text and non-linguistic cues.
result ELICA supports analysts in understanding and eliciting requirements from unfamiliar domains.
Transfer learning improves understanding of users on new Web platforms.
problem Lack of knowledge about novel phenomena on new Web platforms due to data sparsity.
method TraNet, a transfer learning-based approach, adapts knowledge from one domain to another.
result TraNet outperforms other approaches in transferring knowledge about users across different Web platforms.
Two KG-based methods explain transfer learning in CNN and ZSL.
problem Uninterpretable transfer learning for non-ML experts.
method Knowledge Graph-based explanation for transferability and model justification.
result Rich, human-understandable explanations for transfer learning.
In this paper we give two examples of sequences of embedded minimal planar domains in R3 which converge to singular laminations of R3. In contrast with the situation for embedded minimal disks, these examples do not arise from complete embedded minimal planar domains and highlight some of the su…
Expanding self-supervised learning to diverse domains reveals Rotation's semantic superiority.
problem Limited self-supervised learning experiments on diverse domains.
method Experimented on various domains (satellite, textural, biological) using popular self-supervised methods.
result Rotation task is semantically most meaningful, with other tasks relying on distribution rather than semantic understanding.
Unified QuesNet learns comprehensive representations for diverse test questions.
problem Lack of labeled data for test questions in online learning systems.
method Unified framework and two-level hierarchical pre-training algorithm for unsupervised learning of heterogeneous question representations.
result QuesNet effectively learns comprehensive question representations and outperforms existing methods.
Visuals in scientific papers are used to express complex ideas; this study uses them to identify knowledge domains.
problem Scientific figures are underutilized in literature analysis.
method Encoded scientific figures into visual signatures and used distances between signatures to compare communities of practice.
result Figures can differentiate knowledge domains as effectively as text or citation patterns.
Study finds neural dialog models struggle with conversational tasks.
problem Insufficient understanding of dialog by neural models.
method Analysis of internal representations and evaluation of model performance.
result Neural dialog models lack key conversational skills like answering questions and inferring contradiction.
Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithms with simple heuristic exploration strategies that have few formal guarantees, achieve surprising success in many domain…
MA-DST improves multi-domain dialog state tracking.
problem Accurate multi-domain dialog state tracking in natural language interfaces.
method Multi-attention based architecture to encode conversation history and slot semantics.
result Improves joint goal accuracy by 5% in full-data setting and up to 2% in zero-shot setting.
InvestLM is a financial domain LLM tuned on LLaMA-65B for investment advice.
problem Improving financial text understanding and advice generation for investment.
method Curated financial instruction dataset, LLaMA-65B, less-is-more-for-alignment approach.
result InvestLM provides comparable responses to state-of-the-art commercial models.
Study introduces KorFinMTEB for Korean financial texts, revealing model limitations.
problem Limited evaluation benchmarks for low-resource domains, especially Korean.
method Developed KorFinMTEB, a tailored benchmark for Korean financial texts.
result Models perform better on translated benchmarks than on domain-specific ones.
CoNDA improves domain classification for IPDAs by incorporating new and personalized domains.
problem Continuous learning for new and personalized domains in IPDAs.
method Neural network based approach for incremental learning.
result CoNDA achieves high accuracy and outperforms baselines.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
Study improves financial chatbot command understanding.
problem Improving chatbot command understanding for financial contexts.
method Sequence to sequence learning and Multi-Task Learning techniques.
result Enhanced performance in intent and content extraction.
New technique explains convergence in ML models with data modifications.
problem Understanding convergence of ML models under data changes.
method Analogue of Fatou's lemma and gamma-convergence.
result Relevance and applications in general ML tasks and domain adaptation.
System helps scientists visualize deep learning model of x-ray images.
problem Understanding complex x-ray scattering images with multiple attributes.
method Interactive visualization system in feature space and classification output.
result Users can explore and compare images and attributes flexibly.
RuleMatrix visualizes machine learning models for non-experts.
problem Making machine learning models transparent and interpretable for non-expert users.
method Extracts rule-based knowledge from model behavior and presents it in an interactive matrix visualization.
result RuleMatrix helps non-expert users understand and validate machine learning models.
CSD learns a common component for domain generalization, outperforming existing methods.
problem Training models to generalize across unseen domains.
method CSD decomposes the model into a common and specific component, discarding the latter.
result CSD outperforms state-of-the-art domain generalization methods.
This paper explores conditions for neural networks to extrapolate to new domains.
problem Understanding when neural networks can extrapolate to unseen domains.
method Analyzes conditions for nonlinear models to extrapolate under specific distribution shifts.
result Neural networks of the form f(x)=∑fi(xi) can extrapolate if feature covariance is well-conditioned. The paper studies fundamental domains in H^3 and their associated polyhedra.
problem Understanding the relationship between polyhedra and groups associated with fundamental domains in H^3.
method Analyzes torsion-free groups and edge classes of abstract polyhedra, proving results about group properties and edge classes.
result Classifies fundamental domains on the cube with torsion-free groups and provides insights into polyhedra and groups.
New method improves domain generalization by aligning causal mechanisms across domains.
problem Improving model's ability to generalize across different distributions.
method Introduces invariance of average causal effect of features to labels, regularizing training approach.
result Demonstrates superior performance on benchmark datasets compared to state-of-the-art methods.
Paper explores unsupervised transfer learning for SLU, improving model performance with unlabeled data.
problem Improving SLU model performance with limited labeled data.
method Uses ELMo embeddings for unsupervised pre-training and ELMo-Light for faster pre-training. Combines unsupervised and supervised transfer techniques.
result Unsupervised pre-training on unlabeled data significantly improves SLU performance, even outperforming conventional supervised transfer.
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
problem Standard fine-tuning degrades pretraining domain representations.
method Complements task-specific loss with adversarial objective.
result AFTER leads to improved performance on various NLP tasks.
The paper examines domain generalization algorithms and finds empirical risk minimization performs well.
problem Comparing domain generalization algorithms is difficult due to inconsistent experimental conditions.
method Implemented DomainBed, a testbed for domain generalization with seven datasets and model selection criteria.
result Empirical risk minimization shows state-of-the-art performance across all datasets.
New nodal domain theorems for symmetric matrices via signed graphs.
problem Establish nodal domain theorems for symmetric matrices.
method Explore signed graph structure to define nodal domains for any function.
result Improved lower bound estimates for the number of strong nodal domains.
Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.
problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.
We study the Cauchy data spaces of the strongly Callias-type operators using maximal domain on manifolds with non-compact boundary, with the aim of understanding the Atiyah-Patodi-Singer index and elliptic boundary value problems.
Proposes a new method for handling domain shift in samples with biases in both covariates and labels.
problem Domain shift in samples with biases in both covariates and labels.
method Factorizable Joint Shift (FJS) and Joint Importance Aligning (JIA).
result Our method can handle co-existence of sampling bias in covariates and labels.
TIM framework uses LLMs and domain experts to infer DeFi user transaction intents.
problem Challenges in understanding user intent in DeFi transactions due to complex interactions and opaque logs.
method TIM framework leverages a DeFi intent taxonomy, multi-agent LLM system, and a Meta-Level Planner.
result TIM significantly outperforms existing methods in inferring user transaction intents.
Self-training improves gradual domain adaptation with unlabeled data.
problem Improving machine learning models' adaptability to gradually shifting data distributions.
method Proved upper bounds on self-training error, highlighted the importance of regularization and label sharpening, and demonstrated algorithmic insights.
result Self-training works well for gradual shifts, especially with small Wasserstein-infinity distance.
Proposes a new approach to improve disease prediction by considering who generates the data.
problem Improving disease prediction across different datasets considering who generates the data.
method Formulates domain adaptation as a multi-source hierarchical Bayesian framework.
result Improves prediction accuracy in target datasets with largely unlabelled data.
An essential problem in domain adaptation is to understand and make use of distribution changes across domains. For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains. By explicitly…
Hessian alignment improves OOD generalization in deep learning.
problem Improving deep learning models' ability to generalize to out-of-distribution data.
method Analyzed Hessian and gradient alignment for domain generalization using recent OOD theory.
result Hessian alignment methods achieve promising performance on various OOD benchmarks.
timeXplain bridges AI and time series, making predictions understandable.
problem Making time series classifier predictions interpretable.
method Developed a framework that combines time series data with model-agnostic explainers.
result timeXplain improves the interpretability of time series classifiers.
RL benefits from natural language understanding, surveying recent advances.
problem Exploit natural language to enhance RL performance.
method Survey recent research integrating natural language with RL.
result Natural language can improve RL's world knowledge and task transfer.
DGSAM improves domain generalization by minimizing individual sharpness.
problem Improving domain generalization models that perform well on unseen target domains.
method Shifts DG paradigm toward minimizing individual sharpness across source domains.
result DGSAM reduces performance variance across domains with less computational overhead.
PLIs improve classifier performance by fine-tuning latent representations.
problem Difficult interpretation of high-dimensional latent representations in neural networks.
method Back-propagation of manual changes to low-dimensional embeddings using t-distributed stochastic neighbourhood embeddings.
result Manual separation of class clusters in latent space enhances classifier performance.
Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…
Personalized explanations improve understanding of machine learning models.
problem Improving human understanding of machine learning models and decisions.
method Deriving a conceptualization of personalized explanation, categorizing explainee data, identifying key properties, and introducing new measures.
result Identification of three key properties amendable to personalization: complexity, decision information, and presentation.
Deep architecture learns transferable features for robust speech emotion recognition.
problem Robust and discriminative features for diverse speech emotion domains.
method Jointly uses CNN for domain-shared features and LSTM for domain-specific emotion classification.
result Transferable features provide gains up to 18.4% in speech emotion recognition.