Model uses RNN and CNN for sequence-based short-text classification.
problem Lack of sequence consideration in short-text classification.
method Recurrent and Convolutional Neural Networks for sequence data.
result Achieves state-of-the-art results on three datasets.
This paper introduces a new method for dialog state tracking.
problem Accurately estimating dialog state from noisy observations.
method Bilinear algebraic decomposition model with collective matrix factorization.
result The proposed tracker performs well compared to state-of-the-art trackers.
GP optimizes ANN hyperparameters for dialog act classification.
problem Optimizing ANN hyperparameters for better performance.
method Bayesian optimization with Gaussian processes.
result GP reduces computational time by 4x and improves dialog act classification.
Solves TOD systems' query annotation problem without explicit annotations.
problem Training TOD systems without explicit KB query annotation.
method Reinforcement learning (RL) and pipelined approach for query prediction and system training.
result Improved RL agent with modifications for TOD tasks.
Paper reduces dialog policy optimization with RL methods.
problem Sample inefficiency in RL for optimizing dialog policies.
method Two RNNs for prediction and experience replay.
result Reduces dialog episodes by about a third.
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.
A new method for dialog state tracking using memory networks.
problem Accurately estimate the current dialog status from noisy observations.
method End-to-End Memory Network (MemN2N) for hidden state variable inference.
result The proposed tracker gives encouraging results on DSTC-2 dataset.
Improves generative Visual Dialog by asking diverse questions.
problem Generative Visual Dialog models degrade after a few rounds of interaction.
method Introduce a simple auxiliary objective to incentivize Qbot to ask diverse questions.
result Better dialog diversity, consistency, fluency, and detail with improved image relevance.
A new neural network models discourse relations with latent variables.
problem Jointly modeling discourse relations and word sequences.
method Latent variable recurrent neural network for discourse relations.
result Model outperforms state-of-the-art alternatives on discourse classification tasks.
HRL improves open-domain dialog models by optimizing long-term conversational goals.
problem Challenges in open-domain dialog generation, including repetitive outputs, difficulty tracking conversational goals, and inappropriate text.
method Proposes VHRL, a hierarchical reinforcement learning approach using policy gradients to tune utterance-level embeddings of a variational sequence model.
result Significant improvements in human evaluation and automatic metrics over state-of-the-art dialog models.
This study compares hierarchical and non-hierarchical models for open-domain multi-turn dialog generation.
problem Which kind of models (hierarchical or non-hierarchical) is better for open-domain multi-turn dialog generation?
method Systematically compared nearly all representative hierarchical and non-hierarchical models over the same experimental settings.
result Nearly all hierarchical models are worse than non-hierarchical models in open-domain multi-turn dialog generation, except for HRAN.
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.
Neural Assistant integrates knowledge reasoning and dialogue generation in a single model.
problem Challenges in task-oriented dialog systems, including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction.
method Develops a single neural network model that jointly predicts text responses and actions from conversation history and external knowledge.
result The model learns to reason on external knowledge with weak supervision, improving factual accuracy and language generation performance.
Pretrained model improves visual dialog performance.
problem Improving performance in visual dialog tasks.
method Pretrained ViLBERT model on vision-language datasets, fine-tuned on VisDial.
result Best model outperforms prior work by more than 1% on NDCG and MRR.
Paper proposes a self-play method to approximate human evaluation of conversational agents.
problem Challenges in evaluating open-domain dialog systems.
method Self-play scenario with sentiment and semantic coherence proxies.
result Self-play metric correlates significantly with human ratings (r>.7, p<.05).
BoSsNet learns language and knowledge separately, improving task-oriented dialog performance.
problem End-to-end neural networks struggle with KB changes in task-oriented dialogs.
method Encoder-decoder architecture with Bag-of-Sequences memory.
result BoSsNet outperforms state-of-the-art models with >10% improvement on bAbI OOV test sets.
Novel memory access mechanism improves complex reasoning tasks.
problem Challenges in multi-fact question-answering and positional reasoning.
method Gated End-to-End Memory Network architecture with a novel access regulation mechanism.
result Significant improvements on challenging tasks in the 20 bAbI dataset and DSTC-2.
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.
Novel RL algorithms learn from human interaction data without exploration.
problem Efficiently learning from off-policy data in reinforcement learning.
method Developed off-policy batch RL algorithms using KL-control and dropout-based uncertainty.
result Successfully learned multiple reward functions from human interaction data.
FastSGT improves accuracy in BERT-based DST for SGD datasets.
problem Dialog State Tracking in goal-oriented dialogue systems.
method BERT-based model with two carry-over procedures and multi-head attention.
result Significantly improved accuracy compared to baseline model.
New method for explaining dialogue response generation models.
problem Interpreting sequence generation models, especially dialogue response generation.
method Local Explanation of Response Generation (LERG) method.
result LERG improves dialogue response generation explanations compared to existing methods.
Develops a technique to audit text-generation models trained on personal data.
problem Enforce data-protection regulations like GDPR and detect unauthorized data usage.
method Black-box auditing method that queries a model to detect if a user's data was used for training.
result Successfully audits well-generalized models without overfitting to training data.
End-to-end deep learning detects emotions in real-life emergency calls.
problem Recognizing emotions in real-life emergency call center recordings.
method Used an end-to-end deep learning architecture trained on IEMOCAP and CEMO datasets.
result Obtained 45.6% Unweighted Accuracy Recall on CEMO with 4 classes, 76.9% on 2 classes (Anger, Neutral).
Paper introduces a dynamic reference frame strategy to predict events with a buffer time.
problem Lack of time buffer for predictions to enable timely action.
method Introduces a new concept of dynamic reference frame creation.
result Enables organizations to act on predictions with a buffer time.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
Scl in groups acting on trees is rational and converges to limits.
problem Understanding stable commutator length in group actions on trees.
method Analyzing groups acting on trees with cyclic stabilizers, focusing on stable commutator length and its limits.
result Stable commutator length is rational and converges to limits in surgery families.
Modeling long-range context for multi-function utterances in dialogues.
problem Complex dependencies across dialogue turns in long utterances.
method Adapted Convolutional Recurrent Neural Network (CRNN) to model interactions between utterances.
result Significantly outperforms existing work on CDA recognition on a tech forum dataset.
Model learns tensor representations from imperfect multimodal data.
problem Learning from imperfect multimodal data with noise or missing entries.
method Tensor rank minimization to regularize rank of tensor representations.
result Model effectively learns tensor representations from imperfect data.
New method improves dialogue agents focusing on simple utterances.
problem Dialogue agents often focus on simple utterances and suboptimal policies.
method Tempered Policy Gradient (TPG) methods to improve dialogue performance.
result Significant improvements in dialogue performance, especially in producing convincing utterances.
Proposes a VAE with a discrete bottleneck for better text generation.
problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.
APo-VAE generates text in hyperbolic space for better hierarchical representation.
problem Lack of hierarchical structure in Euclidean embeddings for natural language.
method Adversarial Poincare Variational Autoencoder (APo-VAE) in hyperbolic latent space.
result APo-VAE outperforms Euclidean VAEs in capturing latent language hierarchies.
Derives formulae for general permutation equivariant layers and presents a second order graph variational encoder.
problem Tackles the limitation of previous equivariant neural networks by considering permutations of matrices.
method Derives formulae for general permutation equivariant layers, including matrix permutations. Presents a second order graph variational encoder.
result Latent distribution of equivariant generative models must be exchangeable.
Cyclical Annealing Schedule improves VAE performance in NLP tasks.
problem KL term vanishing in VAEs with auto-regressive decoders.
method Cyclical Annealing Schedule to vary β over multiple cycles.
result Progressive learning of meaningful latent codes improves VAE performance.
Autoencoder learns group representations from actions, improving future prediction accuracy.
problem Learning internal models of interactions with the real world.
method Homomorphism autoencoder with group representation trained on equivariance-derived loss.
result Agents can predict future actions with improved accuracy.
The paper addresses decision making with partially calibrated forecasts, offering a robust approach.
problem Developing a decision-making strategy for forecasts that are only partially calibrated.
method A minimax approach to mapping predictions to actions, considering worst-case distributions.
result The minimax optimal decision rule is to trust predictions and act accordingly, even for partially calibrated forecasts.
UQE uses LLMs to analyze unstructured data efficiently.
problem Efficient analytics on unstructured data.
method Proposes UQE, a query engine that uses LLMs to interpret UQL queries.
result Demonstrates efficient analytics on various unstructured data types.
Model shows disclosure reduces trading costs in oligopolistic markets.
problem Reducing trading costs in oligopolistic markets with imperfect competition.
method Developed a multi-period Kyle-type model with mandatory disclosure and imperfect competition, proving existence and uniqueness of a linear equilibrium.
result Disclosure lowers trading costs by reducing price impact, and its marginal benefit is larger when competition is weak.
AI model predicts stock prices using social media data and hybrid neural networks.
problem Predicting stock price movements during the COVID-19 pandemic.
method Integrates social media trends and historical stock data using a hybrid CNN-BLSTM framework.
result The proposed framework outperforms traditional models in predicting stock price movements.
Study predicts when ALS patients will lose speech, swallowing, etc. based on covariates.
problem Predicting when ALS patients will experience significant functional decline.
method Multi-event survival analysis, covariate-based models.
result Covariate-based models outperform Kaplan-Meier estimator in predicting time-to-event outcomes.
Advances deep latent variable models for more flexible text generation.
problem Limited representation power of VAEs due to Gaussian assumptions and posterior collapse.
method Develops sample-based variational distributions and an LVM to directly match aggregated posterior to prior.
result Demonstrates improved text generation in various scenarios.
New framework for predicting decisions that influence their own outcomes.
problem Predictions that affect the outcomes they predict, leading to undesirable distribution shift.
method Risk minimization framework combining statistics, game theory, and causality.
result Necessary and sufficient conditions for retraining to converge to a performatively stable point of minimal loss.
ASAC uses actor-critic models to optimize observation selection in medical settings.
problem Optimizing observation selection in costly sequential observation scenarios.
method ASAC framework with selector and predictor networks, using actor-critic models for training.
result ASAC significantly outperforms state-of-the-art methods in real-world medical datasets.
Regularizes predictions to encourage beneficial user actions.
problem Learning models affect user actions, but provide no guarantees.
method Introduces look-ahead regularization to anticipate and encourage beneficial actions.
result Effective in promoting beneficial user actions in real and synthetic data.
TuckER predicts missing facts in knowledge graphs using tensor decomposition.
problem Predicting missing facts in knowledge graphs.
method TuckER uses Tucker decomposition of binary tensor representations.
result TuckER outperforms state-of-the-art models in link prediction.
Conformal prediction sets can lead to unfair outcomes.
problem Disparate impact in decision-making with conformal prediction sets.
method Experiments with human participants to demonstrate disparate impact and propose equalizing set sizes across groups.
result Providing prediction sets that satisfy Equalized Coverage increases disparate impact compared to marginal coverage.
Advances fair representation learning for unknown third-party uses.
problem Mitigating unfair prediction outcomes when representations are used by third parties with unknown objectives.
method Adversarial representation learning to ensure fairness.
result Demonstrated fair transfer learning and maintained utility.
Gold Seeker uses reinforcement learning to select actions that maximize information gain.
problem Active information selection for goal-oriented vision-and-language reasoning.
method Reinforcement learning with policy distributions to represent and reduce uncertainty.
result The method outperforms competitors in visual dialog and visual query generation challenges.
Normalizing Flows improve prediction interval efficiency in CP.
problem Inefficient prediction intervals in CP due to non-uniform error distribution.
method Train a Normalizing Flow to optimize the distance metric between errors and inputs.
result Optimized prediction intervals are more efficient and valid.