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.
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.
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.
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.
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.
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.
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.
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.
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.
Classifies Lie groups acting on compact Lorentz manifolds.
problem Classifying Lie groups acting on compact Lorentz manifolds.
method Classification up to local isomorphisms.
result Classification of Lie groups without compact factors.
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 groups defined that act on trees without repeating.
problem Understanding groups acting on trees without repeating.
method Developed a new concept of acylindrically arboreal groups and classified specific groups.
result Provided examples of groups with tree actions but no non-elementary acylindrical actions.
DAG-LSTM improves DA classification in group chats.
problem DA classification in multi-party conversations.
method Directed-Acyclic-Graph LSTM (DAG-LSTM) exploiting turn-taking structure.
result DAG-LSTM outperforms existing methods by 0.8% in accuracy and 1.2% in macro-F1 score.
New method clusters tasks for deep learning to improve multi-task and few-shot learning.
problem Uncertainty and asymmetry in task similarity matrices affect clustering accuracy.
method Proposes a matrix completion technique to overcome limitations of task similarity matrices.
result The proposed algorithm can accurately recover task clusters with high probability.
Topology aids in solving machine learning classification problems.
problem Machine learning classification problems.
method Classical topology applied to neural networks.
result Topology guides neural network architecture and training.
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).
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.
Study of groups acting on complex projective varieties.
problem Classifying groups of birational transformations on complex projective varieties.
method Free, properly discontinuous, cocompact action on open sets of complex projective varieties.
result Classification in dimension two.
One computes the cohomology of the projective embedding of sl(m+1,R) acting on the differential operators on densities on R^m of various weights. This cohomology is non vanishing only for some special critical values of the weights. This allows us first to explain some strange feature pointed out by Gargoubi in his cla…
We show that a closed simply connected 8-manifold (9-manifold) of positive sectional curvature on which a 3-torus (4-torus) acts isometrically is homeomorphic to a sphere, a complex projective space or a quaternionic projective plane (sphere). We show that a closed simply connected 2m-manifold (m>4) of positive section…
Simplified proof of sphere group classification.
problem Classifying finite groups acting on spheres.
method Simplified proof and removal of redundancy.
result Improved classification of sphere groups.
We classify pairs (M,G) where M is a 3--dimensional simply connected smooth manifold and G a Lie group acting on M transitively, effectively with compact isotropy group.
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.
The main result of the paper is the complete classification of the compact connected Lie groups acting coisotropically on complex Grassmannians. This is used to determine the polar actions on the same manifolds.
Study classifies Persian speech acts for better understanding of text intent.
problem Understanding the intended function of Persian texts.
method Dictionary-based statistical technique using WordNet for SA recognition.
result Proposed method achieved state-of-the-art accuracy of 0.95 for Persian SA classification.
We characterize isometric actions on compact Kaehler manifolds admitting a Lagrangian orbit, describing under which condition the Lagrangian orbit is unique. We furthermore give the complete classification of simple groups acting on the complex projective space with a Lagrangian orbit, and we give the explicit list of …
We study higher rank Cartan actions on compact manifolds preserving an ergodic measure with full support. In particular, we classify actions by Rk with k≥3 whose one-parameter groups act transitively as well as nondegenerate totally nonsymplectic $\Zk$-actions for k≥3.
We define the notion of characteristic classes for supermanifolds endowed with a homological vector field Q. These take values in the cohomology of the Lie derivative operator LQ acting on arbitrary tensor fields. We formulate a classification theorem for intrinsic characteristic classes and give their explicit de…
This paper investigates some actions "à la Johnson" on the set, denoted by E, of Spin-structures which are interpreted as special double-coverings of a trivial S1−fibration over a non-orientable surface Ng+1. The group acting is first a group of orthogonal isomorphisms assoiciated to Ng+1. A secon…
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.
BNNs enhance reservoir computing by acting as generalization filters.
problem Understanding how BNNs integrate with reservoir computing.
method Optogenetics and calcium imaging to record BNNs, reservoir computing framework.
result BNNs improve reservoir computing performance through generalization.
Let (M,ω) be a connected symplectic manifold on which a connected Lie group G acts properly and in a Hamiltonian fashion with moment map $μ:M \lra \mf g^*$. Our purpose is investigate multiplicity-free actions, giving criteria to decide a multiplicity freenes of the action. As an application we give the complete cl…
In this paper we give a classification of closed and connected Lie groups, up to conjugacy in Iso(R13), acting by cohomogeneity one on the three dimensional Minkowski space R13 in both cases, proper and nonproper actions. Then we determine causal characters of the orbits.
Classification of torus homeomorphisms on fine curve graph completed.
problem Classifying actions of torus homeomorphisms on fine curve graph.
method Proof involving slow rotation sets for torus homeomorphisms.
result Actions of torus homeomorphisms on fine curve graph classified.
Poincare function counts geometric moduli, solving Arnold's conjecture.
problem Counting moduli in differential-geometric problems.
method Derives Poincare function properties and solves Arnold's conjecture.
result Derives new formulae for differential invariants and classification problems.
In the present paper we introduce the notion of complex asystatic Hamiltonian action on a Kähler manifold. In the algebraic setting we prove that if a complex linear group G acts complex asystatically on a Kähler manifold then the G-orbits are spherical. Finally we give the complete classification of complex asysta…