Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

13253850 · Oct 202519922001200920182026
48 results for dialogue management

This paper examines methods to estimate uncertainty in neural networks for dialogue policy optimization.

problem Efficient exploration in neural network-based dialogue policy optimization.
method Extensive benchmark of deep Bayesian methods to extract uncertainty estimates from DQN.
result Combining uncertainty estimation methods with DQN improves sample efficiency and user experience.

This paper proposes a benchmarking environment for RL-based dialogue management.

problem Lack of a common benchmarking framework for RL models in dialogue management.
method Developed a set of simulated environments and compared RL models (DQN, A2C, Natural Actor-Critic, GP-SARSA).
result Demonstrated the effectiveness of various RL models in dialogue management.

Reinforcement Learning improves personalized dialogue systems.

problem Personalized dialogue systems that generalize across users.
method Two RL-based approaches: single learner with user context features, and learner per context segmentation.
result RL methods outperform handcrafted systems in financial product recommendation.

Automated dialogue quality evaluation using user satisfaction estimates across multiple domains.

problem Lack of automated and domain-independent dialogue quality evaluation metrics.
method Created a new Response Quality annotation scheme, introduced five domain-independent feature sets, and experimented with six machine learning models.
result Gradient Boosting Regression model achieved best prediction performance, with a 16% relative improvement in binary satisfaction class prediction accuracy.

New metric estimates user satisfaction for dialogue quality evaluation.

problem Sparse and intrusive explicit user feedback for dialogue quality evaluation.
method Created a new Response Quality annotation scheme and developed a turn-level User Satisfaction metric using five domain-independent feature sets and six machine learning models.
result Gradient boosting regression achieved best correlation of ~0.79 between predicted and annotated user satisfaction labels.

Pretraining method enhances dialogue representation learning across various tasks.

problem Scarce labeled data for specific dialogue tasks.
method Multi-task unsupervised pretraining with natural training objectives.
result Significant improvement in downstream tasks without encoder discrimination.

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.

Optimizes dialogue success and length using multi-objective reinforcement learning.

problem Balancing multiple reward components in spoken dialogue systems.
method Structured multi-objective reinforcement learning to find optimal reward weights.
result Optimized reward weights significantly improve dialogue performance across six domains.

We present a dialogue on Funding Costs and Counterparty Credit Risk modeling, inclusive of collateral, wrong way risk, gap risk and possible Central Clearing implementation through CCPs. This framework is important following the fact that derivatives valuation and risk analysis has moved from exotic derivatives managed…

2013-11-30abs ↗pdf ↗

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructi…

2017-05-29abs ↗pdf ↗

DLGNet improves dialogue response generation by leveraging transformer architecture.

problem Lack of relevance, diversity, and coherence in dialogue responses.
method Transformer-based model for dialogue response generation, incorporating long-range structures and random paddings.
result Significant improvements over state-of-the-art models on multiple datasets.

The paper improves dialogue quality estimation using a novel user satisfaction model.

problem Improving dialogue quality estimation in spoken dialogue systems.
method Proposes a novel user satisfaction estimator based on BiLSTMs and reinforcement learning.
result The novel user satisfaction estimator outperforms previous models in terms of user satisfaction and task success.

Fund2Persona creates personalized financial advisor personas from fund data, improving investment advice and manager interpretation.

problem Lack of consistent and specific financial advisor expertise in personalized investment advice.
method Grounds financial advisor personas in fund disclosures, holdings transitions, market context, and manager commentary through an agentic actor--scorer--patcher loop.
result Personas better recover portfolio decisions and grounded manager interpretation than generic baselines.

Memory-Augmented Recurrent Networks improve dialogue coherence by expanding conversation history storage.

problem Fixed-size vectors limit dialogue coherence; attention mechanisms are computationally expensive.
method Introduce Neural Turing Machines (NTMs) to provide flexible and permanent storage for dialogue history.
result Improved perplexity performance compared to existing baselines.

A new psychotherapy dialogue model learns compressed text representations.

problem Modeling psychotherapy dialogues with small datasets.
method Nonparametric kernel functions and hashcode representations.
result Significantly outperforms state-of-the-art models in psychotherapy sessions.

Fund2Persona creates personalized financial advisor personas from fund data, improving investment advice.

problem Lack of consistent advisor expertise and difficulty in encoding it in LLM systems.
method Grounds financial advisor personas in fund disclosures, market context, and manager commentary through an agentic actor--scorer--patcher loop.
result Personas better recover portfolio decisions and manager interpretation than generic baselines.

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning pr…

2016-04-15abs ↗pdf ↗

Adversarial learning improves multi-turn dialogue response generation.

problem Generating coherent and diverse multi-turn dialogue responses.
method hredGAN based on conditional GANs with HRED generator and word-level RNN discriminator.
result hredGAN generates more informative and diverse responses with limited data.

Improved dialogue system training with deep reinforcement learning.

problem Training efficient dialogue systems with large action spaces.
method Deep reinforcement learning, actor-critic methods, off-policy learning, ACER algorithm.
result ACER algorithm trains significantly faster in large action spaces.

Study combines chit-chat and goal-oriented dialogue in fantasy games.

problem Combining naturalistic chit-chat with goal-oriented tasks in fantasy games.
method Trained a goal-oriented model with reinforcement learning against an imitation-learned chit-chat model using two approaches.
result Both models outperform a baseline and can converse naturally to achieve goals.

Enhances persona-based conversation model for multi-turn dialogue.

problem Improving persona-based conversation models for multi-turn dialogue.
method Introduced additional input modality into hredGAN to capture external attributes.
result Persona hredGAN (phredGANphredGAN) outperforms existing models in multi-turn dialogue corpora.

Paper proposes a method to generate task-oriented dialogue queries.

problem Scarcity of training data for task-oriented dialogue systems.
method Conditional variational autoencoder for intent-specific sentence generation and query transfer protocol.
result Our method improves the diversity of generated queries without compromising quality.

This paper collects a large dataset for conversational recommendation research.

problem Creating dialogue systems for conversational recommendation.
method Collects a large dataset (ReDial) and explores neural architectures, mechanisms, and methods for conversational recommendation systems.
result Demonstrates the utility of the collected dataset for systematic probing of model sub-components in conversational recommendation.

End-to-end dialogue model learns from joint embeddings and user intent.

problem Challenges in reasoning and incorporating state-full knowledge in goal-oriented dialogues.
method Proposes an RNN-based end-to-end encoder-decoder architecture trained with joint embeddings and multi-task learning.
result Improves task-oriented dialogue system performance as shown by BLEU score evaluation.

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.

Neural User Simulator outperforms traditional ABUS in training dialogue systems.

problem Limited diversity and lack of natural language in ABUS.
method NUS learns user behavior from a corpus and generates natural language.
result NUS trained policies outperform ABUS in real user evaluations.

Improves dialogue response model interpretability using attention and regularization.

problem Improving interpretability of dual encoder models for dialogue response suggestions.
method Integrates attention mechanism and novel regularization loss to emphasize important words.
result Improves model accuracy and interpretability compared to existing methods.

DGDS uses documents to center conversations, promising broader AI understanding.

problem DS classification by function is insufficient for complex conversations.
method Classify DS based on document grounding, analyzing classification, architecture, datasets, and models.
result DGDS can better represent current DS development trends and future AI understanding.

TCT learns multimodal sequence representations by translating from related sequences.

problem Challenges in learning semantic representations from multimodalities.
method Transformer based Cross-modal Translator (TCT) combined with Multimodal Transformer Network (MTN).
result Proposed method achieves new state-of-the-art performance on video-grounded dialogue.

A new multi-hop FiLM approach improves visual reasoning tasks.

problem Challenging multi-modal tasks like visual question-answering and dialogue.
method Generate FiLM layer parameters in a multi-hop fashion, alternating between attending to language and generating parameters.
result Multi-hop FiLM generation achieves state-of-the-art performance on visual dialogue tasks.

Paper proposes RL for efficient MCI diagnosis from dialogue data.

problem Efficiently diagnose MCI from conversational data with minimal interaction.
method Reinforcement learning framework trained on clinical trial transcripts.
result Significantly outperforms supervised learning approaches with minimal conversation turns.

Improved model-based reinforcement learning for interactive dialogue tasks reduces sample needs and improves performance.

problem Limited data and high sample cost in interactive dialogue systems.
method Model-based actor-critic approach with an environment model and planner.
result 70 times fewer samples required compared to baseline model-free algorithm, with 2x better asymptotic performance.

Deep learning improves conversational recommender systems.

problem Creating effective goal-oriented dialogue systems through natural language interactions.
method Apply deep learning techniques to conversational recommender systems.
result Deep learning models enhance user preference learning in CRS.

Self-attentional models improve chatbot efficiency and performance.

problem Training efficient task-oriented dialogue generation systems.
method Applied self-attentional models to three datasets for chatbot training.
result Self-attentional models outperform recurrence-based models in efficiency and performance.