Paper improves conversion prediction models for online advertising.
problem Predicting different types of conversions in online advertising.
method Multi-Task Learning with MT-FwFM.
result Improved AUC by 0.74% and 0.84% on two conversion types, and overall AUC by 0.50%.
Automated system extracts medication regimens from medical conversations.
problem Extract relevant medication information from medical conversations.
method QA task approach, combined QA and Information Extraction, data augmentation, public embeddings, pretraining.
result Improved accuracy in extracting dosage and frequency from 54.28 and 37.13 to 89.57 and 45.94.
A new framework converts EEG signals between subjects and tasks.
problem Noise and variability in EEG data hinder generalizable signal extraction.
method Contrastive Split-Latent Permutation Autoencoder (CSLP-AE) framework.
result The CSLP-AE framework enables zero-shot conversion between unseen subjects.
In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations (14,000 hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data qua…
A fast voice conversion method using diffusion models.
problem One-shot many-to-many voice conversion.
method Diffusion probabilistic modeling with Fast Maximum Likelihood Sampling Scheme.
result Superior quality compared to state-of-the-art approaches.
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.
We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal ident…
We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks. This model can a…
Bidirectional sequence generation improves performance in conversational tasks.
problem Neural sequence generation typically considers only past tokens, limiting performance.
method Introduced placeholder tokens that can consider both past and future tokens in sequence generation.
result Bidirectional model outperforms competitive baselines on conversational tasks.
This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully…
Improved conversion rate prediction in online advertising using self-supervised pre-training.
problem Data sparsity and calibration issues in predicting conversions given clicks.
method Self-supervised pre-training on all conversion events to enrich CVR prediction model without compromising calibration.
result Improvements in offline training and online A/B tests, with full deployment to Yahoo native advertising system.
Proposes a new voice conversion model that preserves pitch patterns.
problem Preserving pitch patterns while changing speaker identity.
method Variational-autoencoder-based model with an auxiliary network.
result Ensures the conversion result correctly reflects specified F0/timbre information.
Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several task-specific problems in prac…
Model improves email-based conversational agents' ability to extract relevant information.
problem Asynchronous email communication makes it hard for agents to detect intents and extract relevant entities.
method Neural model for scoping relevant information from large queries.
result Improves performance of intent detection and entity extraction tasks by 35% in precision.
The paper extracts structured data from physician-patient conversations, reducing clerical burden.
problem Mining insights from physician-patient conversations for electronic health record documentation.
method Created a dataset of transcripts and summaries, extracted noteworthy utterances, and improved model performance.
result Extracting noteworthy utterances significantly boosts model performance for recognizing diagnoses and RoS abnormalities.
MaskCycleGAN-VC improves voice conversion without parallel data.
problem Limited ability to convert mel-spectrogram data without parallel data.
method Integrates a novel auxiliary task called filling in frames (FIF) to learn time-frequency structures.
result MaskCycleGAN-VC outperforms existing methods with similar model size.
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…
Improved autoencoder for F0-consistent voice conversion.
problem Non-parallel many-to-many voice conversion with prosodic information leakage.
method Conditional autoencoder with information-constraining bottlenecks.
result Controlled F0 contour and improved speech quality.
MathChat uses LLM agents to solve challenging math problems through conversational problem-solving.
problem Solving math problems expressed in natural language.
method MathChat is a conversational framework combining an LLM agent and a user proxy agent for collaborative problem-solving.
result MathChat improves tool-using prompting methods by 6% on difficult math problems.
Dual learning algorithm addresses delayed conversions in CVR prediction.
problem Challenges in predicting conversion rate due to delayed feedback.
method Proposes two unbiased estimators and a dual learning algorithm.
result Demonstrates practical value of the proposed approach through empirical evaluations.
A multi-task learning model for slot tagging in biomedical domains.
problem Limited labeled data, memory constraints, and domain-specific slot types.
method Multi-task learning using deep bidirectional transformers.
result Outperforms previous state-of-the-art systems in efficiency and effectiveness.
In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying the document, thereby explaining the model's prediction. We successfully applied HAN to a sequential analysis task in the form of real-time m…
Neuro-symbolic system tackles conversational AI's need for natural, broad-ranging dialogue.
problem Understanding unstated presumptions in conversational AI commands.
method Neuro-symbolic theorem prover for multi-hop reasoning.
result Extracts multi-hop reasoning chains from natural language commands.
Improves medication name inference for telemedicine and conversational agents.
problem Challenges in mapping user-friendly medication names to standardized ones.
method Entity-boosted two-tower neural network for ranking SMN to DMP.
result State-of-the-art results achieved with improved attention-based ranking.
Group discussions are essential for organizing every aspect of modern life, from faculty meetings to senate debates, from grant review panels to papal conclaves. While costly in terms of time and organization effort, group discussions are commonly seen as a way of reaching better decisions compared to solutions that do…
A new model predicts conversion rates by analyzing post-click actions.
problem Challenges in predicting conversion rates due to sample selection bias and data sparsity.
method Post-click behavior decomposition and multi-task learning.
result The model effectively addresses sample selection bias and data sparsity issues.
Singing voice conversion is a task to convert a song sang by a source singer to the voice of a target singer. In this paper, we propose using a parallel data free, many-to-one voice conversion technique on singing voices. A phonetic posterior feature is first generated by decoding singing voices through a robust Automa…
Model user preferences for conversational LLMs using weak rewards.
problem Lack of persistent user models in conversational LLMs leading to repeated user restatements.
method Vector-Adapted Retrieval Scoring (VARS) framework that updates user vectors online from weak scalar rewards.
result Full VARS agent achieves strongest overall performance, matches strong Reflection baseline in task success, and reduces user effort.
A-StarGAN improves nonparallel voice conversion speed and realism.
problem Nonparallel voice conversion without parallel data.
method Augmented classifier StarGAN (A-StarGAN) for nonparallel voice conversion.
result A-StarGAN generates realistic-sounding speech quickly and efficiently.
Many-to-Many VTN improves voice conversion across multiple speakers.
problem Voice conversion across multiple speakers.
method Sequence-to-sequence learning framework with many-to-many VTN architecture.
result Improved sound quality and speaker similarity compared to baseline methods.
Model improves CVR estimation in recommender systems by mitigating bias and overlooking causal relationships.
problem Data sparsity and sample selection bias in CVR estimation.
method Entire Space Counterfactual Multitask Model (ESCM2) incorporating counterfactual risk minimizer. result Significantly enhances recommendation performance by effectively mitigating bias and overlooking causal relationships.
Paper optimizes recommendation systems for long-term business metrics.
problem Short-term reward optimization ignores long-term business metrics.
method Introduced a framework for modeling long-term rewards in RecoGym.
result Proposed a simple extension leading to state-of-the-art results.
This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN. Our method, which we call StarGAN-VC, is noteworthy in that it (1) requires no parallel utterances, transcriptions, or time alignment procedures for speec…
This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder ne…
Proposes a new method for conversational agents using deep learning.
problem Building coherent and non-monotonous conversational agents with proper discourse and coverage.
method End-to-end multi-stream deep learning architecture leveraging contextual and syntactic information.
result Significantly improved next sentence prediction task.
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.
Enhanced transformer converts whispered speech to natural speech.
problem Machine recognition of whispered speech is challenging.
method Proposes an enhanced transformer architecture trained end-to-end using supervised learning.
result Similar formant distributions of converted speech to groundtruth.
Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep RL suffers from high sensitivity to noisy, incomplete, and misleading…
A new TTS method uses diffusion and VAE for better speech synthesis.
problem Improving text-to-speech synthesis for better speech quality and robustness.
method Combines diffusion probabilistic model and variational autoencoder for latent variable conversion.
result The method is robust to poor orthography and alignment errors.
Study examines cash conversion cycle in manufacturing firms, finding negative relationships with profitability and size.
problem Understanding cash conversion cycle in manufacturing firms and its impact on profitability and size.
method Empirical study of 30 manufacturing firms in Dhaka Stock Exchanges, categorizing them into six industries, analyzing industry averages and relationships with size and profitability.
result Negative relationship between cash conversion cycle and profitability, especially ROE; negative relationship with firm size in terms of net sales.
Framework converts singer identity and vocal technique from non-parallel corpora.
problem Converts singer identity and vocal technique from non-parallel corpora.
method Uses variational autoencoders with separate encoders for singer identity and vocal technique.
result Successfully disentangles and converts singer identity and vocal technique.
FasterVoiceGrad speeds up VC by 6-7x with novel distillation.
problem Slow iterative sampling in diffusion-based VC models.
method Adversarial diffusion conversion distillation (ADCD) to create a faster one-step model.
result 6.6-6.9 and 1.8x faster on GPU and CPU, respectively.
Study proposes an ad creative selection algorithm considering user fatigue.
problem Ad creative effectiveness varies with user exposure.
method Proposes an algorithm that considers user fatigue in ad selection.
result The proposed algorithm outperforms baseline algorithms in real-world testing.
In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF…
Conversational UCB accelerates bandit learning with user feedback.
problem Slow learning speed in traditional contextual bandit algorithms.
method Generalized contextual bandit to conversational contextual bandit, leveraging both behavioral and conversational feedbacks.
result ConUCB achieves a smaller regret upper bound, indicating faster learning speed.
Hybrid approach combines user feedback and machine learning for predicting user satisfaction.
problem Measuring user satisfaction in large-scale conversational agent systems.
method Fusion of explicit user feedback and predictions from two machine-learned models trained on different data types.
result Hybrid approach significantly improves user satisfaction predictions.
FedConPE improves conversational recommender systems efficiency and privacy.
problem Efficiently eliciting user preferences in interactive systems with heterogeneous clients.
method Phase elimination-based federated conversational bandit algorithm with adaptive key term construction.
result Minimizes uncertainty across all dimensions in feature space and offers improved efficiency and privacy.
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
problem Voice conversion between speakers with limited parallel audio pairs.
method Hierarchical sequence to sequence model with attention-based decoder, trained on single speaker dataset.
result Improved voice conversion quality using mel spectrograms and wavenet vocoder.