Search Results for author:
Found 119 papers, 63 papers with code
Counterfactual Off-Policy Training for Neural Dialogue Generation
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses.
Technical Report on Shared Task in DialDoc21
The task requires identifying the grounding knowledge in form of a document span for the next dialogue turn.
Visualizing attention zones in machine reading comprehension models
The attention mechanism plays an important role in the machine reading comprehension (MRC) model.
A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
To address this issue, in this paper, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses.
A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline. Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding.
Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
The framework consists of two modules: the Policy planner leverages policy-aware dialogue representation to select knowledge and predict the policy of the response; the generator uses policy/knowledge-aware dialogue representation for response generation.
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue
This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS.
Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI.
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task.
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).
Neural Stylistic Response Generation with Disentangled Latent Variables
Generating open-domain conversational responses in the desired style usually suffers from the lack of parallel data in the style.
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Maintaining consistent personas is essential for dialogue agents.
A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses.
Profile Consistency Identification for Open-domain Dialogue Agents
Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans.
GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
The heavy traffic congestion problem has always been a concern for modern cities.
GIKT: A Graph-based Interaction Model for Knowledge Tracing
With the rapid development in online education, knowledge tracing (KT) has become a fundamental problem which traces students' knowledge status and predicts their performance on new questions.
Ranked #7 on
Knowledge Tracing
on EdNet
Learning to Infer User Hidden States for Online Sequential Advertising
To drive purchase in online advertising, it is of the advertiser's great interest to optimize the sequential advertising strategy whose performance and interpretability are both important.
Glancing Transformer for Non-Autoregressive Neural Machine Translation
With GLM, we develop Glancing Transformer (GLAT) for machine translation.
Ranked #68 on
Machine Translation
on WMT2014 English-German
Bidirectional Model-based Policy Optimization
Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate.
An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.
Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning
Interactive recommender system (IRS) has drawn huge attention because of its flexible recommendation strategy and the consideration of optimal long-term user experiences.
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation.
Multi-Agent Determinantal Q-Learning
Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution.
User Behavior Retrieval for Click-Through Rate Prediction
These retrieved behaviors are then fed into a deep model to make the final prediction instead of simply using the most recent ones.
A Deep Recurrent Survival Model for Unbiased Ranking
Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data.
Counterfactual Off-Policy Training for Neural Response Generation
Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses.
Energy-Based Imitation Learning
We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals.
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
A Survey of Document Grounded Dialogue Systems (DGDS)
We believe that extracting unstructured document(s) information is the future trend of the DS because a great amount of human knowledge lies in these document(s).
Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines.
AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model.
Ranked #31 on
Click-Through Rate Prediction
on Criteo
Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency
Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning.
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention.
Ranked #1 on
Molecular Graph Generation
on MOSES
Multi-Agent Interactions Modeling with Correlated Policies
In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions.
Discriminative Sentence Modeling for Story Ending Prediction
Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge.
Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available.
Contextual Recurrent Units for Cloze-style Reading Comprehension
Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks.
Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
Consistency is one of the major challenges faced by dialogue agents.
Exploring Diverse Expressions for Paraphrase Generation
Paraphrasing plays an important role in various natural language processing (NLP) tasks, such as question answering, information retrieval and sentence simplification.
Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching
Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots
The heart of TripleNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels.
Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning
Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Bi-level Actor-Critic for Multi-agent Coordination
Coordination is one of the essential problems in multi-agent systems.
Multiagent Systems
Learning to Advertise for Organic Traffic Maximization in E-Commerce Product Feeds
We refer to this process as Leverage.
Towards Making the Most of BERT in Neural Machine Translation
Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.
An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation
This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problems.
Ranked #2 on
Click-Through Rate Prediction
on MovieLens 1M
Exploiting Persona Information for Diverse Generation of Conversational Responses
Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task.
CoRide: Joint Order Dispatching and Fleet Management for Multi-Scale Ride-Hailing Platforms
How to optimally dispatch orders to vehicles and how to trade off between immediate and future returns are fundamental questions for a typical ride-hailing platform.
Multiagent Systems
Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence
Knowledge base is one of the main forms to represent information in a structured way.
Dynamically Fused Graph Network for Multi-hop Reasoning
However, many difficult questions require multiple supporting evidence from scattered text among two or more documents.
Ranked #33 on
Question Answering
on HotpotQA
CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario
The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
CoLight: Learning Network-level Cooperation for Traffic Signal Control
To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication.
Multi-agent Reinforcement Learning
Reinforcement Learning
+1
Deep Landscape Forecasting for Real-time Bidding Advertising
The problem is formulated as to forecast the probability distribution of market price for each ad auction.
Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
In order to tackle these challenges, in this paper, we propose a Hierarchical Periodic Memory Network for lifelong sequential modeling with personalized memorization of sequential patterns for each user.
Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs
Lipschitz continuity recently becomes popular in generative adversarial networks (GANs).
Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space
In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks.
Lipschitz Generative Adversarial Nets
By contrast, Wasserstein GAN (WGAN), where the discriminative function is restricted to 1-Lipschitz, does not suffer from such a gradient uninformativeness problem.
CommunityGAN: Community Detection with Generative Adversarial Nets
In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning.
Ranked #1 on
Clique Prediction
on arXiv-GrQc 3-clique
Large-scale Interactive Recommendation with Tree-structured Policy Gradient
Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for long-run performance.
Layout Design for Intelligent Warehouse by Evolution with Fitness Approximation
With the rapid growth of the express industry, intelligent warehouses that employ autonomous robots for carrying parcels have been widely used to handle the vast express volume.
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
The DRR framework treats recommendation as a sequential decision making procedure and adopts an "Actor-Critic" reinforcement learning scheme to model the interactions between the users and recommender systems, which can consider both the dynamic adaptation and long-term rewards.
AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods
Adam is shown not being able to converge to the optimal solution in certain cases.
Retrieval-Enhanced Adversarial Training for Neural Response Generation
Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models.
Sampled in Pairs and Driven by Text: A New Graph Embedding Framework
TGE-PS uses Pairs Sampling (PS) to improve the sampling strategy of RW, being able to reduce ~99% training samples while preserving competitive performance.
Factorized Q-Learning for Large-Scale Multi-Agent Systems
Deep Q-learning has achieved a significant success in single-agent decision making tasks.
Multiagent Systems
Learning Adaptive Display Exposure for Real-Time Advertising
In this paper, we investigate the problem of advertising with adaptive exposure: can we dynamically determine the number and positions of ads for each user visit under certain business constraints so that the platform revenue can be increased?
Deep Recurrent Survival Analysis
By capturing the time dependency through modeling the conditional probability of the event for each sample, our method predicts the likelihood of the true event occurrence and estimates the survival rate over time, i. e., the probability of the non-occurrence of the event, for the censored data.
Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation.
Zero Pronoun Resolution with Attention-based Neural Network
Recent neural network methods for zero pronoun resolution explore multiple models for generating representation vectors for zero pronouns and their candidate antecedents.
Context-Sensitive Generation of Open-Domain Conversational Responses
Despite the success of existing works on single-turn conversation generation, taking the coherence in consideration, human conversing is actually a context-sensitive process.
AceKG: A Large-scale Knowledge Graph for Academic Data Mining
Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing.
Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs.
Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data
User response prediction is a crucial component for personalized information retrieval and filtering scenarios, such as recommender system and web search.
Generative Adversarial Nets for Information Retrieval: Fundamentals and Advances
In this tutorial, we focus on discussing the GAN techniques and the variants on discrete data fitting in various information retrieval scenarios.
Deep Reinforcement Learning for Chinese Zero pronoun Resolution
In this study, we show how to integrate local and global decision-making by exploiting deep reinforcement learning models.
Path-Level Network Transformation for Efficient Architecture Search
We introduce a new function-preserving transformation for efficient neural architecture search.
Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition
We study the problem of named entity recognition (NER) from electronic medical records, which is one of the most fundamental and critical problems for medical text mining.
Medical Named Entity Recognition
named-entity-recognition
+3
CoT: Cooperative Training for Generative Modeling of Discrete Data
In this paper, we study the generative models of sequential discrete data.
QA4IE: A Question Answering based Framework for Information Extraction
Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts.
Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning
From the advertisers' side, participating in ranking the search results by paying for the sponsored search advertisement to attract more awareness and purchase facilitates their commercial goal.
Neural Text Generation: Past, Present and Beyond
This paper presents a systematic survey on recent development of neural text generation models.
Bidding Machine: Learning to Bid for Directly Optimizing Profits in Display Advertising
From the learning perspective, we show that the bidding machine can be updated smoothly with both offline periodical batch or online sequential training schemes.
Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising
Real-time advertising allows advertisers to bid for each impression for a visiting user.
Mean Field Multi-Agent Reinforcement Learning
Existing multi-agent reinforcement learning methods are limited typically to a small number of agents.
Texygen: A Benchmarking Platform for Text Generation Models
We introduce Texygen, a benchmarking platform to support research on open-domain text generation models.
MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
Unlike previous research platforms on single or multi-agent reinforcement learning, MAgent focuses on supporting the tasks and the applications that require hundreds to millions of agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
A Neural Stochastic Volatility Model
In this paper, we show that the recent integration of statistical models with deep recurrent neural networks provides a new way of formulating volatility (the degree of variation of time series) models that have been widely used in time series analysis and prediction in finance.
GraphGAN: Graph Representation Learning with Generative Adversarial Nets
The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space.
Ranked #1 on
Node Classification
on Wikipedia
Improving Negative Sampling for Word Representation using Self-embedded Features
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood.
Face Transfer with Generative Adversarial Network
Face transfer animates the facial performances of the character in the target video by a source actor.
The First Evaluation of Chinese Human-Computer Dialogue Technology
In this paper, we introduce the first evaluation of Chinese human-computer dialogue technology.
Long Text Generation via Adversarial Training with Leaked Information
Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc.
Ranked #1 on
Text Generation
on COCO Captions
A Study of AI Population Dynamics with Million-agent Reinforcement Learning
We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning.
Chinese Zero Pronoun Resolution with Deep Memory Network
Existing approaches for Chinese zero pronoun resolution typically utilize only syntactical and lexical features while ignoring semantic information.
Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative
In this article, we mathematically study several GAN related topics, including Inception score, label smoothing, gradient vanishing and the -log(D(x)) alternative.
Efficient Architecture Search by Network Transformation
Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results.
Ranked #151 on
Image Classification
on CIFAR-10
Learning to Design Games: Strategic Environments in Reinforcement Learning
In typical reinforcement learning (RL), the environment is assumed given and the goal of the learning is to identify an optimal policy for the agent taking actions through its interactions with the environment.
Wasserstein Distance Guided Representation Learning for Domain Adaptation
Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WDGRL).
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair.
Activation Maximization Generative Adversarial Nets
Our proposed model also outperforms the baseline methods in the new metric.
Unsupervised Diverse Colorization via Generative Adversarial Networks
Colorization of grayscale images has been a hot topic in computer vision.
Real-Time Bidding by Reinforcement Learning in Display Advertising
In this paper, we formulate the bid decision process as a reinforcement learning problem, where the state space is represented by the auction information and the campaign's real-time parameters, while an action is the bid price to set.
Neural Personalized Response Generation as Domain Adaptation
Moreover, the lexical divergence of the responses generated by the 5 personalized models indicates that the proposed two-phase approach achieves good results on modeling the responding style of human and generating personalized responses for the conversational systems.
Product-based Neural Networks for User Response Prediction
Predicting user responses, such as clicks and conversions, is of great importance and has found its usage in many Web applications including recommender systems, web search and online advertising.
Ranked #1 on
Click-Through Rate Prediction
on iPinYou
Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting
The most significant progress in recent years in online display advertising is what is known as the Real-Time Bidding (RTB) mechanism to buy and sell ads.
Computer Science and Game Theory
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data.
Ranked #2 on
Text Generation
on Chinese Poems
Learning to Start for Sequence to Sequence Architecture
An obvious drawback of these work is that there is not a learnable relationship between words and the start symbol.
Learning text representation using recurrent convolutional neural network with highway layers
Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks.
Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution
Most existing approaches for zero pronoun resolution are heavily relying on annotated data, which is often released by shared task organizers.
Neural Recovery Machine for Chinese Dropped Pronoun
Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc.
A Deep Neural Network for Chinese Zero Pronoun Resolution
This is because zero pronouns have no descriptive information, which results in difficulty in explicitly capturing their semantic similarities with antecedents.
Feedback Control of Real-Time Display Advertising
In this paper, we propose a feedback control mechanism for RTB which helps advertisers dynamically adjust the bids to effectively control the KPIs, e. g., the auction winning ratio and the effective cost per click.
Computer Science and Game Theory Systems and Control
Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
Different from continuous raw features that we usually found in the image and audio domains, the input features in web space are always of multi-field and are mostly discrete and categorical while their dependencies are little known.
Ranked #2 on
Click-Through Rate Prediction
on Company*
Implicit Look-alike Modelling in Display Ads: Transfer Collaborative Filtering to CTR Estimation
In this work, we propose a general framework which learns the user profiles based on their online browsing behaviour, and transfers the learned knowledge onto prediction of their ad response.
Real-Time Bidding Benchmarking with iPinYou Dataset
This dataset directly supports the experiments of some important research problems such as bid optimisation and CTR estimation.
Computer Science and Game Theory Computers and Society
