【AI-Paper-Collector】ACL2021中72篇含对话Dialog关键字论文整理!

程序员大白

共 7502字,需浏览 16分钟

 ·

2022-05-09 23:42

MLNLP 机器学习算法与自然语言处理 )社区是国内外知名自然语言处理社区,受众覆盖国内外NLP硕博生、高校老师以及企业研究人员。
社区的愿景 是促进国内外自然语言处理,机器学习学术界、产业界和广大爱好者之间的交流,特别是初学者同学们的进步。

1

『项目概况』



每当我们接触一个新领域需要调研的时候,都需要去检索相关主题的论文,为了方便大家检索和提高效率,我们开源了一个工具AI-Paper-Collector能够自动帮助大家获取指定主题的会议论文(目前已经支持CV与NLP近20个常见会议),并且支持精准匹配和模糊匹配。由于我们的水平有限,望大家多提bug,多反馈,多交流,可以帮助我们迭代的更好。希望对大家有所帮助。

AI Paper Collector项目地址如下图所示,可以直接扫描二维码或者点击阅读原文即可访问。


2

『本日推送』



本日推送ACL2021中包含Dialog的72篇文章:

  • 【ACL2021】   Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances

  • 【ACL2021】  Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking

  • 【ACL2021】  Transferable Dialogue Systems and User Simulators

  • 【ACL2021】  BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data

  • 【ACL2021】  SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

  • 【ACL2021】  TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems

  • 【ACL2021】  Improving Dialog Systems for Negotiation with Personality Modeling

  • 【ACL2021】  Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training

  • 【ACL2021】  Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

  • 【ACL2021】  Prosodic segmentation for parsing spoken dialogue

  • 【ACL2021】  Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization

  • 【ACL2021】  Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection

  • 【ACL2021】  I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling

  • 【ACL2021】  A Sequence-to-Sequence Approach to Dialogue State Tracking

  • 【ACL2021】  Discovering Dialog Structure Graph for Coherent Dialog Generation

  • 【ACL2021】  Dialogue Response Selection with Hierarchical Curriculum Learning

  • 【ACL2021】  Discovering Dialogue Slots with Weak Supervision

  • 【ACL2021】  Robustness Testing of Language Understanding in Task-Oriented Dialog

  • 【ACL2021】  Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?

  • 【ACL2021】  OTTers: One-turn Topic Transitions for Open-Domain Dialogue

  • 【ACL2021】  Towards Quantifiable Dialogue Coherence Evaluation

  • 【ACL2021】  Towards Emotional Support Dialog Systems

  • 【ACL2021】  Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

  • 【ACL2021】  Diversifying Dialog Generation via Adaptive Label Smoothing

  • 【ACL2021】  NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation

  • 【ACL2021】  RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems

  • 【ACL2021】  Semantic Representation for Dialogue Modeling

  • 【ACL2021】  Structural Pre-training for Dialogue Comprehension

  • 【ACL2021】  A Human-machine Collaborative Framework for Evaluating Malevolence in Dialogues

  • 【ACL2021】  Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders

  • 【ACL2021】  DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

  • 【ACL2021】  DynaEval: Unifying Turn and Dialogue Level Evaluation

  • 【ACL2021】  RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy

  • 【ACL2021】  PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling

  • 【ACL2021】  Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer

  • 【ACL2021】  DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations

  • 【ACL2021】  TIMEDIAL: Temporal Commonsense Reasoning in Dialog

  • 【ACL2021】  Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries

  • 【ACL2021】  PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation

  • 【ACL2021】  Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking

  • 【ACL2021】  Unsupervised Enrichment of Persona-grounded Dialog with Background Stories

  • 【ACL2021】  Domain-Adaptive Pretraining Methods for Dialogue Understanding

  • 【ACL2021】  Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking

  • 【ACL2021】  On the Generation of Medical Dialogs for COVID-19

  • 【ACL2021】  Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images

  • 【ACL2021】  ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation

  • 【ACL2021】  LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing

  • 【ACL2021 findings】 GoG: Relation-aware Graph-over-Graph Network for Visual Dialog

  • 【ACL2021 findings】 Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation

  • 【ACL2021 findings】 Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory

  • 【ACL2021 findings】 Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

  • 【ACL2021 findings】 A Dialogue-based Information Extraction System for Medical Insurance Assessment

  • 【ACL2021 findings】 Scheduled Dialog Policy Learning: An Automatic Curriculum Learning Framework for Task-oriented Dialog System

  • 【ACL2021 findings】 Unsupervised Knowledge Selection for Dialogue Generation

  • 【ACL2021 findings】 HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

  • 【ACL2021 findings】 Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning

  • 【ACL2021 findings】 High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles

  • 【ACL2021 findings】 Assessing Dialogue Systems with Distribution Distances

  • 【ACL2021 findings】 REAM♯: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation

  • 【ACL2021 findings】 Dialogue-oriented Pre-training

  • 【ACL2021 findings】 Knowledge-Grounded Dialogue Generation with Term-level De-noising

  • 【ACL2021 findings】 Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL

  • 【ACL2021 findings】 Dialogue Graph Modeling for Conversational Machine Reading

  • 【ACL2021 findings】 Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation

  • 【ACL2021 findings】 An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation – Avoiding Discrepancies

  • 【ACL2021 findings】 Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction

  • 【ACL2021 findings】 Enhancing the Open-Domain Dialogue Evaluation in Latent Space

  • 【ACL2021 findings】 Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation

  • 【ACL2021 findings】 Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

  • 【ACL2021 findings】 DialogSum: A Real-Life Scenario Dialogue Summarization Dataset

  • 【ACL2021 findings】 What Did You Refer to? Evaluating Co-References in Dialogue

  • 【ACL2021 findings】 Controllable Abstractive Dialogue Summarization with Sketch Supervision


3

『项目地址』



AI Paper Collector项目地址如下图所示,可以直接扫描二维码或者点击阅读原文即可访问。AI Paper Collector目前是一个正在进行的中项目,如有疏漏在所难免,欢迎任何的PR及issue讨论,也希望对大家有所帮助。

https://github.com/MLNLP-World/AI-Paper-Collector


关于我们

MLNLP社区 (机器学习算法与自然语言处理) 是由国内外自然语言处理学者联合构建的民间学术社区,目前已经发展为国内外知名自然语言处理社区,旗下包括 万人顶会交流群、AI臻选汇、AI英才汇 以及 AI学术汇 等知名品牌,旨在促进机器学习,自然语言处理学术界、产业界和广大爱好者之间的进步。
社区可以为相关从业者的深造、就业及研究等方面提供开放交流平台。欢迎大家关注和加入我们。

浏览 96
点赞
评论
收藏
分享

手机扫一扫分享

分享
举报
评论
图片
表情
推荐
点赞
评论
收藏
分享

手机扫一扫分享

分享
举报