最新NLP论文阅读列表，包括对话、问答、摘要、翻译、看图说话等

会员服务 ·

最新NLP论文阅读列表，包括对话、问答、摘要、翻译、看图说话等

2019 年 3 月 22 日 专知

【导读】Github项目iwangjian/Paper-Reading包含了最新的NLP相关论文列表，包括对话系统、文本摘要、主题模型、自动问答、机器翻译等，并在持续更新中。

Github项目iwangjian/Paper-Reading包含了最新的NLP相关论文列表，列表中将论文进行了分类，并提供了论文地址和部分代码地址。Paper-Reading项目的地址为：

https://github.com/iwangjian/Paper-Reading

目前列表包含的内容大致如下：

NLP中的深度学习

BERT: "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding". arXiv(2018)
ELMo: "Deep contextualized word representations". NAACL(2018)
Survey on Attention: "An Introductory Survey on Attention Mechanisms in NLP Problems". arXiv(2018)
Transformer: "Attention is All you Need". NIPS(2017)
ConvS2S: "Convolutional Sequence to Sequence Learning". ICML(2017)
Additive Attention: "Neural Machine Translation by Jointly Learning to Align and Translate". ICLR(2015)
Multiplicative Attention: "Effective Approaches to Attention-based Neural Machine Translation". EMNLP(2015)
Memory Net: "End-To-End Memory Networks". NIPS(2015)
Pointer Net: "Pointer Networks". NIPS(2015)
Copying Mechanism: "Incorporating Copying Mechanism in Sequence-to-Sequence Learning". ACL(2016)
Coverage Mechanism: "Modeling Coverage for Neural Machine Translation". ACL(2016)
GAN: "Generative Adversarial Nets". NIPS(2014)
SeqGAN: "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient". AAAI(2017)
MacNet: "MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models". NIPS(2018)
Graph2Seq: "Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks". arXiv(2018)
Pretrained Seq2Seq: "Unsupervised Pretraining for Sequence to Sequence Learning". EMNLP(2017)
Multi-task Learning: "An Overview of Multi-Task Learning in Deep Neural Networks". arXiv(2017)
Latent Multi-task: "Latent Multi-task Architecture Learning". AAAI(2019)
Multi-domain multi-task: "A Unified Perspective on Multi-Domain and Multi-Task Learning". ICLR(2015)

对话系统

Survey of Dialogue Corpora: "A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version". Dialogue & Discourse(2018) ⭐️ ⭐️ ⭐️
Two-Stage-Transformer: "Wizard of Wikipedia: Knowledge-Powered Conversational agents". ICLR(2019) ⭐️ ⭐️ ⭐️ ⭐️
Edit-N-Rerank: "Response Generation by Context-aware Prototype Editing". AAAI(2019) ⭐️ ⭐️ ⭐️ ⭐️
D2A: "Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base". NIPS(2018) ⭐️ ⭐️ ⭐️ ⭐️
DAIM: "Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization". NIPS(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
LU-DST: "Multi-task Learning for Joint Language Understanding and Dialogue State Tracking". SIGDIAL(2018) ⭐️ ⭐️ ⭐️ ⭐️
MTask: "A Knowledge-Grounded Neural Conversation Model". AAAI(2018) ⭐️ ⭐️ ⭐️
MTask-M: "Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models". IJCNLP(2018) ⭐️ ⭐️ ⭐️
GenDS: "Flexible End-to-End Dialogue System for Knowledge Grounded Conversation". arXiv(2017) ⭐️ ⭐️ ⭐️ ⭐️
SL+RL: "Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems". NAACL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
Time-Decay-SLU: "How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues". NAACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
REASON: "Dialog Generation Using Multi-turn Reasoning Neural Networks". NAACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
ADVMT: "One “Ruler” for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning". IJCAI(2018) ⭐️ ⭐️ ⭐️
STD/HTD: "Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
CSF used: "Generating Informative Responses with Controlled Sentence Function". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
Mem2Seq: "Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
NKD: "Knowledge Diffusion for Neural Dialogue Generation". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
DAWnet: "Chat More: Deepening and Widening the Chatting Topic via A Deep Model". SIGIR(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
ZSDG: "Zero-Shot Dialog Generation with Cross-Domain Latent Actions". SIGDIAL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
DUA: "Modeling Multi-turn Conversation with Deep Utterance Aggregation". COLING(2018) ⭐️ ⭐️ ⭐️ ⭐️
Data-Aug: "Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding". COLING(2018)
⭐️ ⭐️ ⭐️ ⭐️
DSR: "Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation". COLING(2018) ⭐️ ⭐️ ⭐️ ⭐️
DC-MMI: "Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️
StateNet: "Towards Universal Dialogue State Tracking". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️
cVAE-XGate/CGate: "Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
SMN: "Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots". ACL(2017) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
MMI: "A Diversity-Promoting Objective Function for Neural Conversation Models". NAACL-HLT(2016) ⭐️ ⭐️ ⭐️
RL-Dialogue: "Deep Reinforcement Learning for Dialogue Generation". EMNLP(2016) ⭐️ ⭐️ ⭐️ ⭐️
TA-Seq2Seq: "Topic Aware Neural Response Generation". AAAI(2017) ⭐️ ⭐️ ⭐️ ⭐️
MA: "Mechanism-Aware Neural Machine for Dialogue Response Generation". AAAI(2017) ⭐️ ⭐️ ⭐️
HRED: "Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models". AAAI(2016) ⭐️ ⭐️ ⭐️ ⭐️
VHRED: "A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues". AAAI(2017) ⭐️ ⭐️ ⭐️ ⭐️
CVAE/KgCVAE: "Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders". ACL(2017) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
ERM: "Elastic Responding Machine for Dialog Generation with Dynamically Mechanism Selecting". AAAI(2018) ⭐️ ⭐️ ⭐️ ⭐️
Tri-LSTM: "Augmenting End-to-End Dialogue Systems With Commonsense Knowledge". AAAI(2018) ⭐️ ⭐️ ⭐️
Dual Fusion: "Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm". IJCAI(2018)
⭐️ ⭐️ ⭐️ ⭐️
CCM: "Commonsense Knowledge Aware Conversation Generation with Graph Attention". IJCAI(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
PCCM: "Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation". IJCAI(2018) ⭐️ ⭐️ ⭐️ ⭐️
ECM: "Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory". AAAI(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
Topic-Seg-Label: "A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning". IJCAI(2018) ⭐️ ⭐️ ⭐️ ⭐️
AliMe: "AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine". ACL(2017) ⭐️ ⭐️ ⭐️
Retrieval+multi-seq2seq: "An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems". IJCAI(2018) ⭐️ ⭐️ ⭐️ ⭐️

文本摘要

BERT-Two-Stage: "Pretraining-Based Natural Language Generation for Text Summarization". arXiv(2019) ⭐️ ⭐️ ⭐️
Re^3Sum: "Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
NeuSum: "Neural Document Summarization by Jointly Learning to Score and Select Sentences". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
rnn-ext+abs+RL+rerank: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
Seq2Seq+CGU: "Global Encoding for Abstractive Summarization". ACL(2018) ⭐️ ⭐️ ⭐️ ⭐️
T-ConvS2S: "Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
RL-Topic-ConvS2S: "A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization." IJCAI (2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
GANsum: "Generative Adversarial Network for Abstractive Text Summarization". AAAI (2018) ⭐️ ⭐️ ⭐️
FTSum: "Faithful to the Original: Fact Aware Neural Abstractive Summarization". AAAI(2018) ⭐️ ⭐️ ⭐️ ⭐️
PGC: "Get To The Point: Summarization with Pointer-Generator Networks". ACL (2017) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
ABS/ABS+: "A Neural Attention Model for Abstractive Sentence Summarization". EMNLP (2015) ⭐️ ⭐️ ⭐️ ⭐️
RAS-Elman/RAS-LSTM: "Abstractive Sentence Summarization with Attentive Recurrent Neural Networks. HLT-NAACL (2016) ⭐️ ⭐️ ⭐️ ⭐️
words-lvt2k-1sent: "Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond". CoNLL (2016) ⭐️ ⭐️ ⭐️ ⭐️

主题模型

LDA: "Latent Dirichlet Allocation". JMLR (2003) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
Parameter Estimation: "Parameter estimation for text analysis." Technical report (2005). ⭐️ ⭐️ ⭐️ ⭐️
DTM: "Dynamic Topic Models". ICML (2006) ⭐️ ⭐️ ⭐️
cDTM: "Continuous Time Dynamic Topic Models". arXiv (2012) ⭐️ ⭐️
NTM: "A Novel Neural Topic Model and Its Supervised Extension". AAAI (2015) ⭐️ ⭐️ ⭐️ ⭐️
TWE: "Topical Word Embeddings". AAAI (2015) ⭐️ ⭐️ ⭐️
RATM-D: Recurrent Attentional Topic Model. AAAI (2017) ⭐️ ⭐️ ⭐️ ⭐️
RIBS-TM: "Don't Forget the Quantifiable Relationship between Words: Using Recurrent Neural Network for Short Text Topic Discovery". AAAI (2017) ⭐️ ⭐️ ⭐️ ⭐️
Topic coherence: "Optimizing Semantic Coherence in Topic Models". EMNLP (2011) ⭐️ ⭐️ ⭐️
Topic coherence: "Automatic Evaluation of Topic Coherence". NAACL (2010) ⭐️ ⭐️ ⭐️
DADT: "Authorship Attribution with Author-aware Topic Models". ACL(2012) ⭐️ ⭐️ ⭐️ ⭐️
Gaussian-LDA: "Gaussian LDA for Topic Models with Word Embeddings". ACL (2015) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
LFTM: "Improving Topic Models with Latent Feature Word Representations". TACL (2015) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
TopicVec: "Generative Topic Embedding: a Continuous Representation of Documents". ACL (2016) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
SLRTM: "Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves". arXiv (2016) ⭐️ ⭐️ ⭐️ ⭐️
TopicRNN: "TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency". ICLR(2017) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
NMF boosted: "Stability of topic modeling via matrix factorization". Expert Syst. Appl. (2018) ⭐️ ⭐️ ⭐️
Evaluation of Topic Models: "External Evaluation of Topic Models". Australasian Doc. Comp. Symp. (2009) ⭐️ ⭐️
Topic2Vec: "Topic2Vec: Learning distributed representations of topics". IALP (2015) ⭐️ ⭐️ ⭐️
L-EnsNMF: "L-EnsNMF: Boosted Local Topic Discovery via Ensemble of Nonnegative Matrix Factorization". ICDM (2016) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
DC-NMF: "DC-NMF: nonnegative matrix factorization based on divide-and-conquer for fast clustering and topic modeling". J. Global Optimization (2017) ⭐️ ⭐️ ⭐️ ⭐️
cFTM: "The contextual focused topic model". KDD (2012) ⭐️ ⭐️ ⭐️ ⭐️
CLM: "Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts". KDD (2017) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
GMTM: "Unsupervised Topic Modeling for Short Texts Using Distributed Representations of Words". NAACL (2015) ⭐️ ⭐️ ⭐️ ⭐️
GPU-PDMM: "Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings". TOIS (2017) ⭐️ ⭐️ ⭐️ ⭐️
BPT: "A Two-Level Topic Model Towards Knowledge Discovery from Citation Networks". TKDE (2014) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
BTM: "A Biterm Topic Model for Short Texts". WWW (2013) ⭐️ ⭐️ ⭐️ ⭐️
HGTM: "Using Hashtag Graph-Based Topic Model to Connect Semantically-Related Words Without Co-Occurrence in Microblogs". TKDE (2016) ⭐️ ⭐️ ⭐️ ⭐️
COTM: "A topic model for co-occurring normal documents and short texts". WWW (2018) ⭐️ ⭐️ ⭐️ ⭐️

机器翻译

Deliberation Networks: "Deliberation Networks: Sequence Generation Beyond One-Pass Decoding". NIPS(2017) ⭐️ ⭐️ ⭐️ ⭐️
Multi-pass decoder: "Adaptive Multi-pass Decoder for Neural Machine Translation". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️

自动问答

MTQA: "Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering". AAAI(2019) ⭐️ ⭐️ ⭐️ ⭐️
CQG-KBQA: "Knowledge Base Question Answering via Encoding of Complex Query Graphs". EMNLP(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
HR-BiLSTM: "Improved Neural Relation Detection for Knowledge Base Question Answering". ACL(2017) ⭐️ ⭐️ ⭐️ ⭐️
KBQA-CGK: "An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge". ACL(2017) ⭐️ ⭐️ ⭐️ ⭐️

看图说话

MLAIC: "A Multi-task Learning Approach for Image Captioning". IJCAI(2018) ⭐️ ⭐️ ⭐️ ⭐️
Up-Down Attention: "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering". CVPR(2018) ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
Recurrent-RSA: "Pragmatically Informative Image Captioning with Character-Level Inference". NAACL(2018) ⭐️ ⭐️ ⭐️ ⭐️