Nature language process
- 500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow).
arxiv
- A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation.
arxiv
- Analysis Methods in Neural Language Processing: A Survey.
arxiv
- An end-to-end TextSpotter with Explicit Alignment and Attention.
arxiv
code
- An Introductory Survey on Attention Mechanisms in NLP Problems.
arxiv
- Annotation Artifacts in Natural Language Inference Data.
arxiv
:star:
- A Universal Music Translation Network.
arxiv
- Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension.
arxiv
- Calculating the similarity between words and sentences using a lexical database and corpus statistics.
arxiv
- Chinese Text in the Wild.
arxiv
- Content Selection in Deep Learning Models of Summarization.
arxiv
- Constituency Parsing with a Self-Attentive Encoder.
arxiv
code
- Embedding Logical Queries on Knowledge Graphs.
arxiv
code
- Extracting Action Sequences from Texts Based on Deep Reinforcement Learning.
arxiv
- Generating Wikipedia by Summarizing Long Sequences.
arxiv
:star:
- How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks.
arxiv
- IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection.
arxiv
- Linguistically-Informed Self-Attention for Semantic Role Labeling.
arxiv
:star:
- Neural Relational Inference for Interacting Systems.
arxiv
code
- Neural Text Generation: Past, Present and Beyond.
arxiv
- PixelLink: Detecting Scene Text via Instance Segmentation.
arxiv
code
- Shape Robust Text Detection with Progressive Scale Expansion Network.
arxiv
code
- Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings.
arxiv
- TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces.
arxiv
code
- Using J-K fold Cross Validation to Reduce Variance When Tuning NLP Models.
arxiv
code
Chatbot
- A Deep Reinforcement Learning Chatbot (Short Version).
arxiv
- Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning.
arxiv
- Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning.
arxiv
- Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems.
arxiv
code
- The Design and Implementation of XiaoIce, an Empathetic Social Chatbot.
arxiv
Embeddings
- An efficient framework for learning sentence representations.
arxiv
- A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks.
arxiv
code
- A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings.
arxiv
code
- Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases.
arxiv
- Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts.
arxiv
- Deep contextualized word representations.
arxiv
- Evaluating Compositionality in Sentence Embeddings.
arxiv
code
- From Word to Sense Embeddings: A Survey on Vector Representations of Meaning.
arxiv
- Learning Domain-Sensitive and Sentiment-Aware Word Embeddings.
arxiv
- Learning Role-based Graph Embeddings.
arxiv
code
- Learning Word Embeddings for Low-resource Languages by PU Learning.
arxiv
- On the Dimensionality of Word Embedding.
arxiv
code
- Poincaré GloVe: Hyperbolic Word Embeddings.
arxiv
- Query2Vec: NLP Meets Databases for Generalized Workload Analytics.
arxiv
- Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings.
arxiv
- Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech.
arxiv
- Word Embedding Attention Network: Generating Words by Querying Distributed Word Representations for Paraphrase Generation.
arxiv
code
- Word2Bits - Quantized Word Vectors.
arxiv
code
:star:
- EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings.
arxiv
Knowledge Graphs
- Variational Knowledge Graph Reasoning.
arxiv
Language Model
- An Analysis of Neural Language Modeling at Multiple Scales.
arxiv
code
Pos-tagging
- Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks.
arxiv
code
QA
- A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts.
arxiv
- A Question-Focused Multi-Factor Attention Network for Question Answering.
arxiv
code
- Being curious about the answers to questions: novelty search with learned attention.
arxiv
code
- Bilinear Attention Networks.
arxiv
code
- EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs.
arxiv
code
- Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning.
arxiv
code
- The Natural Language Decathlon: Multitask Learning as Question Answering.
arxiv
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.
arxiv
code
- TVQA: Localized, Compositional Video Question Answering.
arxiv
- Visual Question Generation as Dual Task of Visual Question Answering.
url
code
NER
- Chinese NER Using Lattice LSTM.
arxiv
code
- Named Entity Disambiguation using Deep Learning on Graphs.
arxiv
code
NMT
- Achieving Human Parity on Automatic Chinese to English News Translation.
arxiv
- Apply Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level.
arxiv
- Phrase-Based & Neural Unsupervised Machine Translation.
arxiv
- Self-Attention with Relative Position Representations.
arxiv
Recommender Systems
- Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba.
arxiv
- DKN: Deep Knowledge-Aware Network for News Recommendation.
arxiv
- Explainable Recommendation: A Survey and New Perspectives.
arxiv
- FashionNet: Personalized Outfit Recommendation with Deep Neural Network.
arxiv
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems.
arxiv
- Learning Tree-based Deep Model for Recommender Systems.
arxiv
- MARS: Memory Attention-Aware Recommender System.
arxiv
- Offline A/B testing for Recommender Systems.
arxiv
- Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System.
arxiv
code
- Sequence-Aware Recommender Systems.
arxiv
- Top-K Off-Policy Correction for a REINFORCE Recommender System.
arxiv
Sentiment Analysis
- Combination of Domain Knowledge and Deep Learning for Sentiment Analysis.
arxiv
- Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries.
arxiv
Speech Recognition
- Automatic Detection of Online Jihadist Hate Speech.
arxiv
- Do WaveNets Dream of Acoustic Waves?
arxiv
- End-to-End Speech Recognition From the Raw Waveform.
arxiv
- Large-Scale Visual Speech Recognition.
arxiv
- Speech Emotion Recognition with Data Augmentation and Layer-wise Learning Rate Adjustment.
arxiv
- Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data.
arxiv
- VoxCeleb2: Deep Speaker Recognition.
arxiv
Text Classification
- Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks.
arxiv
- Fake News Identification on Twitter with Hybrid CNN and RNN Models.
arxiv
- Fine-tuned Language Models for Text Classification.
arxiv
- Joint Embedding of Words and Labels for Text Classification.
arxiv
code
- Online Embedding Compression for Text Classification using Low Rank Matrix Factorization.
arxiv
- SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines.
arxiv
code