All Episodes

ep52(ACL): A Two-Stage Masked LM Method for Term Set Expansion

ep51 (arXiv): XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization

ep50 (ICLR): ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

ep49 (ICASSP): Looking Enhances Listening: Recovering Missing Speech Using Images

ep48 (AAAI): Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization

ep47 (ICLR): ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ep46: FreeLB: Enhanced Adversarial Training for Language Understanding

ep45: Episodic Memory in Lifelong Language Learning

ep44: 75 Languages, 1 Model: Parsing Universal Dependencies Universally

ep43: BPE-Dropout: Simple and Effective Subword Regularization

ep42: HuggingFace's Transformers: State-of-the-art Natural Language Processing

ep41: A Simple Theoretical Model of Importance for Summarization

ep40: OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs

ep39: Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding

ep38: Trends in Natural Language Processing: ACL 2019 In Review

ep37: Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems

ep36: A Survey of Reinforcement Learning Informed by Natural Language

ep35: Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables

ep34: Do Neural Dialog Systems Use the Conversation History Effectively?

ep33: Target-Guided Open-Domain Conversation

ep32: We need to talk about standard splits

ep31: CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

ep30: Probing the Need for Visual Context in Multimodal Machine Translation

ep29: What's in a Name? Reducing Bias in Bios without Access to Protected Attributes

ep28: Attention is not Explanation

ep27: 今年度の振り返りとこれからについて

ep26: 大規模な自動解析データが形態素解析器をどこまで小さくできるか

ep25: サブワードに基づく単語分散表現の縮約モデリング

ep24: BERT for Joint Intent Classification and Slot Filling

ep23: End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis

ep22: What are the biases in my data?

ep21: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

ep20: Comprehensive evaluation of statistical speech waveform synthesis

ep19: SentencePiece: A simple and language independent subword tokenizer and detokenizer for NLP

ep18: PyText: A Seamless Path from NLP research to production

ep17: User Modeling for Task Oriented Dialogues

ep16: Contextual Topic Modeling For Dialog Systems

ep15: Another Diversity-Promoting Objective Function for Neural Dialogue Generation

ep14: XNLI: Evaluating Cross-lingual Sentence Representations

ep13: You May Not Need Attention

ep12: Word Embedding based Edit Distance

ep11: Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective

ep10: Automatic Evaluation of Neural Personality-based Chatbots

ep9: Learning and Evaluating Sparse Interpretable Sentence Embeddings

ep8: Zero-Shot Adaptive Transfer for Conversational Language Understanding

ep7: Training Millions of Personalized Dialogue Agents

ep6: Bag of Experts Architectures for Model Reuse in Conversational Language Understanding

ep5: Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue

ep4: CoQA: A Conversational Question Answering Challeng

ep3: Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing

ep2: Zero-Shot Dialog Generation with Cross-Domain Latent Actions

ep1: Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates.