52 Episodio

  1. ep32: We need to talk about standard splits

    Pubblicato: 26/05/2019

  2. ep31: CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

    Pubblicato: 11/05/2019

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

    Pubblicato: 30/04/2019

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

    Pubblicato: 22/04/2019

  5. ep28: Attention is not Explanation

    Pubblicato: 13/04/2019

  6. ep27: 今年度の振り返りとこれからについて

    Pubblicato: 31/03/2019

  7. 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

    Pubblicato: 23/03/2019

  8. ep25: サブワードに基づく単語分散表現の縮約モデリング

    Pubblicato: 17/03/2019

  9. ep24: BERT for Joint Intent Classification and Slot Filling

    Pubblicato: 02/03/2019

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

    Pubblicato: 24/02/2019

  11. ep22: What are the biases in my data?

    Pubblicato: 17/02/2019

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

    Pubblicato: 03/02/2019

  13. ep20: Comprehensive evaluation of statistical speech waveform synthesis

    Pubblicato: 27/01/2019

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

    Pubblicato: 20/01/2019

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

    Pubblicato: 14/01/2019

  16. ep17: User Modeling for Task Oriented Dialogues

    Pubblicato: 31/12/2018

  17. ep16: Contextual Topic Modeling For Dialog Systems

    Pubblicato: 09/12/2018

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

    Pubblicato: 02/12/2018

  19. ep14: XNLI: Evaluating Cross-lingual Sentence Representations

    Pubblicato: 25/11/2018

  20. ep13: You May Not Need Attention

    Pubblicato: 04/11/2018

2 / 3

Leading NLP Ninjaでは最近のNLP (Natural Language Processing）に関連する論文をjojonkiが短く紹介します．気になったこと・質問・間違い等，フィードバック頂けると嬉しいです． 紹介する論文は，基本的に下記の論文まとめから取り上げる予定です． https://github.com/jojonki/arXivNotes/issues