RNNs can generate bounded hierarchical languages with optimal memory
Comments EMNLP2020 + appendix typo fixes
作者
Christopher D. Manning
Natural Language Processing
The EOS Decision and Length Extrapolation
Comments 16 page, 7 Figures, 9 Tables, Blackbox NLP Workshop at EMNLP 2020
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
Comments Published in 3rd Proceedings of Alexa Prize (Alexa Prize 2019)
Biomedical and Clinical English Model Packages in the Stanza Python NLP Library
Comments Website: https://stanfordnlp.github.io/stanza/; demo page: http://stanza.run/bio
Towards Ecologically Valid Research on Language User Interfaces
Mapping Three Decades of Intellectual Change in Academia
Comments 10 pages and 6 figures plus appendix of 5 pages and 1 figure
Finding Universal Grammatical Relations in Multilingual BERT
Comments To appear in ACL 2020; Farsi typo corrected
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports
Comments ACL2020. 13 pages with appendices
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Comments ACL2020 System Demonstration. First two authors contribute equally. Website: https://stanfordnlp.github.io/stanza
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection
Comments LREC 2020
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Comments ICLR 2020
Learning by Abstraction: The Neural State Machine
Comments Published as a conference paper at NeurIPS 2019 (spotlight)
Answering Complex Open-domain Questions Through Iterative Query Generation
Comments EMNLP-IJCNLP 2019. Xiaowen Lin, Leo Mehr, and Zijian Wang contributed equally. GitHub: https://github.com/qipeng/golden-retriever
Do Massively Pretrained Language Models Make Better Storytellers?
Comments Accepted to CoNLL 2019
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
Comments Published as a conference paper at CVPR 2019 (oral)
BAM! Born-Again Multi-Task Networks for Natural Language Understanding
Comments ACL 2019
What Does BERT Look At? An Analysis of BERT's Attention
Comments BlackBoxNLP 2019
CoQA: A Conversational Question Answering Challenge
Comments TACL (presented at NAACL 2019)
Universal Dependency Parsing from Scratch
Comments In Proceedings of the CoNLL 2018 UD Shared Task. First three authors contributed roughly equally. Github repo: https://github.com/stanfordnlp/stanfordnlp Website: https://stanfordnlp.github.io/stanfordnlp/
Learning to Summarize Radiology Findings
Comments EMNLP 2018 Workshop on Health Text Mining and Information Analysis (EMNLP-LOUHI). Code and pretrained model available at: https://github.com/yuhaozhang/summarize-radiology-findings
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
Comments EMNLP 2018. Code available at: https://github.com/qipeng/gcn-over-pruned-trees
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Comments EMNLP 2018 long paper. The first three authors contribute equally. Data, code, and blog posts available at https://hotpotqa.github.io/
Semi-Supervised Sequence Modeling with Cross-View Training
Comments EMNLP 2018
Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts
Comments 12 pages including appendix and references. To be presented at EMNLP 2018
Simpler but More Accurate Semantic Dependency Parsing
Comments ACL 2018 short paper
Compositional Attention Networks for Machine Reasoning
Comments Published as a conference paper at ICLR 2018
Sentences with Gapping: Parsing and Reconstructing Elided Predicates
Comments To be presented at NAACL 2018
Journal ref Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2018)
A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue
Comments 6 pages
Key-Value Retrieval Networks for Task-Oriented Dialogue
Arc-swift: A Novel Transition System for Dependency Parsing
Comments Accepted at ACL 2017
