语言大模型 / LLM - arXivDaily 专题

2008.09150 2021-10-22 cs.CL cs.AI cs.CV 62%

VisualSem: A High-quality Knowledge Graph for Vision and Language

Houda Alberts, Teresa Huang, Yash Deshpande, Yibo Liu, Kyunghyun Cho, Clara Vania, Iacer Calixto

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted for publication at the 1st Multilingual Representation Learning workshop (MRL 2021) co-located with EMNLP 2021. 15 pages, 8 figures, 6 tables

2110.09393 2021-10-19 cs.CL cs.AI 62%

Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language

Arushi Sharma, Anubha Kabra, Minni Jain

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted in Elsevier Journal of Information Processing and Management. Sharma and Kabra made equal contribution

2109.00194 2021-09-24 cs.CL cs.LG 62%

Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen, Jinho D. Choi

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to EMNLP 2021

2109.07141 2021-09-16 cs.CL cs.AI 62%

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Ke Wang, Yangbin Shi, Jiayi Wang, Yuqi Zhang, Yu Zhao, Xiaolin Zheng

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by Findings of EMNLP 2021

2108.04556 2021-09-10 cs.CL cs.AI cs.PL 62%

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, Xin Jiang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 9 pages, 3 figures, 5 tables

2103.09656 2021-09-10 cs.LG cs.AI 62%

Set-to-Sequence Methods in Machine Learning: a Review

Mateusz Jurewicz, Leon Strømberg-Derczynski

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI、cs.LG

Comments 46 pages of text, with 10 pages of references. Contains 2 tables and 4 figures. Updated version includes expanded notes on method comparison

Journal ref Journal of Artificial Intelligence Research 71 (2021): 885 - 924

2108.13766 2021-09-01 cs.CL cs.AI 62%

The five Is: Key principles for interpretable and safe conversational AI

Mattias Wahde, Marco Virgolin

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments 6 pages, one figure

2105.01060 2021-09-01 cs.CV cs.AI cs.LG cs.RO 62%

Curious Representation Learning for Embodied Intelligence

Yilun Du, Chuang Gan, Phillip Isola

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.AI、cs.LG

Comments To apear at ICCV 2021. Code is available at https://yilundu.github.io/crl

2012.12007 2021-08-11 cs.CL cs.AI 62%

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Yubo Xie, Junze Li, Pearl Pu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL-IJCNLP 2021

2107.09046 2021-07-20 cs.RO cs.AI cs.CV cs.LG 62%

Playful Interactions for Representation Learning

Sarah Young, Jyothish Pari, Pieter Abbeel, Lerrel Pinto

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.AI、cs.LG

2106.06697 2021-06-15 cs.CL cs.AI 62%

Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features

Francesco Ventura, Salvatore Greco, Daniele Apiletti, Tania Cerquitelli

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2101.07597 2021-06-11 cs.CL cs.LG cs.SD eess.AS 62%

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.CL、cs.LG

Comments accepted by ICML2021

2106.04905 2021-06-10 cs.CL cs.AI 62%

DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching

Kun Zhang, Guangyi Lv, Meng Wang, Enhong Chen

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by CICAI2021

2106.04631 2021-06-10 cs.CL cs.LG 62%

On the Lack of Robust Interpretability of Neural Text Classifiers

Muhammad Bilal Zafar, Michele Donini, Dylan Slack, Cédric Archambeau, Sanjiv Das, Krishnaram Kenthapadi

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Appearing at ACL Findings 2021

2106.02559 2021-06-07 cs.CL cs.LG 62%

Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing

Rowan Hall Maudslay, Ryan Cotterell

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

2106.02232 2021-06-07 cs.CL cs.AI 62%

Language Scaling for Universal Suggested Replies Model

Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2105.14478 2021-06-01 cs.CL cs.AI 62%

Pre-training Universal Language Representation

Yian Li, Hai Zhao

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ACL-IJCNLP 2021 main conference

2105.11741 2021-05-26 cs.CL cs.AI 62%

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Yuanmeng Yan, Rumei Li, Sirui Wang, Fuzheng Zhang, Wei Wu, Weiran Xu

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ACL2021, 10 pages, 7 figures, 4 tables

2104.06555 2021-05-12 cs.CL cs.AI 62%

Should Semantic Vector Composition be Explicit? Can it be Linear?

Dominic Widdows, Kristen Howell, Trevor Cohen

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

2105.04404 2021-05-11 stat.ML cs.AI cs.LG 62%

Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs

Théo Lacombe, Yuichi Ike, Mathieu Carriere, Frédéric Chazal, Marc Glisse, Yuhei Umeda

专题命中知识编辑与模型理解：post-training(abstract)；分类 cs.AI、cs.LG

Journal ref 2021 International Joint Conference on Artificial Intelligence, Aug 2021, Montr{é}al, Canada

2003.14056 2021-04-15 cs.CL cs.LG 62%

Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks

Prajit Dhar, Arianna Bisazza

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments v3: Submitted to NaDaLiDa 2021. 9 pages, two columns and with 6 figures and 1 table

2103.12258 2021-04-02 cs.CL cs.LG 62%

Hallucination of speech recognition errors with sequence to sequence learning

Prashant Serai, Vishal Sunder, Eric Fosler-Lussier

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Submitted to IEEE/ACM Transactions on Audio Speech and Language Processing

2010.07432 2021-03-30 cs.LG cs.CL cs.CV 62%

Viewmaker Networks: Learning Views for Unsupervised Representation Learning

Alex Tamkin, Mike Wu, Noah Goodman

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.CL、cs.LG

Comments ICLR 2021

2103.06089 2021-03-11 cs.LG cs.CL cs.SD eess.AS 62%

Variable-rate discrete representation learning

Sander Dieleman, Charlie Nash, Jesse Engel, Karen Simonyan

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments 26 pages, 15 figures, samples can be found at https://vdrl.github.io/

2102.08147 2021-02-17 cs.CL cs.LG 62%

Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents

Ryo Masumura, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Shota Orihashi

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at IEEE Spoken Language Technology Workshop (SLT), 2021, pp.1012-1019

2002.04397 2021-02-16 cs.SI cs.CL cs.LG stat.ML 62%

Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attention

Yuxiang Ren, Jiawei Zhang

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.LG

2102.04231 2021-02-09 cs.AI cs.LG cs.NE 62%

Neurogenetic Programming Framework for Explainable Reinforcement Learning

Vadim Liventsev, Aki Härmä, Milan Petković

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.AI、cs.LG

Comments Source code is available at https://github.com/vadim0x60/cibi

2101.00752 2021-01-05 cs.LG cs.AI 62%

Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph

Yuandong Wang, Hongzhi Yin, Tong Chen, Chunyang Liu, Ben Wang, Tianyu Wo, Jie Xu

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.AI、cs.LG

2006.13979 2020-12-17 cs.CL cs.LG cs.SD eess.AS 62%

Unsupervised Cross-lingual Representation Learning for Speech Recognition

Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli

专题命中知识编辑与模型理解：pretraining(abstract)；分类 cs.CL、cs.LG

2012.01631 2020-12-04 cs.CL cs.AI 62%

Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning

Wei Zhang, Murray Campbell, Yang Yu, Sadhana Kumaravel

专题命中知识编辑与模型理解：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to AAAI 2021

1. 知识编辑与模型理解 7583 篇

VisualSem: A High-quality Knowledge Graph for Vision and Language

Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language

Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation

Set-to-Sequence Methods in Machine Learning: a Review

The five Is: Key principles for interpretable and safe conversational AI

Curious Representation Learning for Embodied Intelligence

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Playful Interactions for Representation Learning

Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching

On the Lack of Robust Interpretability of Neural Text Classifiers

Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing

Language Scaling for Universal Suggested Replies Model

Pre-training Universal Language Representation

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Should Semantic Vector Composition be Explicit? Can it be Linear?

Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs

Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks

Hallucination of speech recognition errors with sequence to sequence learning

Viewmaker Networks: Learning Views for Unsupervised Representation Learning

Variable-rate discrete representation learning

Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents

Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attention

Neurogenetic Programming Framework for Explainable Reinforcement Learning

Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph

Unsupervised Cross-lingual Representation Learning for Speech Recognition

Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning