语言大模型 / LLM - arXivDaily 专题

2109.10410 2021-09-23 cs.CL cs.IR cs.LG 62%

RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing

Vivek Gupta, Akshat Shrivastava, Adithya Sagar, Armen Aghajanyan, Denis Savenkov

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 12 pages, 9 figures, 5 Tables

2104.11070 2021-09-14 cs.CL cs.LG cs.SD 62%

Adapting Long Context NLM for ASR Rescoring in Conversational Agents

Ashish Shenoy, Sravan Bodapati, Monica Sunkara, Srikanth Ronanki, Katrin Kirchhoff

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to Interspeech 2021. arXiv admin note: text overlap with arXiv:2103.10325

2108.09355 2021-09-03 cs.CL cs.AI 62%

One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles

Zhengyi Ma, Zhicheng Dou, Yutao Zhu, Hanxun Zhong, Ji-Rong Wen

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted By SIGIR 2021, Full Papers. The code is available at https://github.com/zhengyima/DHAP

2107.06573 2021-07-15 cs.AI cs.LG physics.comp-ph 62%

A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer

Wenqi Zeng, Siqin Cao, Xuhui Huang, Yuan Yao

专题命中长上下文与记忆：language model(abstract)；分类 cs.AI、cs.LG

2106.08927 2021-06-17 cs.CL cs.LG 62%

On the long-term learning ability of LSTM LMs

Wim Boes, Robbe Van Rompaey, Lyan Verwimp, Joris Pelemans, Hugo Van hamme, Patrick Wambacq

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Journal ref ESANN 2020 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (2020) 625-630

2105.06548 2021-06-15 cs.LG cs.AI 62%

Not All Memories are Created Equal: Learning to Forget by Expiring

Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan

专题命中长上下文与记忆：language model(abstract)；分类 cs.AI、cs.LG

2105.03775 2021-05-11 cs.CL cs.IR cs.IT cs.LG math.IT 62%

NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer

Hossein Basafa, Sajad Movahedi, Ali Ebrahimi, Azadeh Shakery, Heshaam Faili

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 6 pages, 1 figure. Accepted in SemEval2021

1907.04670 2021-03-02 cs.LG cs.CL stat.CO stat.ML 62%

Improving the Performance of the LSTM and HMM Model via Hybridization

Larkin Liu, Yu-Chung Lin, Joshua Reid

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments Working Manuscript

2006.11527 2021-02-17 cs.CL cs.LG cs.NE 62%

Memory Transformer

Mikhail S. Burtsev, Yuri Kuratov, Anton Peganov, Grigory V. Sapunov

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

2102.05271 2021-02-11 cs.AR cs.AI cs.ET cs.LG 62%

Hybrid In-memory Computing Architecture for the Training of Deep Neural Networks

Vinay Joshi, Wangxin He, Jae-sun Seo, Bipin Rajendran

专题命中长上下文与记忆：post-training(abstract)；分类 cs.AI、cs.LG

Comments Accepted at ISCAS 2021 for publication

2002.09402 2021-01-26 cs.LG cs.CL stat.ML 62%

Addressing Some Limitations of Transformers with Feedback Memory

Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, Sainbayar Sukhbaatar

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

2101.09313 2021-01-26 cs.CL cs.LG 62%

$k$-Neighbor Based Curriculum Sampling for Sequence Prediction

James O' Neill, Danushka Bollegala

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments arXiv admin note: substantial text overlap with arXiv:1809.05916

2012.02287 2020-12-07 cs.IR cs.CL cs.LG 62%

Coarse-to-Fine Memory Matching for Joint Retrieval and Classification

Allen Schmaltz, Andrew Beam

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 19 pages, 3 figures, 7 tables (main: 11 pages, 2 figures, 4 tables)

1911.02972 2020-11-03 cs.CL cs.LG 62%

Blockwise Self-Attention for Long Document Understanding

Jiezhong Qiu, Hao Ma, Omer Levy, Scott Wen-tau Yih, Sinong Wang, Jie Tang

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at Findings of EMNLP'20 and SustaiNLP 2020 at EMNLP'20, 12 pages

2009.01719 2020-10-15 cs.CL cs.AI 62%

Grounded Language Learning Fast and Slow

Felix Hill, Olivier Tieleman, Tamara von Glehn, Nathaniel Wong, Hamza Merzic, Stephen Clark

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.AI

2004.07202 2020-10-08 cs.CL cs.LG 62%

Entities as Experts: Sparse Memory Access with Entity Supervision

Thibault Févry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi, Tom Kwiatkowski

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

2003.09833 2020-09-30 cs.CL cs.LG 62%

SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection

Xiaoya Li, Yuxian Meng, Mingxin Zhou, Qinghong Han, Fei Wu, Jiwei Li

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments To appear at NeurIPS 2020

2007.03356 2020-07-08 cs.LG cs.CL stat.ML 62%

Do Transformers Need Deep Long-Range Memory

Jack W. Rae, Ali Razavi

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments published at 58th Annual Meeting of the Association for Computational Linguistics. 6 pages, 4 figures, 1 table

2006.03274 2020-06-08 cs.LG cs.CL stat.ML 62%

GMAT: Global Memory Augmentation for Transformers

Ankit Gupta, Jonathan Berant

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

2006.01204 2020-06-03 cs.CL cs.AI 62%

Automatic Dialogic Instruction Detection for K-12 Online One-on-one Classes

Shiting Xu, Wenbiao Ding, Zitao Liu

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.AI

Comments The 21th International Conference on Artificial Intelligence in Education(AIED), 2020

1907.01409 2020-05-21 eess.AS cs.CL cs.LG cs.SD stat.ML 62%

Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR

Wilfried Michel, Ralf Schlüter, Hermann Ney

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments Submitted to Interspeech 2019

Journal ref Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019, pp. 1601--1605

2005.00048 2020-05-04 cs.CL cs.LG 62%

Context based Text-generation using LSTM networks

Sivasurya Santhanam

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, Abstract published in A2IC 2018 (https://www.premc.org/doc/A2IC2018/A2IC2018_Book_Of_Abstracts.pdf)

1911.03864 2020-04-24 cs.CL cs.LG 62%

Improving Transformer Models by Reordering their Sublayers

Ofir Press, Noah A. Smith, Omer Levy

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments To appear at ACL 2020

2004.07623 2020-04-23 cs.CL cs.LG 62%

Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack

Ankur Mali, Alexander Ororbia, Daniel Kifer, Clyde Lee Giles

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 14 pages, 10 tables

1912.11959 2020-01-01 cs.LG cs.CL stat.ML 62%

Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention

Thomas Dowdell, Hongyu Zhang

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 7 pages, 2 figures

1907.05242 2019-12-17 cs.CL cs.LG 62%

Large Memory Layers with Product Keys

Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments Advances in Neural Information Processing Systems, 2019

1912.01116 2019-12-04 cs.LG cs.CL cs.NE stat.ML 62%

Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling

Jeremy Gordon, David Rawlinson, Subutai Ahmad

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

Comments 9 pages, 6 figures, 4 tables

1911.06415 2019-11-18 cs.CL cs.LG 62%

Sparse associative memory based on contextual code learning for disambiguating word senses

Max Raphael Sobroza, Tales Marra, Deok-Hee Kim-Dufor, Claude Berrou

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

1911.03329 2019-11-11 cs.CL cs.LG cs.NE 62%

Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages

Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov, Stuart M. Shieber

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

1911.00461 2019-11-04 cs.CL cs.LG 62%

On the Unintended Social Bias of Training Language Generation Models with Data from Local Media

Omar U. Florez

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.LG

1. 长上下文与记忆 4789 篇

RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing

Adapting Long Context NLM for ASR Rescoring in Conversational Agents

One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles

A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer

On the long-term learning ability of LSTM LMs

Not All Memories are Created Equal: Learning to Forget by Expiring

NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer

Improving the Performance of the LSTM and HMM Model via Hybridization

Memory Transformer

Hybrid In-memory Computing Architecture for the Training of Deep Neural Networks

Addressing Some Limitations of Transformers with Feedback Memory

$k$-Neighbor Based Curriculum Sampling for Sequence Prediction

Coarse-to-Fine Memory Matching for Joint Retrieval and Classification

Blockwise Self-Attention for Long Document Understanding

Grounded Language Learning Fast and Slow

Entities as Experts: Sparse Memory Access with Entity Supervision

SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection

Do Transformers Need Deep Long-Range Memory

GMAT: Global Memory Augmentation for Transformers

Automatic Dialogic Instruction Detection for K-12 Online One-on-one Classes

Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR

Context based Text-generation using LSTM networks

Improving Transformer Models by Reordering their Sublayers

Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack

Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention

Large Memory Layers with Product Keys

Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling

Sparse associative memory based on contextual code learning for disambiguating word senses

Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages

On the Unintended Social Bias of Training Language Generation Models with Data from Local Media