语言大模型 / LLM - arXivDaily 专题

1811.05249 2018-11-14 cs.LG cs.AI stat.ML 62%

Modular Networks: Learning to Decompose Neural Computation

Louis Kirsch, Julius Kunze, David Barber

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments NIPS 2018

1811.05121 2018-11-14 cs.CL cs.LG 62%

Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks

Chang Xu, Weiran Huang, Hongwei Wang, Gang Wang, Tie-Yan Liu

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1811.01307 2018-11-06 cs.CL cs.LG cs.SD eess.AS 62%

Towards Unsupervised Speech-to-Text Translation

Yu-An Chung, Wei-Hung Weng, Schrasing Tong, James Glass

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1805.09208 2018-09-28 stat.ML cs.CL cs.LG 62%

Pushing the bounds of dropout

Gábor Melis, Charles Blundell, Tomáš Kočiský, Karl Moritz Hermann, Chris Dyer, Phil Blunsom

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1809.05889 2018-09-18 cs.CR cs.AI cs.LG 62%

Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection

Mohit Sewak, Sanjay K. Sahay, Hemant Rathore

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments 11 Pages, 1 figure

Journal ref IEEE, pp. 293-296, 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2018

1809.04214 2018-09-13 cs.CL cs.IR cs.LG cs.SD eess.AS 62%

Automatic, Personalized, and Flexible Playlist Generation using Reinforcement Learning

Shun-Yao Shih, Heng-Yu Chi

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 7 pages, 4 figures, ISMIR 2018

1806.07000 2018-08-28 cs.CL cs.LG 62%

A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation

Jingyuan Li, Xiao Sun

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2018

1806.04535 2018-06-13 cs.CL cs.AI 62%

Automatic Target Recovery for Hindi-English Code Mixed Puns

Srishti Aggarwal, Kritik Mathur, Radhika Mamidi

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

1805.06201 2018-05-17 cs.CL cs.LG 62%

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations

Sosuke Kobayashi

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments NAACL 2018

1801.07736 2018-03-02 stat.ML cs.AI cs.LG 62%

MaskGAN: Better Text Generation via Filling in the______

William Fedus, Ian Goodfellow, Andrew M. Dai

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments 16 pages, ICLR 2018

1711.01694 2018-02-16 eess.AS cs.AI cs.CL 62%

Multilingual Speech Recognition With A Single End-To-End Model

Shubham Toshniwal, Tara N. Sainath, Ron J. Weiss, Bo Li, Pedro Moreno, Eugene Weinstein, Kanishka Rao

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted in ICASSP 2018

1801.00215 2018-01-03 cs.IR cs.AI cs.CL 62%

Learning Continuous User Representations through Hybrid Filtering with doc2vec

Simon Stiebellehner, Jun Wang, Shuai Yuan

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments 10 pages

1705.09037 2017-10-31 cs.NE cs.CL cs.LG 62%

Deriving Neural Architectures from Sequence and Graph Kernels

Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments extended version of ICML 2017 camera ready

1606.01305 2017-09-26 cs.NE cs.CL cs.LG 62%

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron Courville, Chris Pal

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments David Krueger and Tegan Maharaj contributed equally to this work

1512.00177 2017-09-25 cs.CL cs.AI cs.NE 62%

LSTM Neural Reordering Feature for Statistical Machine Translation

Yiming Cui, Shijin Wang, Jianfeng Li

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

Comments 6 pages, accepted by NAACL2016 short paper

1707.06556 2017-07-21 cs.CL cs.LG 62%

High-risk learning: acquiring new word vectors from tiny data

Aurelie Herbelot, Marco Baroni

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted as short paper at EMNLP 2017

1703.10356 2017-07-18 cs.LG cs.CL cs.NE 62%

Simplified End-to-End MMI Training and Voting for ASR

Lior Fritz, David Burshtein

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1605.08535 2017-07-17 cs.SE cs.CL cs.LG cs.NE 62%

Deep API Learning

Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments The paper is accepted at FSE 2016 (the 24th ACM SIGSOFT International Symposium on the Foundations of Software Engineering)

1702.08139 2017-06-20 cs.NE cs.CL cs.LG 62%

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov, Taylor Berg-Kirkpatrick

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments camera ready

1705.01346 2017-05-04 cs.CL cs.LG cs.NE 62%

Going Wider: Recurrent Neural Network With Parallel Cells

Danhao Zhu, Si Shen, Xin-Yu Dai, Jiajun Chen

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1511.03745 2017-02-21 cs.CV cs.CL cs.LG 62%

Grounding of Textual Phrases in Images by Reconstruction

Anna Rohrbach, Marcus Rohrbach, Ronghang Hu, Trevor Darrell, Bernt Schiele

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments published at ECCV 2016 (oral); updated to final version

1509.05962 2017-02-16 stat.ML cs.AI cs.CV cs.LG cs.NE 62%

Telugu OCR Framework using Deep Learning

Rakesh Achanta, Trevor Hastie

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

1701.01329 2017-01-06 cs.NE cs.AI cs.LG physics.chem-ph stat.ML 62%

Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks

Marwin H. S. Segler, Thierry Kogej, Christian Tyrchan, Mark P. Waller

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

Comments 17 pages, 17 figures

1312.5542 2017-01-05 cs.CL cs.LG 62%

Word Emdeddings through Hellinger PCA

Rémi Lebret, Ronan Collobert

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 9 pages, 5 tables

Journal ref Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2014

1612.06212 2016-12-20 cs.NE cs.CL cs.LG 62%

A recurrent neural network without chaos

Thomas Laurent, James von Brecht

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1605.01652 2016-05-06 cs.AI cs.CL 62%

LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues

Phong Le, Marc Dymetman, Jean-Michel Renders

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.AI

1511.08400 2016-04-27 cs.NE cs.CL cs.LG stat.ML 62%

Regularizing RNNs by Stabilizing Activations

David Krueger, Roland Memisevic

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1510.06786 2016-03-08 cs.CL cs.IR cs.LG 62%

Freshman or Fresher? Quantifying the Geographic Variation of Internet Language

Vivek Kulkarni, Bryan Perozzi, Steven Skiena

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

Comments 11 pages (updated submission)

1510.08565 2015-11-06 cs.NE cs.AI cs.HC cs.LG 62%

Attention with Intention for a Neural Network Conversation Model

Kaisheng Yao, Geoffrey Zweig, Baolin Peng

专题命中其他LLM ：language model(abstract)；分类 cs.AI、cs.LG

1508.01211 2015-08-21 cs.CL cs.LG cs.NE stat.ML 62%

Listen, Attend and Spell

William Chan, Navdeep Jaitly, Quoc V. Le, Oriol Vinyals

专题命中其他LLM ：language model(abstract)；分类 cs.CL、cs.LG

1. 其他LLM 12321 篇

Modular Networks: Learning to Decompose Neural Computation

Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks

Towards Unsupervised Speech-to-Text Translation

Pushing the bounds of dropout

Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection

Automatic, Personalized, and Flexible Playlist Generation using Reinforcement Learning

A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation

Automatic Target Recovery for Hindi-English Code Mixed Puns

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations

MaskGAN: Better Text Generation via Filling in the______

Multilingual Speech Recognition With A Single End-To-End Model

Learning Continuous User Representations through Hybrid Filtering with doc2vec

Deriving Neural Architectures from Sequence and Graph Kernels

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

LSTM Neural Reordering Feature for Statistical Machine Translation

High-risk learning: acquiring new word vectors from tiny data

Simplified End-to-End MMI Training and Voting for ASR

Deep API Learning

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Going Wider: Recurrent Neural Network With Parallel Cells

Grounding of Textual Phrases in Images by Reconstruction

Telugu OCR Framework using Deep Learning

Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks

Word Emdeddings through Hellinger PCA

A recurrent neural network without chaos

LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues

Regularizing RNNs by Stabilizing Activations

Freshman or Fresher? Quantifying the Geographic Variation of Internet Language

Attention with Intention for a Neural Network Conversation Model

Listen, Attend and Spell