\text{\{<sos> a a, <sos> a b, <sos> a <eos>, <sos> b a, <sos> b b, <sos> b <eos>\}}\nonumber
\end{eqnarray}
\parinterval 此时可以划分出长度为1的完整单词序列集合\{<sos> a <eos>, <sos> b <eos>\}，以及长度为2的未结束的单词序列片段集合\{<sos> a a, <sos> a b, <sos> b a, <sos> b b\}。如此类推，继续生成未结束序列，直到单词序列的长度达到所允许的最大长度。
\parinterval 此时可以划分出长度为1的完整单词序列集合\{<sos> a <eos>, <sos> b <eos>\}，以及长度为2的未结束单词序列片段集合\{<sos> a a, <sos> a b, <sos> b a, <sos> b b\}。以此类推，继续生成未结束序列，直到单词序列的长度达到所允许的最大长度。
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2011418219",
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2011418219},
year={1965}
}
...
...
@@ -1387,7 +1387,7 @@
volume={42},
number={2},
pages={189--211},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2021061679",
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2021061679},
year={1990}
}
...
...
@@ -1398,7 +1398,7 @@
volume={8},
number={1},
pages={1--38},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2075201173",
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2075201173},
year={1994}
}
...
...
@@ -1407,9 +1407,269 @@
author={H. {Ney} and U. {Essen}},
booktitle={[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing},
pages={825--828},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2020749563",
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2020749563},
year={1991}
}
@article{chen1999an,
title={An empirical study of smoothing techniques for language modeling},
author={Stanley F. {Chen} and Joshua {Goodman}},
journal={Computer Speech \& Language},
volume={13},
number={4},
pages={359--394},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2158195707},
year={1999}
}
%需要确认
@book{bell1990text,
title={Text compression},
author={Timothy C. {Bell} and John G. {Cleary} and Ian H. {Witten}},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2611071497},
year={1990},
publisher={Prentice-Hall, Inc.}
}
@article{katz1987estimation,
title={Estimation of probabilities from sparse data for the language model component of a speech recognizer},
author={S. {Katz}},
journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
volume={35},
number={3},
pages={400--401},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2134237567},
year={1987}
}
@article{witten1991the,
title={The zero-frequency problem: estimating the probabilities of novel events in adaptive text compression},
author={I.H. {Witten} and T.C. {Bell}},
journal={IEEE Transactions on Information Theory},
volume={37},
number={4},
pages={1085--1094},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2113641473},
year={1991}
}
@article{jelinek1980interpolated,
title={Interpolated estimation of Markov source parameters from sparse data},
author={F. {Jelinek}},
journal={Proc. Workshop on Pattern Recognition in Practice, 1980},
pages={381--397},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/1597533204},
year={1980}
}
@article{goodman2001a,
title={A Bit of Progress in Language Modeling Extended Version},
author={Joshua T. {Goodman}},
journal={Machine Learning and Applied Statistics Group Microsoft Research. Technical Report, MSR-TR-2001-72},
volume={28},
////notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/10704533},
year={2001}
}
@inproceedings{heafield2011kenlm,
title={KenLM: Faster and Smaller Language Model Queries},
author={Kenneth {Heafield}},
booktitle={Proceedings of the Sixth Workshop on Statistical Machine Translation},
pages={187--197},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2134800885",
year={2011}
}
@inproceedings{koehn2007factored,
title={Factored Translation Models},
author={Philipp {Koehn} and Hieu {Hoang}},
booktitle={Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
pages={868--876},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2113788796",
year={2007}
}
@inproceedings{talbot2007randomised,
title={Randomised Language Modelling for Statistical Machine Translation},
author={David {Talbot} and Miles {Osborne}},
booktitle={Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics},
pages={512--519},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2106540279",
year={2007}
}
@inproceedings{federico2007efficient,
title={Efficient Handling of N-gram Language Models for Statistical Machine Translation},
author={Marcello {Federico} and Mauro {Cettolo}},
booktitle={Proceedings of the Second Workshop on Statistical Machine Translation},
pages={88--95},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2125750666",
year={2007}
}
@inproceedings{talbot2007smoothed,
title={Smoothed Bloom Filter Language Models: Tera-Scale LMs on the Cheap},
author={David {Talbot} and Miles {Osborne}},
booktitle={Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
pages={468--476},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/162552777},
year={2007}
}
@inproceedings{kirchhoff2005improved,
title={Improved Language Modeling for Statistical Machine Translation},
author={Katrin {Kirchhoff} and Mei {Yang}},
booktitle={Proceedings of the ACL Workshop on Building and Using Parallel Texts},
pages={125--128},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2097661835",
year={2005}
}
@inproceedings{federico2006how,
title={How Many Bits Are Needed To Store Probabilities for Phrase-Based Translation?},
author={Marcello {Federico} and Nicola {Bertoldi}},
booktitle={Proceedings on the Workshop on Statistical Machine Translation},
pages={94--101},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2103803302",
year={2006}
}
@inproceedings{sarikaya2007joint,
title={Joint Morphological-Lexical Language Modeling for Machine Translation},
author={Ruhi {Sarikaya} and Yonggang {Deng}},
booktitle={Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers},
pages={145--148},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2152277656",
year={2007}
}
@inproceedings{vaswani2017attention,
title={Attention is All You Need},
author={Ashish {Vaswani} and Noam {Shazeer} and Niki {Parmar} and Jakob {Uszkoreit} and Llion {Jones} and Aidan N. {Gomez} and Lukasz {Kaiser} and Illia {Polosukhin}},
booktitle={Proceedings of the 31st International Conference on Neural Information Processing Systems},
pages={5998--6008},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2963403868",
year={2017}
}
@inproceedings{mikolov2010recurrent,
title={Recurrent neural network based language model},
author={Tomas {Mikolov} and Martin {Karafiát} and Lukás {Burget} and Jan {Cernocký} and Sanjeev {Khudanpur}},
booktitle={INTERSPEECH},
pages={1045--1048},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/179875071",
year={2010}
}
@article{bengio2003a,
title={A neural probabilistic language model},
author={Yoshua {Bengio} and Réjean {Ducharme} and Pascal {Vincent} and Christian {Janvin}},
journal={Journal of Machine Learning Research},
volume={3},
number={6},
pages={1137--1155},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2132339004",
year={2003}
}
@inproceedings{sundermeyer2012lstm,
title={LSTM Neural Networks for Language Modeling.},
author={Martin {Sundermeyer} and Ralf {Schlüter} and Hermann {Ney}},
booktitle={INTERSPEECH},
pages={194--197},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2402268235",
year={2012}
}
@inproceedings{dai2019transformer,
title={Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
author={Zihang {Dai} and Zhilin {Yang} and Yiming {Yang} and Jaime {Carbonell} and Quoc {Le} and Ruslan {Salakhutdinov}},
booktitle={ACL 2019 : The 57th Annual Meeting of the Association for Computational Linguistics},
pages={2978--2988},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2964110616",
year={2019}
}
@article{jing2019a,
title={A Survey on Neural Network Language Models.},
author={Kun {Jing} and Jungang {Xu}},
journal={arXiv preprint arXiv:1906.03591},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2948559998",
year={2019}
}
@inproceedings{germann2001fast,
title={Fast Decoding and Optimal Decoding for Machine Translation},
author={Ulrich {Germann} and Michael {Jahr} and Kevin {Knight} and Daniel {Marcu} and Kenji {Yamada}},
booktitle={Proceedings of 39th Annual Meeting of the Association for Computational Linguistics},
pages={228--235},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2139403546},
year={2001}
}
@inproceedings{huang2007forest,
title={Forest Rescoring: Faster Decoding with Integrated Language Models},
author={Liang {Huang} and David {Chiang}},
booktitle={Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics},
pages={144--151},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2161227214},
year={2007}
}
@inproceedings{tillmann1997a,
title={A DP-based Search Using Monotone Alignments in Statistical Translation},
author={Christoph {Tillmann} and Stephan {Vogel} and Hermann {Ney} and Alex {Zubiaga}},
booktitle={Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics},
pages={289--296},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2158164089",
year={1997}
}
@inproceedings{wang1997decoding,
title={Decoding Algorithm in Statistical Machine Translation},
author={Ye-Yi {Wang} and Alex {Waibel}},
booktitle={Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics},
pages={366--372},
//notes={Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2012511220},
year={1997}
}
@inproceedings{germann2003greedy,
title={Greedy decoding for statistical machine translation in almost linear time},
author={Ulrich {Germann}},
booktitle={NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1},
pages={1--8},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2160233880",
year={2003}
}
@inproceedings{venugopal2007an,
title={An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT},
author={Ashish {Venugopal} and Andreas {Zollmann} and Vogel {Stephan}},
booktitle={Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference},
pages={500--507},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2105132850",
year={2007}
}
@inproceedings{bangalore2001a,
title={A finite-state approach to machine translation},
author={S. {Bangalore} and G. {Riccardi}},
booktitle={IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.},
pages={381--388},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2116912781",
year={2001}
}
@inproceedings{bangalore2000stochastic,
title={Stochastic finite-state models for spoken language machine translation},
author={Srinivas {Bangalore} and Giuseppe {Riccardi}},
booktitle={NAACL-ANLP-EMTS '00 Proceedings of the 2000 NAACL-ANLP Workshop on Embedded machine translation systems - Volume 5},
pages={52--59},
//notes="Sourced from Microsoft Academic - https://academic.microsoft.com/paper/2114532736",
