RNNLM - Recurrent Neural Network Language Modeling Toolkit

By Tomas Mikolov, Stefan Kombrink, Anoop Deoras, Lukáš Burget, Jan Honza Cernocký. 2011

332 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/86d62362d50fd3d26f0c049fc72d4cf40bd218b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks (2014, background): “For example, RNN language model (Mikolov et al. 2010; Mikolov et al. 2011a; Mikolov et al. 2011b) successfully leverages long-span sequential information among the massive language corpus, which results in better performance than traditional neural networks language model (Bengio et al. 2006).”
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation (2019, background): “Recent developments in neural language models (Mikolov and Zweig, 2012), (Reiter and Belz, 2009), (Mikolov et al., 2011b), (Mikolov et al.”
Embedding Logic Rules Into Recurrent Neural Networks (2019, unknown): “[12] and Hochreiter and Schmidhuber [13].”
Multiscale recurrent neural network based language model (2015, background): “More detailed explanations about training this network are described in [1, 2, 6].”
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, methodology): “An l 2 regularisation term was added to the objective function for every 10 training examples as suggested in Mikolov et al. (2011b).”
On Using Monolingual Corpora in Neural Machine Translation (2015, methodology): “Without loss of generality, we use a language model based on recurrent neural networks (RNNLM, (Mikolov et al., 2011)) which is equivalent to the decoder described in the previous section except that it is not biased by a context vector (i.”
A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition (2018, background): “In recent years, with the accessibility of greater computing power, recurrent neural network language models (RNNLM) [1] have become possible and have quickly surpassed back-off n-gram models [2] in various language-related tasks.”
Recurrent neural network based language model personalization by social network crowdsourcing (2013, methodology): “For RNNLMs, we utilized the RNNLM toolkit [45] for implementation.”
From Feedforward to Recurrent LSTM Neural Networks for Language Modeling (2015, methodology): “Following recommendations given in [45], we make use of a ‘ ’ value of 6, and we train the RNN in block mode with ‘ ’ set to 10 and ‘ ’ set to 1.”
Structured Output Layer Neural Network Language Models for Speech Recognition (2013, background): “Another active direction of research dealing with different clustering methods is connected with recently proposed Model M and its enhancements [19], [20].”
Towards Decoding as Continuous Optimisation in Neural Machine Translation (2017, background): “ortance of the additional monolingual language model, and PLM (y |x) is the target language model (e.g., N-gram (Koehn, 2010), NPLM (Bengio et al., 2003), RNNLM (Mnih and Hinton, 2007; Mikolov, 2012; Mikolov et al., 2011)). It’s worth noting that the additional monolingual language model can play a ”
Named Entity Recognition with Bidirectional LSTM-CNNs (2015, background): “Recently, RNNs have shown great success in diverse NLP tasks such as speech recognition (Graves et al., 2013), machine translation (Cho et al., 2014), and language modeling (Mikolov et al., 2011).”
Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks (2016, unknown): “We also tried a variant of the LSTM model, gated recurrent units (Cho et al., 2014), but the results were generally lower than LSTM. word vectors pretrained with GloVe on Twitter (Pennington et al., 2014) for MRDA and SwDA, as these choices yielded the best results among all publicly available word2”
Auto-Sizing Neural Networks: With Applications to n-gram Language Models (2015, background): “RNNLM is an open-source implementation of a language model using recurrent neural networks (RNN) where connections between units can form directed cycles (Mikolov et al., 2011).”
JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS (2015, methodology): “We used the RNNLM toolkit (0.3e) [32] to train our recurrent neural network language models (RNN-LMs).”