paper-with-me

홈 › Papers

Sequential Recurrent Neural Networks for Language Modeling

2017-03-23 · Youssef Oualil, Clayton Greenberg, Mittul Singh, Dietrich Klakow

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some context information that cycles in the network. This paper presents a novel approach, which bridges the gap between these two categories of networks. In particular, we propose an architecture which takes advantage of the explicit, sequential enumeration of the word history in FNN structure while enhancing each word representation at the projection layer through recurrent context information that evolves in the network. The context integration is performed using an additional word-dependent weight matrix that is also learned during the training. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.

📄 PDF Abstract BibTeX arXiv:1703.08068

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingText Compression

Similar Papers 제목 키워드 기반

Feedforward Sequential Memory Neural Networks without Recurrent Feedback

2015-10-09 · ShiLiang Zhang, Hui Jiang, Si Wei, Li-Rong Dai

We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback. The proposed FSMN is a standard feedfo…

Language ModelingLanguage Modelling

Recurrent Neural Network Grammars

2016-02-25 · NAACL 2016 6 · Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith

We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Ex…

Constituency ParsingLanguage ModelingLanguage Modelling

Long Expressive Memory for Sequence Modeling

2021-10-10 · ICLR 2022 4 · T. Konstantin Rusch, Siddhartha Mishra, N. Benjamin Erichson, Michael W. Mahoney

We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies. LEM is gradient-based, it can efficiently process sequential tasks with very long-term dependencies, and it is…

Language ModelingLanguage ModellingSequential Image Classificationspeech-recognition+4

Language Modeling with Graph Temporal Convolutional Networks

2019-05-01 · ICLR 2019 5 · Hongyin Luo, Yichen Li, Jie Fu, James Glass

Recently, there have been some attempts to use non-recurrent neural models for language modeling. However, a noticeable performance gap still remains. We propose a non-recurrent neural language model, dubbed graph temp…

Graph Neural NetworkLanguage ModelingLanguage Modelling

Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency

2015-12-28 · Shiliang Zhang, Cong Liu, Hui Jiang, Si Wei 외

In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback. The proposed FSMN is…

Language Modellingspeech-recognitionSpeech RecognitionTime Series+1