Improved Training Of Neural Trans-Dimensional Random field Language Models with Dynamic Noise-Contrastive Estimation

By Zhijian Ou. 2018

15 citations recorded by the source corpus.

A new whole-sentence language model - neural trans-dimensional random field language model (neural TRF LM), where sentences are modeled as a collection of random fields, and the potential function is defined by a neural network, has been introduced and successfully trained by noise-contrastive estimation (NCE). In this paper, we extend NCE and propose dynamic noise-contrastive estimation (DNCE) to solve the two problems observed in NCE training. First, a dynamic noise distribution is introduced and trained simultaneously to converge to the data distribution. This helps to significantly cut down the noise sample number and reduce the training cost over NCE. Second, DNCE discriminates between sentences generated from the noise distribution and sentences generated from the interpolation of the data distribution and the noise distribution. This alleviates the overfitting problem caused by the sparseness of the training set. With DNCE, we can successfully and efficiently train neural TRF LMs on large corpus (about 0.8 billion words) with large vocabulary (about 568 K words). Neural TRF LMs perform as good as LSTM LMs with less parameters and being 5x~114x faster in rescoring sentences. Interpolating neural TRF LMs with LSTM LMs and n-gram LMs can further reduce the error rates.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Residual Energy-Based Models for Text Generation (2020, methodology): “We investigated an EBM trained on the residual of a pretrained autoregressive language model (Wang & Ou, 2018b; Parshakova et al., 2019).”
Residual Energy-Based Models for Text (2021, methodology): “EBMs have been used for sequence modeling (Rosenfeld et al., 2001; Wang et al., 2015, 2017; Wang and Ou, 2017, 2018a; Parshakova et al., 2019).”
Energy-Based Models for Text (2020, methodology): “EBMs have been used for sequence modeling (Rosenfeld et al., 2001; Wang et al., 2015, 2017; Wang and Ou, 2017, 2018a; Parshakova et al., 2019).”