Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Unsupervised Neural Hidden Markov Models

About

In this work, we present the first results for neuralizing an Unsupervised Hidden Markov Model. We evaluate our approach on tag in- duction. Our approach outperforms existing generative models and is competitive with the state-of-the-art though with a simpler model easily extended to include additional context.

Ke Tran, Yonatan Bisk, Ashish Vaswani, Daniel Marcu, Kevin Knight• 2016

Related benchmarks

TaskDatasetResultRank
ForecastingExchange (test)
MSE100
63
Time Series ForecastingTraffic
MAE1.5881
58
State estimation3-variable simulated dataset (No. 2) with frequent transitions v1 (test)
Accuracy68.5
18
Forecasting and state estimation10-variable simulated dataset (infrequent transitions)
Accuracy75.55
18
Unsupervised POS taggingWSJ entire corpus (full)
M1 Score79.1
13
ForecastingExchange dataset
MAE4.4926
13
Forecasting3-variable simulated dataset with infrequent transitions (test)
MAE0.1277
9
ForecastingSimulated dataset (3 variables) with infrequent transitions
MAE0.1277
9
ForecastingTraffic (test)
MAE1.5881
9
ForecastingSMachine
MAE0.0194
9
Showing 10 of 20 rows

Other info

Follow for update