Papers with HMMs
Neural Particle Smoothing for Sampling from Conditional Sequence Models (N18-1)
Copied to clipboard
| Challenge: | In structured prediction problems, labeling an input string with a length-T sequence of tags becomes intractable. |
| Approach: | They propose a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. |
| Outcome: | The proposed method improves the quality of the sample. |
Scaling Hidden Markov Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Hidden Markov models are a fundamental tool for sequence modeling that separates the hidden state from the emission structure. |
| Approach: | They propose methods for scaling hidden Markov models to massive state spaces while maintaining efficient exact inference and effective regularization. |
| Outcome: | The proposed methods are much more accurate than previous HMMs and n-gram-based methods, making progress towards the performance of state-of-the-art NN models. |
Can Rumour Stance Alone Predict Veracity? (C18-1)
Copied to clipboard
| Challenge: | Existing studies of automatic veracity classification of social media rumours have not explored the effectiveness of crowd stance to determine veracity. |
| Approach: | They propose to use stance as an additional feature to those commonly used in earlier studies to model the veracity of a rumour using Hidden Markov Models and collective stance information to model a social media rumor. |
| Outcome: | The proposed models outperform those using crowd stance and tweets’ times as the only features for modelling true and false rumours. |
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs (2022.naacl-main)
Copied to clipboard
| Challenge: | Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models. |
| Approach: | They use tensor rank decomposition to reduce computational complexities for a subset of FGGs subsuming HMMs and PCFGs. |
| Outcome: | The proposed model performs better on HMM modeling and unsupervised PCFG parsing than previous work. |
Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent work on scaling-up HMMs to perform competitively as language models has indicated that this challenge only increases with larger hidden state sizes. |
| Approach: | They propose two strategies that use neural reparameterization and neural initialization to enhance HMM optimization. |
| Outcome: | The proposed techniques work well for scaled HMM language modeling, and linear reparameterizations can be as effective as non-linear ones, and the strategies are complementary. |
An HMM Approach with Inherent Model Selection for Sign Language and Gesture Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | despite the extensive use of HMMs for sign recognition, determining the HMM structure remains a challenge . despite their success in modeling sequential and multivariate data, establishing the structure remains challenging . |
| Approach: | They propose a continuous HMM framework for modeling and recognizing isolated signs . they propose to optimize the number of states for each sign separately during recognition . |
| Outcome: | The proposed model performs better on three different datasets and is competitive with existing models. |