Papers with EM algorithm

6 papers
Probabilistic Bilingual Subword Segmentation with Latent Subword Alignment (2026.eacl-srw)

Copied to clipboard

Challenge: Existing methods do not consider parallel relationships, preventing translation model training.
Approach: They propose a method for learning subword correspondences in parallel sentence pairs using the EM algorithm.
Outcome: The proposed method improves translation accuracy for many tasks.
Unsupervised Speech-text word-level alignment with Dynamic Programming (2025.findings-naacl)

Copied to clipboard

Challenge: Word-level alignment in speech-text pretraining models is limited by word-level annotated data . authors propose an iterative training method for USDP that reduces the dependency on scarce annotation resources.
Approach: They propose an Unsupervised Speech-text word-level alignment with Dynamic Programming (USDP) this method uses Dynamic programming principles to iteratively refine temporal alignment predictions .
Outcome: The proposed method significantly improves on speech-text pretraining tasks compared to existing methods.
LATENTLOGIC: Learning Logic Rules in Latent Space over Knowledge Graphs (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for learning logic rules for knowledge graph reasoning face limitations such as searching in vast search space and inefficient optimization.
Approach: They propose a framework to efficiently mine logic rules by controllable generation in the latent space by a pre-trained VAE and a discriminator.
Outcome: The proposed framework efficiently mines logic rules by controllable generation in the latent space.
Retrieval-Augmented Few-shot Text Classification (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for retrieval-augmented text classification are successful in the few-shot scenario with limited retrieval space.
Approach: They propose to use EM-L and R-L to provide task-specific guidance to retrieval metric . they also propose to incorporate retrieved memory alongside parameters for better generalization .
Outcome: The proposed methods perform better on the few-shot scenario with limited retrieval space.
Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing (2022.lrec-1)

Copied to clipboard

Challenge: A variety of hierarchical RNN models have been proposed to incorporate hierarchically-based hierarchic information in modeling languages in the literature.
Approach: They propose a latent indicator layer approach to identify and learn hierarchical information and develop an EM algorithm to handle the latent indicators layer in training.
Outcome: The proposed approach outperforms other RNN-based models in document classification tasks.
Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)

Copied to clipboard

Challenge: evaluating superLLMs is especially difficult because of their intelligence-intensive nature.
Approach: They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated .
Outcome: The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations