Factorization of Language Models through Backing-Off Lattices
Wei Wang
Abstract
Factorization of statistical language models is the task that we resolve the most discriminative model into factored models and determine a new model by combining them so as to provide better estimate. Most of previous works mainly focus on factorizing models of sequential events, each of which allows only one factorization manner. To enable parallel factorization, which allows a model event to be resolved in more than one ways at the same time, we propose a general framework, where we adopt a backing-off lattice to reflect parallel factorizations and to define the paths along which a model is resolved into factored models, we use a mixture model to combine parallel paths in the lattice, and generalize Katz's backing-off method to integrate all the mixture models got by traversing the entire lattice. Based on this framework, we formulate two types of model factorizations that are used in natural language modeling.
Create a lesson
Related papers
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
Taoyong Cui, Pinxian Zeng, Wanghan Xu et al.
When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors
Shubh Garg, Chen Shani
Structural Automata for Neural Semantic Parsing
Xiao Zhang
Task Context Shapes Component Roles in Language Models
Sovesh Mohapatra, Dani S Bassett
Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection
Juan Terven, Diana-Margarita Córdova-Esparza, Ruben Gomez et al.
Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR
Katsumi Ibaraki, David Chiang