Factored language model

Factored language model (FLM) is an extension of conventional Language model. In an FLM, each word is viewed as a vector of k factors: w_i = {f_i¹, ..., f_i^k}. An FLM provides the probabilistic model P(f|f₁, ..., f_N).

Like N-gram models, smoothing techniques are necessary in parameter estimation. In particular, generalized backing-off is used in training an FLM.

References

• {{cite conference}}: Empty citation (help)