Incremental HMM alignment for MT system combination

Abstract

Inspired by the incremental TER alignment, we redesigned the Indirect HMM (IHMM) alignment, which is one of the best hypothesis alignment methods for conventional MT system combination, in an incremental manner. One crucial problem of incremental alignment is to align a hypothesis to a confusion network (CN). Our incremental IHMM alignment is implemented in three different ways: 1) treat CN spans as HMM states and define state transition as distortion over covered ngrams between two spans; 2) treat CN spans as HMM states and define state transition as distortion over words in component translations in the CN; and 3) use a consensus decoding algorithm over one hypothesis and multiple IHMMs, each of which corresponds to a component translation in the CN. All these three approaches of incremental alignment based on IHMM are shown to be superior to both incremental TER alignment and conventional IHMM alignment in the setting of the Chinese-to-English track of the 2008 NIST Open MT evaluation.

Joint optimization for machine translation system combination

“…However, the gain of incremental HMM over IHMM is smaller than that reported in Li et al (2009). One possible reason of such discrepancy could be that fewer hypotheses are used for combination in this experiment compared to that of Li et al (2009), so the performance difference between them is narrowed accordingly. Despite that, the proposed joint decoding method outperforms both IHMM and IncHMM baselines significantly.…”

“…The baselines include a pair-wise hypothesis alignment approach using the indirect HMM (IHMM) proposed by He et al (2008), and an incremental hypothesis alignment approach using the incremental HMM (IncHMM) proposed by Li et al (2009). The lexical translation model used to compute the semantic similarity is estimated from two million parallel sentencepairs selected from the training corpus of MT08.…”

“…Incremental alignment methods have been proposed to relax the independence assumption of pair-wise alignment (Rosti et al 2008, Li et al 2009). Such methods align hypotheses to a partially constructed CN in some order.…”

Conditional Random Fields for Machine Translation System Combination

“…h 0 in Table I. To construct a CN, the remaining hypotheses would be aligned to skeleton [10], [3], [8] or to partially constructed CN [7], [12].…”

A Probabilistic Model Based Approach For Aligning Multiple Audio Sequences

“…Image stitching is another visual analogy in which multiple images of the same scene taken from slightly different perspectives are assembled into a full panoramic view [21]. In machine translation systems, similar methods exist for word alignment between a skeleton translation and a hypothesis translation [22], [23].…”