Multi-Rate HMMs for Word Alignment
نویسندگان
چکیده
We apply multi-rate HMMs, a tree structured HMM model, to the word-alignment problem. Multi-rate HMMs allow us to model reordering at both the morpheme level and the word level in a hierarchical fashion. This approach leads to better machine translation results than a morphemeaware model that does not explicitly model morpheme reordering.
منابع مشابه
Multiple Word Alignment with Profile Hidden Markov Models
Profile hidden Markov models (Profile HMMs) are specific types of hidden Markov models used in biological sequence analysis. We propose the use of Profile HMMs for word-related tasks. We test their applicability to the tasks of multiple cognate alignment and cognate set matching, and find that they work well in general for both tasks. On the latter task, the Profile HMM method outperforms avera...
متن کاملAsynchrony modeling for audio-visual speech recognition
We investigate the use of multi-stream HMMs in the automatic recognition of audio-visual speech. Multi-stream HMMs allow the modeling of asynchrony between the audio and visual state sequences at a variety of levels (phone, syllable, word, etc.) and are equivalent to product, or composite, HMMs. In this paper, we consider such models synchronized at the phone boundary level, allowing various de...
متن کاملA novel approach for matched reverberant training of HMMs using data pairs
For robust distant-talking speech recognition, a novel HMM training approach using data pairs is proposed. The data pairs of clean and reverberant feature vectors, also called stereo data, are used for deriving the HMM parameters of a matched-condition reverberant HMM from a well-trained clean-speech HMM in two steps. In the first step, the alignment of the frames to the states is determined fr...
متن کاملRegularizing Mono- and Bi-Word Models for Word Alignment
Conditional probabilistic models for word alignment are popular due to the elegant way of handling them in the training stage. However, they have weaknesses such as garbage collection and scale poorly beyond single word based models (DeNero et al., 2006): not all parameters should actually be used. To alleviate the problem, in this paper we explore regularity terms that penalize the used parame...
متن کاملUsing Information About Multi-Word Expressions For The Word-Alignment Task
It is well known that multi-word expressions are problematic in natural language processing. In previous literature, it has been suggested that information about their degree of compositionality can be helpful in various applications but it has not been proven empirically. In this paper, we propose a framework in which information about the multi-word expressions can be used in the word-alignme...
متن کامل