Атты І халықаралық конференция ЕҢбектері
Structural transfer in Apertium
жүктеу/скачать 8,57 Mb. Pdf көрінісі
|
Болатбек М. (1)
| Structural transfer in Apertium
The structural transfer module in Apertium processes the stream of source-language lexical form – target-language lexical form pairs (SL LF–TL LF pairs) and transforms it into a new sequence of TL LFs after a series of structural transfer operations specified in a set of rules: reordering, elimination or insertion of TL LFs, agreement, etc. Structural transfer rules have a pattern–action form: when a specific (finite-length) pattern of SL LFs is detected, an action builds and generates the corresponding sequence of TL LFs. Rules are applied in a greedy, left-to-right, longest-match fashion. There are two main modalities of structural transfer. The first one (used for related languages) generates the TL LF sequence in a single step. The second one (used in the English– Kazakh system described in this paper) uses three stages to improve the granularity of structural transfer rules (each one has its own rules file): 11 http://beta.visl.sdu.dk/cg3.html 325 A first round of transformations (“chunker”) detects SL LF patterns and generates the corresponding sequences of TL LFs grouped in chunks representing simple constituents such as noun phrases, prepositional phrases, etc. These chunks bear tags that may be used for inter-chunk processing. The second round (“interchunk”) reads patterns of chunks and produces a new sequence of chunks. This is the module where one can attempt to perform some longer-range reordering operations, inter-chunk agreement, case selection, etc. The third round (“postchunk”) transfers chunk-level tags to the lexical forms they contain and whose lexical-form-level tags are linked (through a referencing systems) to chunk-level tags (for instance, case determined for a noun phrase is transferred to the main noun), and removes all grouping information to generate the desired sequence of TL LFs. жүктеу/скачать 8,57 Mb. Достарыңызбен бөлісу:
|