281 |
Joshua 6: A phrase-based and hierarchical statistical machine translation system
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 5-16 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
282 |
Sampling Phrase Tables for the Moses Statistical Machine Translation System
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 39-50 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
283 |
TmTriangulate: A Tool for Phrase Table Triangulation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 75-86 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
284 |
MT-ComparEval: Graphical evaluation interface for Machine Translation development
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 63-74 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
285 |
Box: Natural Language Processing Research Using Amazon Web Services
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 27-38 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
286 |
QuEst for High Quality Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 103, Iss 1, Pp 43-64 (2015) (2015)
|
|
BASE
|
|
Show details
|
|
287 |
Grasp: Randomised Semiring Parsing
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 104, Iss 1, Pp 51-62 (2015) (2015)
|
|
Abstract:
We present a suite of algorithms for inference tasks over (finite and infinite) context-free sets. For generality and clarity, we have chosen the framework of semiring parsing with support to the most common semirings (e.g. Forest, Viterbi, k-best and Inside). We see parsing from the more general viewpoint of weighted deduction allowing for arbitrary weighted finite-state input and provide implementations of both bottom-up (CKY-inspired) and top-down (Earley-inspired) algorithms. We focus on approximate inference by Monte Carlo methods and provide implementations of ancestral sampling and slice sampling. In principle, sampling methods can deal with models whose independence assumptions are weaker than what is feasible by standard dynamic programming. We envision applications such as monolingual constituency parsing, synchronous parsing, context-free models of reordering for machine translation, and machine translation decoding.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/f66667db5e18438082bbd8dfc05fc8af https://doi.org/10.1515/pralin-2015-0013
|
|
BASE
|
|
Hide details
|
|
|
|