[KongchangAI]
ConceptLipSpell 框架

LipSpell

A language-independent phonetic spelling correction framework that builds a phoneme distance matrix from IPA distinctive features, combines keyboard geometry and corpus frequency for weighted scoring, and accelerates candidate retrieval through two-stage indexing, supporting cross-lingual transfer.

Timeline (last 90 days)

Nov 19

LipSpell uses a language-agnostic phoneme scoring engine paired with a replaceable language front-end, pulling spelling correction from the orthographic level to the phonological level.

Unverified50%
Nov 19

LipSpell's phoneme distance matrix is precomputed based on IPA distinctive features, and the closer two phonemes are in feature space, the lower the substitution cost.

Unverified50%
Nov 19

LipSpell's unified scoring function combines three components: phoneme similarity, keyboard geometric distance, and a corpus unigram frequency prior.

Unverified50%
Nov 19

LipSpell uses two-stage symmetric deletion plus a seven-class phoneme-encoding index to accelerate candidate recall, doing a coarse filter first and then fine ranking.

Unverified50%
Nov 19

On six English benchmarks, LipSpell comprehensively outperforms Norvig and Hunspell.

Unverified50%
Nov 19

On the Norvig1 benchmark, LipSpell achieves 78.52% accuracy, while Aspell achieves 75.56%.

Unverified50%
Nov 19

On the Holbrook benchmark, LipSpell achieves 32.00% accuracy, while Aspell achieves 26.67%.

Unverified50%
Nov 19

When the fixed weights are transferred directly to Brazilian Portuguese, LipSpell achieves 73.00% Top-1 on 500 Wikipedia samples (without NFD tolerance), and 75.80% after tolerating NFD.

Unverified50%
Nov 19

Under tuned conditions, LipSpell's gains over Norvig are relatively pronounced on Portuguese (86.97% vs 76.75%), Turkish (81.67% vs 79.05%), Hebrew consonantal script (74.59% vs 62.30%), and French (74.53% vs 67.92%); English (80.37%) and Russian (85.67%) remain optimal with fixed weights.

Unverified50%
Nov 19

LipSpell was evaluated on six languages, covering five branches of the Germanic, Romance, Slavic, Semitic, and Turkic families, spanning the Indo-European, Afro-Asiatic, and Turkic language families and three writing systems.

Unverified50%

1 more timeline events

All Facts (11)

Unverified

LipSpell uses a language-agnostic phoneme scoring engine paired with a replaceable language front-end, pulling spelling correction from the orthographic level to the phonological level.

50%
Unverified

LipSpell's phoneme distance matrix is precomputed based on IPA distinctive features, and the closer two phonemes are in feature space, the lower the substitution cost.

50%
Unverified

LipSpell's unified scoring function combines three components: phoneme similarity, keyboard geometric distance, and a corpus unigram frequency prior.

50%
Unverified

LipSpell uses two-stage symmetric deletion plus a seven-class phoneme-encoding index to accelerate candidate recall, doing a coarse filter first and then fine ranking.

50%
Unverified

On six English benchmarks, LipSpell comprehensively outperforms Norvig and Hunspell.

50%
Unverified

On the Norvig1 benchmark, LipSpell achieves 78.52% accuracy, while Aspell achieves 75.56%.

50%
Unverified

On the Holbrook benchmark, LipSpell achieves 32.00% accuracy, while Aspell achieves 26.67%.

50%
Unverified

When the fixed weights are transferred directly to Brazilian Portuguese, LipSpell achieves 73.00% Top-1 on 500 Wikipedia samples (without NFD tolerance), and 75.80% after tolerating NFD.

50%
Unverified

Under tuned conditions, LipSpell's gains over Norvig are relatively pronounced on Portuguese (86.97% vs 76.75%), Turkish (81.67% vs 79.05%), Hebrew consonantal script (74.59% vs 62.30%), and French (74.53% vs 67.92%); English (80.37%) and Russian (85.67%) remain optimal with fixed weights.

50%
Unverified

LipSpell was evaluated on six languages, covering five branches of the Germanic, Romance, Slavic, Semitic, and Turkic families, spanning the Indo-European, Afro-Asiatic, and Turkic language families and three writing systems.

50%
Unverified

The phoneme front-end's dependence on G2P quality for low-resource languages is an unavoidable constraint when extending LipSpell to more languages.

50%

Source Articles