搜索结果: 1-7 共查到“计算语言学 Rules”相关记录7条 . 查询时间(0.082 秒)
Deterministic Coreference Resolution Based on Entity-Centric,Precision-Ranked Rules
Coreference Resolution Entity-Centric Precision-Ranked Rules
2015/9/11
We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of de...
Sentence Comprehension:The Integration of Habits and Rules
Sentence Comprehension Habits Rules
2015/8/27
The last two decades have witnessed a great deal of activity in the development of computational theories of human sentence processing. The aim of such research is to explicitly identify and model the...
Rules or Connections in Past-Tense Inflections:What does the Evidence Rule Out?
Rules Inflectional Morphology Past Tense Connectionist Models Langauge Processing Parallel-Distributed Processing
2015/6/19
Pinker and colleagues propose two mechanisms—a rule system and a lexical memory—to form past tenses and other inflections. They predict that children’s acquisition of the regular inflection is sudden;...
Are Rules a Thing of the Past?:The Acquisition of Verbal Morphology by an Attractor Network
Thing of the Past Verbal Morphology Attractor Network
2015/6/19
This paper investigates the ability of a connectionist attractor network to learn a system analogous to part of the system of English verbal morphology. The model learned to produce phonological repre...
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules
Coreference Resolution Entity-Centric Precision-Ranked Rules
2015/6/10
We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of de...
Language Identification and Language Specific Letter-to-Sound Rules
Language Identification Language Specific Letter-to-Sound Rules
2008/12/26
This paper describes a system that improves automatic ARPABET transcription by addressing performance issues resulting from Arabic and Russian transliteration in English text. Our system is called EAR...
The Method of Chinese Spelling Error Correction Based on SLM and Rules
Chinese text automatic error-detecting Combing rule-based and statistics-based approaches non-multi-character word error orderly-neighborship statistical language model (SLM)
2010/7/8
According to the statistic analysis of common errors found in those Chinese texts that are typed-in, OCR-recognized or phonetics-recognized and the characteristics of such texts, a Chinese text automa...