A GRU-based Pipeline Approach for Word-Sentence Segmentation and Punctuation Restoration in English.
Jasivan SivakumarJake MugaFlavio SpadavecchiaDaniel WhiteBurcu CanPublished in: IALP (2021)
Keyphrases
- english text
- word level
- word segmentation
- stop words
- parallel corpus
- natural language
- sentence pairs
- training corpus
- target language
- segmentation algorithm
- language independent
- sentence level
- level set
- image segmentation
- unknown words
- word order
- word recognition
- part of speech
- source language
- natural language generation
- linguistic features
- numeral strings
- n gram
- text corpus
- noun phrases
- semantic roles
- english words
- recognizing textual entailment
- syntactic categories
- syntactic analysis
- dependency tree
- multiword
- co occurrence
- machine translation
- word sense disambiguation
- tf idf
- language identification
- word sense
- parse tree
- sentence similarity
- computing semantic relatedness
- indian languages
- text to speech
- word pairs
- document images
- image restoration
- wordnet