Improved language modelling using bag of word pairs
نویسندگان
چکیده
The bag-of-words (BoW) method has been used widely in language modelling and information retrieval. A document is expressed as a group of words disregarding the grammar and the order of word information. A typical BoW method is latent semantic analysis (LSA), which maps the words and documents onto the vectors in LSA space. In this paper, the concept of BoW is extended to Bag-of-Word Pairs (BoWP), which expresses the document as a group of word pairs. Using word pairs as a unit, the system can capture more complex semantic information than BoW. Under the LSA framework, the BoWP system is shown to improve both perplexity and word error rate (WER) compared to a BoW system.
منابع مشابه
Psychometric Properties of the Persian Word Pairs Task for Declarative Memory Assessment
Objective: According to the declarative/procedural model, the semantic aspect of language depends on the brain structures responsible for declarative memory. The word pairs task is a common tool for evaluating declarative memory. The current study aimed to design a valid and reliable task for evaluating declarative memory in Persian children at learning and retention stages and to investigate i...
متن کاملWord Type Effects on L2 Word Retrieval and Learning: Homonym versus Synonym Vocabulary Instruction
The purpose of this study was twofold: (a) to assess the retention of two word types (synonyms and homonyms) in the short term memory, and (b) to investigate the effect of these word types on word learning by asking learners to learn their Persian meanings. A total of 73 Iranian language learners studying English translation participated in the study. For the first purpose, 36 freshmen from an ...
متن کاملEnriching machine-mediated speech-to-speech translation using contextual information
Conventional approaches to speech-to-speech (S2S) translation typically ignore key contextual information such as prosody, emphasis, discourse state in the translation process. Capturing and exploiting such contextual information is especially important in machine-mediated S2S translation as it can serve as a complementary knowledge source that can potentially aid the end users in improved unde...
متن کاملApproximate N-Gram Markov Model for Natural Language Generation
This paper proposes an Approximate n-gram Markov Model for bag generation. Directed word association pairs with distances are used to approximate (n-1)-gram and n-gram training tables. This model has parameters of word association model, and merits of both word association model and Markov Model. The training knowledge for bag generation can be also applied to lexical selection in machine trans...
متن کاملText Categorization
Text categorization is the task of assigning predefined categories to natural language text. With the widely used “bag-ofword” representation, previous researches usually assign a word with values that express whether this word appears in the document concerned or how frequently this word appears. Although these values are useful for text categorization, they have not fully expressed the abunda...
متن کامل