There is a need to develop automated dialog systems, such as chatbots, which are capable of engaging in natural conversations with elderly users. We propose an example-based dialog system featuring an adaptation method which customizes the dialog for each user. After retrieving information about the user from the Web using the user’s profile, morpheme analysis is applied to the retrieval results and only proper nouns are extracted. Words which appear with high frequencies are considered to be related to the user. We then calculate the similarity between words related to the user and words in example phrases in the dialog system. Cosine similarity between distributed representations of words is calculated using Word2vec. We then generate a phrase which has been adapted to include a topic related to the user by substituting user-related words for highly similar words in the original example phrase. We manually evaluated the naturalness of the generated phrases and found that the system did in fact generate natural-sounding phrases. However, Word2vec sometimes mistook words which were grammatically different parts of speech (POS) for similar words, so we added a POS constraint to the substitution process. As a result, the system achieved higher phrase generation precision.
We have developed an adaptation method which allows the customization of example-based dialog systems for individual users by applying "plus" and "minus" operations to the distributed representations obtained using the word2vec method. After retrieving user-related profile information from the Web, named entity extraction is applied to the retrieval results. Words with a high term frequency-inverse document frequency (TF-IDF) score are then adopted as user related words. Next, we calculate the similarity between the distrubuted representations of selected user-related words and nouns in the existing example phrases, using word2vec embedding. We then generate phrases adapted to the user by substituting user-related words for highly similar words in the original example phrases. Word2vec also has a special property which allows the arithmetic operations "plus" and "minus" to be applied to distributed word representations. By applying these operations to words used in the original phrases, we are able to determine which user-related words can be used to replace the original words. The user-related words are then substituted to create customized example phrases. We evaluated the naturalness of the generated phrases and found that the system could generate natural phrases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.