Multilingual word embeddings for the assessment of narrative speech in mild cognitive impairment. (January 2019)

• Record Type: Journal Article
• Authors: Fraser, Kathleen C.; Lundholm Fors, Kristina; Kokkinakis, Dimitrios
• Is Part Of: Computer speech & language. Volume 53(2019)
• Page Start: 121
• Page End: 139
• Publication Date: 2019-01
• Subjects: Machine learning -- Topic modeling -- Mild cognitive impairment -- Dementia -- Narrative analysis -- Multilingual analysis; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2018.07.005
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: An analysis of Cookie Theft narratives in English and Swedish is presented. Multilingual word embeddings are clustered to generate multilingual topics. Features extracted from the topic model help detect mild cognitive impairment. Classification accuracy is 63% (English) and 72% (Swedish). Multilingual topic models outperform monolingual models in both languages. Abstract: We analyze the information content of narrative speech samples from individuals with mild cognitive impairment (MCI), in both English and Swedish, using a combination of supervised and unsupervised learning techniques. We extract information units using topic models trained on word embeddings in monolingual and multilingual spaces, and find that the multilingual approach leads to significantly better classification accuracies than training on the target language alone. In many cases, we find that augmenting the topic model training corpus with additional clinical data from a different language is more effective than training on additional monolingual data from healthy controls. Ultimately we are able to distinguish MCI speakers from healthy older adults with accuracies of up to 63% (English) and 72% (Swedish) on the basis of information content alone. We also compare our method against previous results measuring information content in Alzheimer's disease, and report an improvement over other topic-modeling approaches. Furthermore, our results support the hypothesis that subtle differences in language can be detected in narrative speech, even at the very early stages of cognitive decline, when scores on screening tools such as the Mini-Mental State Exam are still in the "normal" range.