Detecting formal thought disorder by deep contextualized word representations

Sarzyńska-Wawer, Justyna; Wawer, Aleksander; Pawlak, Aleksandra; Szymanowska, Julia; Stefaniak, Izabela; Jarkiewicz, M.; Okruszek, Łukasz

doi:10.1016/j.psychres.2021.114135

Cited by 201 publications

(88 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Andreasen, 1979). However, this assumption has only inconsistently been supported by the literature, with highly varying statistical significance and size of the effects found across studies: while some studies found a strong correlation between semantic coherence and measures of formal thought disorder (Bilgrami et al, 2022; Elvevåg et al, 2007), most others reported uncertain results (Bedi et al, 2015; Haas et al, 2020; Just et al, 2020; Morgan et al, 2021; Pauselli et al, 2018; Sarzynska-Wawer et al, 2021; Tang et al, 2021). Our study emphasized the lack of a clear picture.…”

Section: Discussionmentioning

confidence: 99%

“…However, a critical obstacle to any concrete use of these findings is that it is not clear whether the findings would replicate and generalize to new samples and populations, an overarching problem for clinical and social sciences (Hitczenko et al, 2021; Parola et al, 2020; Rocca & Yarkoni, 2021; Rybner et al, 2021). Indeed, a closer look reveals clearly contradictory results: linguistic measures are inconsistently associated with symptoms, and findings vary across different rating scales and samples (Bedi et al, 2015; Corcoran et al, 2018; Haas et al, 2020; Morgan et al, 2021; Pauselli et al, 2018; Sarzynska-Wawer et al, 2021; Tang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speech disturbances in schizophrenia: assessing cross-linguistic generalizability of NLP automated measures of coherence

Parola

Lin

Simonsen

et al. 2022

Preprint

View full text Add to dashboard Cite

Introduction: Language disorders - disorganized and incoherent speech in particular - are distinctive features of schizophrenia. Natural language processing (NLP) offers automated measures of incoherent speech as promising markers for schizophrenia. However, the scientific and clinical impact of NLP markers depends on their generalizability across contexts, samples, and languages, which we systematically assessed in the present study relying on a large, novel, cross-linguistic corpus. Methods: We collected a Danish (DK), German (GE), and Chinese (CH) cross-linguistic dataset involving transcripts from 187 participants with schizophrenia (111DK, 25GE, 51CH) and 200 matched controls (129DK, 29GE, 42CH) performing the Animated Triangle task. Fourteen previously published NLP coherence measures were calculated, and between-groups differences and association with symptoms were tested for cross-linguistic generalizability. Results: One coherence measure robustly generalized across samples and languages. We found several language-specific effects, some of which partially replicated previous findings (lower coherence in German and Chinese patients), while others did not (higher coherence in Danish patients). We found several associations between symptoms and measures of coherence, but the effects were generally inconsistent across languages and rating scales. Conclusions: Using a cumulative approach, we have shown that NLP findings of reduced semantic coherence in schizophrenia have limited generalizability across different languages, samples, and measures. We argue that several factors such as sociodemographic and clinical heterogeneity, cross-linguistic variation, and the different NLP measures reflecting different clinical aspects may be responsible for this variability. Future studies should take this variability into account in order to develop effective clinical applications targeting different patient populations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Speech disturbances in schizophrenia: assessing cross-linguistic generalizability of NLP automated measures of coherence

Parola

Lin

Simonsen

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, most studies have used speech features to directly predict diagnosis or outcomes, without relating features to observable speech disturbances. [5][6][7][8][9][10][11][12][13][14] There are weaknesses to this approach.…”

Section: Introductionmentioning

confidence: 99%

Latent Factors of Language Disturbance and Relationships to Quantitative Speech Features

Tang

Hänsel

Yan

et al. 2022

Preprint

View full text Add to dashboard Cite

Background and Hypothesis Quantitative acoustic and textual measures derived from speech ("speech features") may provide valuable biomarkers for psychiatric disorders, particularly schizophrenia spectrum disorders (SSD). We sought to identify cross-diagnostic latent factors for speech disturbance with relevance for SSD and computational modeling. Study Design Clinical ratings for speech disturbance were generated across 14 items for a cross-diagnostic sample (N=343), including SSD (n=97). Speech features were quantified using an automated pipeline for brief recorded samples of free-speech. Factor models for the clinical ratings were generated using exploratory factor analysis, then tested with confirmatory factor analysis in the cross-diagnostic and SSD groups. Relationships among factor scores, speech features and other clinical characteristics were examined using network analysis. Study Results We found a 3-factor model with good fit in the cross-diagnostic group and acceptable fit for the SSD subsample. The model identifies an impaired expressivity factor and two interrelated disorganized factors for inefficient and incoherent speech. Incoherent speech was specific to psychosis groups, while inefficient speech and impaired expressivity showed intermediate effects in people with nonpsychotic disorders. Network analysis showed that the factors had distinct relationships with speech features, and that the patterns were different in the cross-diagnostic versus SSD groups. Conclusions We report a cross-diagnostic 3-factor model for speech disturbance which is supported by good statistical measures, intuitive, applicable to SSD, and relatable to linguistic theories. It provides a valuable framework for understanding speech disturbance and appropriate targets for modeling with quantitative speech features.

show abstract

“…Recently, PrLMs have dominated the design of encoders for MRC with great success. These PrLMs include ELMo [22], GPT [23], BERT [24], XLNet [25], Roberta [26], ALBERT [27], and ELECTRA [28]. They bring impressive performance improvements for a wide range of NLP tasks for two main reasons: (1) language models are pre-trained on a large-scale text corpus, which allows the models to learn generic language features and serve as a knowledge base; (2) thanks to the Transformer architecture, language models enjoy a powerful feature representation learning capability to capture higher-order, long-range dependencies in text.…”

Section: Introductionmentioning

confidence: 99%

Improving Machine Reading Comprehension with Multi-Task Learning and Self-Training

Ouyang

2022

Mathematics

View full text Add to dashboard Cite

Machine Reading Comprehension (MRC) is an AI challenge that requires machines to determine the correct answer to a question based on a given passage, in which extractive MRC requires extracting an answer span to a question from a given passage, such as the task of span extraction. In contrast, non-extractive MRC infers answers from the content of reference passages, including Yes/No question answering to unanswerable questions. Due to the specificity of the two types of MRC tasks, researchers usually work on one type of task separately, but real-life application situations often require models that can handle many different types of tasks in parallel. Therefore, to meet the comprehensive requirements in such application situations, we construct a multi-task fusion training reading comprehension model based on the BERT pre-training model. The model uses the BERT pre-training model to obtain contextual representations, which is then shared by three downstream sub-modules for span extraction, Yes/No question answering, and unanswerable questions, next we fuse the outputs of the three sub-modules into a new span extraction output and use the fused cross-entropy loss function for global training. In the training phase, since our model requires a large amount of labeled training data, which is often expensive to obtain or unavailable in many tasks, we additionally use self-training to generate pseudo-labeled training data to train our model to improve its accuracy and generalization performance. We evaluated the SQuAD2.0 and CAIL2019 datasets. The experiments show that our model can efficiently handle different tasks. We achieved 83.2EM and 86.7F1 scores on the SQuAD2.0 dataset and 73.0EM and 85.3F1 scores on the CAIL2019 dataset.

show abstract

Detecting formal thought disorder by deep contextualized word representations

Cited by 201 publications

References 27 publications

Speech disturbances in schizophrenia: assessing cross-linguistic generalizability of NLP automated measures of coherence

Speech disturbances in schizophrenia: assessing cross-linguistic generalizability of NLP automated measures of coherence

Latent Factors of Language Disturbance and Relationships to Quantitative Speech Features

Improving Machine Reading Comprehension with Multi-Task Learning and Self-Training

Contact Info

Product

Resources

About