Sentence Segmentation in Narrative Transcripts from
            Neuropsychological Tests using Recurrent Convolutional Neural
            Networks

Treviso, Marcos; Shulby, Christopher; Aluísio, Sandra Maria

doi:10.18653/v1/e17-1030

Cited by 14 publications

(16 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CRNN has been widely applied to classification tasks. In Natural Language Processing (NLP) research including sentence segmentation [16], sentiment analysis [17] and discourse modeling [6], CRNN achieves the state-of-the-art in single-label classification where for each input, a single output would be predicted.…”

Section: Related Workmentioning

confidence: 99%

Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

Peng

Yang

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

In dialogues, an utterance is a chain of consecutive sentences produced by one speaker which ranges from a short sentence to a thousand-word post. When studying dialogues at the utterance level, it is not uncommon that an utterance would serve multiple functions. For instance, "Thank you. It works great. " expresses both gratitude and positive feedback in the same utterance. Multiple dialogue acts (DA) for one utterance breeds complex dependencies across dialogue turns. Therefore, DA recognition challenges a model's predictive power over long utterances and complex DA context. We term this problem Concurrent Dialogue Acts (CDA) recognition. Previous work on DA recognition either assumes one DA per utterance or fails to realize the sequential nature of dialogues. In this paper, we present an adapted Convolutional Recurrent Neural Network (CRNN) which models the interactions between utterances of long-range context. Our model significantly outperforms existing work on CDA recognition on a tech forum dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

Peng

Yang

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…In order to carry out experiments with a balanced corpus, as with the previous two datasets, we excluded seven transcriptions from the MCI group. We used the automatic sentence segmentation method referred to as DeepBond (Treviso et al, 2017) in the transcripts. Table 3 shows the demographic information.…”

Section: The Abcd Datasetmentioning

confidence: 99%

Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts

Santos¹,

Júnior²,

Oliveira³

et al. 2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

Self Cite

View full text Add to dashboard Cite

Mild Cognitive Impairment (MCI) is a mental disorder difficult to diagnose. Linguistic features, mainly from parsers, have been used to detect MCI, but this is not suitable for large-scale assessments. MCI disfluencies produce nongrammatical speech that requires manual or high precision automatic correction of transcripts. In this paper, we modeled transcripts into complex networks and enriched them with word embedding (CNE) to better represent short texts produced in neuropsychological assessments. The network measurements were applied with well-known classifiers to automatically identify MCI in transcripts, in a binary classification task. A comparison was made with the performance of traditional approaches using Bag of Words (BoW) and linguistic features for three datasets: DementiaBank in English, and Cinderella and Arizona-Battery in Portuguese. Overall, CNE provided higher accuracy than using only complex networks, while Support Vector Machine was superior to other classifiers. CNE provided the highest accuracies for DementiaBank and Cinderella, but BoW was more efficient for the Arizona-Battery dataset probably owing to its short narratives. The approach using linguistic features yielded higher accuracy if the transcriptions of the Cinderella dataset were manually revised. Taken together, the results indicate that complex networks enriched with embedding is promising for detecting MCI in large-scale assessments.

show abstract

“…In this presentation, results from two discursive subtasks of BALE will be presented, one consisting of the retelling of an orally presented narrative, and the other a narrative production based on a sequence of scenes. Data analyses are performed by DeepBond, a method of automatic sentence segmentation (Treviso et al, 2017), together with the use of Coh-Metrix Dementia (CMD) (Aluísio et al, 2016;Cunha et al, 2015), which provides 73 metrics, including syntactic complexity. Moreover, data from questions measuring micro and macrostructure comprehension and text propositions are analyzed.…”

Section: Introductionmentioning

confidence: 99%