Papers by Duanchen Liu
Predicting pragmatic discourse features in the language of adults with autism spectrum disorder (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing tools to quantify atypicality in discourse and pragmatics are difficult to precisely identify and quantify. |
| Approach: | They present a corpus of transcribed natural conversations produced in an experimental setting and annotate them for three pragmatic features on a three-point scale. |
| Outcome: | The proposed model yields higher accuracy than previous approaches for deriving these features, with F1 exceeding 0.82 for all three pragmatic features. |
Evaluating the Performance of Transformer-based Language Models for Neuroatypical Language (2022.coling-1)
Copied to clipboard
| Challenge: | Difficulties with social aspects of language are among the hallmarks of autism spectrum disorder (ASD). |
| Approach: | They propose a transformer-based framework for identifying linguistic features associated with social aspects of communication using a corpus of conversations between adults with and without ASD and neurotypical conversational partners. |
| Outcome: | The proposed framework yields strong accuracy overall, but performance is significantly worse for the language of participants with ASD, suggesting they use a more diverse set of strategies for some social linguistic functions. |