Scoring Spoken Responses Based on Content Accuracy
نویسندگان
چکیده
Accuracy of content have not been fully utilized in the previous studies on automated speaking assessment. Compared to writing tests, responses in speaking tests are noisy (due to recognition errors), full of incomplete sentences, and short. To handle these challenges for doing content-scoring in speaking tests, we propose two new methods based on information extraction (IE) and machine learning. Compared to using an ordinary content-scoring method based on vector analysis, which is widely used for scoring written essays, our proposed methods provided content features with higher correlations to human holistic scores.
منابع مشابه
Automated Content Scoring of Spoken Responses in an Assessment for Teachers of English
This paper presents and evaluates approaches to automatically score the content correctness of spoken responses in a new language test for teachers of English as a foreign language who are non-native speakers of English. Most existing tests of English spoken proficiency elicit responses that are either very constrained (e.g., reading a passage aloud) or are of a predominantly spontaneous nature...
متن کاملAutomated content scoring of spoken responses containing multiple parts with factual information
This paper presents approaches to automated content scoring of spoken language test responses from non-native speakers of English which contain multiple parts addressing factual information that the test taker has previously heard via auditory stimulus materials. While previous work relating to content scoring of spontaneous, unpredictable speech has focused only on entire responses and on gene...
متن کاملPrompt-based Content Scoring for Automated Spoken Language Assessment
This paper investigates the use of promptbased content features for the automated assessment of spontaneous speech in a spoken language proficiency assessment. The results show that single highest performing promptbased content feature measures the number of unique lexical types that overlap with the listening materials and are not contained in either the reading materials or a sample response,...
متن کاملDNN Online with iVectors Acoustic Modeling and Doc2Vec Distributed Representations for Improving Automated Speech Scoring
When applying automated speech-scoring technology to the rating of globally administered real assessments, there are several practical challenges: (a) ASR accuracy on non-native spontaneous speech is generally low; (b) due to the data mismatch between an ASR systems training stage and its final usage, the recognition accuracy obtained in practice is even lower; (c) content-relevance was not wid...
متن کاملModeling Discourse Coherence for the Automated Scoring of Spontaneous Spoken Responses
This study describes an approach for modeling the discourse coherence of spontaneous spoken responses in the context of automated assessment of non-native speech. Although the measurement of discourse coherence is typically a key metric in human scoring rubrics for assessments of spontaneous spoken language, little prior research has been done to assess a speaker’s coherence in the context of a...
متن کامل