Analyzing human and machine performance in resolving ambiguous spoken sentences

1Citations
Citations of this article
56Readers
Mendeley users who have this article in their library.

Abstract

Written sentences can be more ambiguous than spoken sentences. We investigate this difference for two different types of ambiguity: Prepositional phrase (PP) attachment and sentences where the addition of commas changes the meaning. We recorded a native English speaker saying several of each type of sentence both with and without disambiguating contextual information. These sentences were then presented either as text or audio and either with or without context to subjects who were asked to select the proper interpretation of the sentence. Results suggest that commaambiguous sentences are easier to disambiguate than PP-attachmentambiguous sentences, possibly due to the presence of clear prosodic boundaries, namely silent pauses. Subject performance for sentences with PP-attachment ambiguity without context was 52% for text only while it was 72.4% for audio only, suggesting that audio has more disambiguating information than text. Using an analysis of acoustic features of two PP-attachment sentences, a simple classifier was implemented to resolve the PP-attachment ambiguity being early or late closure with a mean accuracy of 80%.

Cite

CITATION STYLE

APA

Ghaly, H., & Mandel, M. I. (2017). Analyzing human and machine performance in resolving ambiguous spoken sentences. In EMNLP 2017 - 1st Workshop on Speech-Centric Natural Language Processing, SCNLP 2017 - Proceedings of the Workshop (pp. 18–26). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w17-4603

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free