A new kid on the block: Distributional semantics predicts the word-specific tone signatures of monosyllabic words in conversational Taiwan Mandarin

TL;DR

This study investigates how the meanings of monosyllabic words influence their pitch contours in conversational Taiwan Mandarin, revealing that semantic factors significantly predict tonal realization beyond phonetic controls.

Contribution

It demonstrates that semantic information, captured through distributional embeddings, predicts tonal variations in Mandarin, challenging traditional tone theories.

Findings

Word semantics significantly predict pitch contours.

Distributional embeddings outperform baseline in predicting tone.

Semantic effects persist even when controlling for phonetic variables.

Abstract

We present a corpus-based investigation of how the pitch contours of monosyllabic words are realized in spontaneous conversational Mandarin, focusing on the effects of words' meanings. We used the generalized additive model to decompose a given observed pitch contour into a set of component pitch contours that are tied to different control variables and semantic predictors. Even when variables such as word duration, gender, speaker identity, tonal context, vowel height, and utterance position are controlled for, the effect of word remains a strong predictor of tonal realization. We present evidence that this effect of word is a semantic effect: word sense is shown to be a better predictor than word, and heterographic homophones are shown to have different pitch contours. The strongest evidence for the importance of semantics is that the pitch contours of individual word tokens can be predicted from their contextualized embeddings with an accuracy that substantially exceeds a permutation baseline. For phonetics, distributional semantics is a new kid on the block. Although our findings challenge standard theories of Mandarin tone, they fit well within the theoretical framework of the Discriminative Lexicon Model.