Papers by Divya Tadimeti
Discourse-Driven Code-Switching: Analyzing the Role of Content and Communicative Function in Spanish-English Bilingual Speech (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has shown that a range of speaker and listener attributes affect or correlate with the prevalence of code-switching during conversation. |
| Approach: | They analyze the names of entities and dialogue acts present in a Spanish-English spontaneous speech corpus and build a predictive model of CSW. |
| Outcome: | The proposed model is the first to take a discourse-sensitive approach to understanding pragmatic and referential cues of bilingual speech. |
Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing automatic speech recognition systems for non-American accents have a much higher error rate than for general american accents. |
| Approach: | They evaluate automatic speech recognition systems on agent-directed speech . they find that the performance is worse for non-American accents than for General American . |
| Outcome: | The ASR systems perform worse for non-American accents than for General American accents . the results suggest that training on non-native English speakers is needed to narrow the performance gap. |
Discovering Differences in the Representation of People using Contextualized Semantic Axes (2022.emnlp-main)
Copied to clipboard
| Challenge: | Past work has compared embeddings against “semantic axes” that represent two opposing concepts. |
| Approach: | They extend this paradigm to BERT embeddings and construct contextualized axes that mitigate pitfall where antonyms have neighboring representations. |
| Outcome: | The proposed axes can characterize differences among instances of the same word type on two people-centric datasets. |