# Converting the Point of View of Messages Spoken to Virtual Assistants

Source: [Converting the Point of View of Messages Spoken to Virtual Assistants](<https://www.sota2.com/research/paper/68fa68821e209131cea1c8f5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:21:41.894Z

Authors: Isabelle G. Lee, Vera Zu, Sai Srujana Buddi, Dennis Liang, Purva Kulkarni, Jack G.M. Fitzgerald

Published: 2020-10-06T10:19:39.000Z

## Abstract

Virtual Assistants can be quite literal at times. If the user says "tell Bob I love him," most virtual assistants will extract the message "I love him" and send it to the user's contact named Bob, rather than properly converting the message to "I love you." We designed a system to allow virtual assistants to take a voice message from one user, convert the point of view of the message, and then deliver the result to its target user. We developed a rule-based model, which integrates a linear text classification model, part-of-speech tagging, and constituency parsing with rule-based transformation methods. We also investigated Neural Machine Translation (NMT) approaches, including LSTMs, CopyNet, and T5. We explored 5 metrics to gauge both naturalness and faithfulness automatically, and we chose to use BLEU plus METEOR for faithfulness and relative perplexity using a separately trained language model (GPT) for naturalness. Transformer-Copynet and T5 performed similarly on faithfulness metrics, with T5 achieving slight edge, a BLEU score of 63.8 and a METEOR score of 83.0. CopyNet was the most natural, with a relative perplexity of 1.59. CopyNet also has 37 times fewer parameters than T5. We have publicly released our dataset, which is composed of 46,565 crowd-sourced samples.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [POV Conversion on POV conversion (test)](<https://www.sota2.com/research/sota/pov-conversion-on-pov-conversion-test.md>): POV conversion; POV conversion (test); BLEU Score: 0.638.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2010.02600>)

[PDF](<https://arxiv.org/pdf/2010.02600.pdf>)

[Implementation](<https://github.com/alexa/alexa-point-of-view-dataset>)