English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Understanding passenger intents and extracting relevant slots are importantbuilding blocks towards developing contextual dialogue systems for naturalinteractions in autonomous vehicles (AV). In this work, we explored AMIE(Automated-vehicle Multi-modal In-cabin Experience), the in-cabin agentresponsible for handling certain passenger-vehicle interactions. When thepassengers give instructions to AMIE, the agent should parse such commandsproperly and trigger the appropriate functionality of the AV system. In ourcurrent explorations, we focused on AMIE scenarios describing usages aroundsetting or changing the destination and route, updating driving behavior orspeed, finishing the trip and other use-cases to support various naturalcommands. We collected a multi-modal in-cabin dataset with multi-turn dialoguesbetween the passengers and AMIE using a Wizard-of-Oz scheme via a realisticscavenger hunt game activity. After exploring various recent Recurrent NeuralNetworks (RNN) based techniques, we introduced our own hierarchical jointmodels to recognize passenger intents along with relevant slots associated withthe action to be performed in AV scenarios. Our experimental resultsoutperformed certain competitive baselines and achieved overall F1 scores of0.91 for utterance-level intent detection and 0.96 for slot filling tasks. Inaddition, we conducted initial speech-to-text explorations by comparingintent/slot models trained and tested on human transcriptions versus noisyAutomatic Speech Recognition (ASR) outputs. Finally, we compared the resultswith single passenger rides versus the rides with multiple passengers.

Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances