Papers by Markus Boese
LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging (2022.coling-1)
Copied to clipboard
| Challenge: | LINGUIST generates annotated data for Intent Classification and Slot Tagging (IC+ST) we demonstrate fine-tuning of a large-scale seq2seq model to control outputs of multilingual data generation. |
| Approach: | They propose a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST) they use a 5-billion-parameter multilingual sequence-to-sequence model to fine-tune it on a flexible instruction prompt. |
| Outcome: | The proposed method outperforms state-of-the-art approaches on a SNIPS intent setting and shows significant improvement on IC+ST in a cross-lingual setting. |
Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances (2020.coling-industry)
Copied to clipboard
| Challenge: | In large-scale commercial dialog systems, users express the same request in a wide variety of alternative ways with a long tail of less frequent alternatives. |
| Approach: | They propose a method to leverage this feedback by creating annotated training examples from it. |
| Outcome: | The proposed method can be used in a commercial dialog system across various domains and three languages. |