Efficient Intent Detection with Dual Sentence Encoders.¶
Casanueva, I., Temčinas, T., Gerz, D., Henderson, M., & Vulić, I. (2020). Efficient Intent Detection with Dual Sentence Encoders. Proceedings of the 2nd Workshop on NLP for Conversational AI, 38-45.
Cited by¶
1 citation across 1 artifact.
Primes¶
- Native-Category Flattening
- Consider building a labeled dataset of customer-support messages where the source — the customers — partition their problems into fine native categories ("the app logs me out mid-purchase," "it logs me out overnight") that a coarse label set would conflate; the pair is this entry's own illustration, though real support-intent data does carry just this kind of partially overlapping, fine-grained distinction — reverted top-up versus failed top-up.
Supported in partVerified against the work's full text
The paper supplies a real single-domain intent dataset (13,083 examples, 77 intents); it supports fine-grained intent categories, not the named top-up overlap.
“In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.”
- Consider building a labeled dataset of customer-support messages where the source — the customers — partition their problems into fine native categories ("the app logs me out mid-purchase," "it logs me out overnight") that a coarse label set would conflate; the pair is this entry's own illustration, though real support-intent data does carry just this kind of partially overlapping, fine-grained distinction — reverted top-up versus failed top-up.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:5251143235c8 · see in the full table