Pith. sign in

REVIEW 3 cited by

DIET: Lightweight Language Understanding for Dialogue Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.09936 v3 pith:3NM3N4DF submitted 2020-04-21 cs.CL

DIET: Lightweight Language Understanding for Dialogue Systems

classification cs.CL
keywords dietlanguagepre-trainedunderstandingdialogueentityintentlike
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations (GloVe) and purely supervised approaches. We introduce the Dual Intent and Entity Transformer (DIET) architecture, and study the effectiveness of different pre-trained representations on intent and entity prediction, two common dialogue language understanding tasks. DIET advances the state of the art on a complex multi-domain NLU dataset and achieves similarly high performance on other simpler datasets. Surprisingly, we show that there is no clear benefit to using large pre-trained models for this task, and in fact DIET improves upon the current state of the art even in a purely supervised setup without any pre-trained embeddings. Our best performing model outperforms fine-tuning BERT and is about six times faster to train.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Building Korean linguistic resource for NLU data generation of banking app CS dialog system

    cs.CL 2026-05 unverdicted novelty 5.0

    FIAD is a new resource that encodes three Korean utterance patterns from banking reviews into Local Grammar Graphs to generate diverse annotated NLU training data, producing strong intent and topic extraction results ...

  2. Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

    cs.CL 2026-08 conditional novelty 4.0

    Statistical classifiers built on LLM activation norms and coordinates match or beat trained MLP heads on coarse intent routing and resist camouflage better, while MLPs win on fine-grained subfield distinctions.

  3. Generating training datasets for legal chatbots in Korean

    cs.CL 2026-05 unverdicted novelty 4.0

    Local grammar graphs generate 700 million labelled utterances that train a DIET classifier to 91% F1 for a Korean legal chatbot answering queries with links to public case documents.