The goal of Slot Filling is to identify from a running dialog different slots, which correspond to different parameters of the user’s query. For instance, when a user queries for nearby restaurants, key slots for location and preferred food are required for a dialog system to retrieve the appropriate information. Thus, the main challenge in the slot-filling task is to extract the target entity.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Additionally, in initial user studies we observed that data programming may be an easier way for non-experts to create machine learning models when training data is limited or unavailable.
We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance.
Ranked #3 on Fact Verification on KILT: FEVER
The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance.
Ranked #4 on Relation Extraction on Re-TACRED
Attention-based recurrent neural network models for joint intent detection and slot filling have achieved the state-of-the-art performance, while they have independent attention weights.
Ranked #6 on Intent Detection on SNIPS
We introduce Baseline: a library for reproducible deep learning research and fast model development for NLP.
Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition.
Ranked #3 on Intent Detection on ATIS