Unified Multi Intent Order and Slot Prediction using Selective Learning Propagation
Natural Language Understanding (NLU) involves two important task namely Intent Determination(ID) and Slot Filling (SF). With recent advancements in Intent Determination and Slot Filling tasks, explorations on handling of multiple intent information in a single utterance is increasing to make the NLU more conversation-based rather than command execution-based. Many have proven this task with huge multi-intent training data. In addition, lots of research have addressed multi intent problem only. The problem of multi intent also poses the challenge of addressing the order of execution of intents found. Hence, we are proposing a unified architecture to address multi-intent detection, associated slotsdetection and order of execution of found intents using low proportion multi-intent corpusin the training data. This architecture consists of Multi Word Importance relation propagator using Multi-Head GRU and Importance learner propagator module using self-attention. This architecture has beaten state-of-the-art by 2.58% on the MultiIntentData dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Intent DetectionNatural Language Understandingslot-fillingSlot FillingSimilar Papers 제목 키워드 기반
Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction
So far, multi-intent spoken language understanding (SLU) has become a research hotspot in the field of natural language processing (NLP) due to its ability to recognize and extract multiple intents expressed and annotate…
Intent Detectionslot-fillingSlot FillingSpoken Language UnderstandingOneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding
In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted d…
Spoken Language UnderstandingSlot-Gated Modeling for Joint Slot Filling and Intent Prediction
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. Considering that slot and intent …
global-optimizationIntent DetectionSentenceslot-filling+3Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling
The joint multiple Intent Detection (ID) and Slot Filling (SF) is a significant challenge in spoken language understanding. Because the slots in an utterance may relate to multi-intents, most existing approaches focus on…
Intent DetectionSemantic Frame Parsingslot-fillingSlot Filling+1Parallel Intent and Slot Prediction using MLB Fusion
Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of…
PredictionSpoken Language Understanding