SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling

• URL: http://arxiv.org/abs/2108.11711v1
• Date: Thu, 26 Aug 2021 11:33:39 GMT
• Title: SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
• Authors: Fengyu Cai, Wanhao Zhou, Fei Mi and Boi Faltings
• Abstract summary: Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems. We propose a multi-intent NLU framework, called SLIM, to jointly learn multi-intent detection and slot filling based on BERT.
• Score: 26.037061005620263
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems. Most existing approaches assume that only a single intent exists in an utterance. However, there are often multiple intents within an utterance in real-life scenarios. In this paper, we propose a multi-intent NLU framework, called SLIM, to jointly learn multi-intent detection and slot filling based on BERT. To fully exploit the existing annotation data and capture the interactions between slots and intents, SLIM introduces an explicit slot-intent classifier to learn the many-to-one mapping between slots and intents. Empirical results on three public multi-intent datasets demonstrate (1) the superior performance of SLIM compared to the current state-of-the-art for NLU with multiple intents and (2) the benefits obtained from the slot-intent classifier.

Related papers

• A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents [12.62162175115002]
  This study addresses three critical tasks: extracting multiple intent spans from queries, detecting multiple intents, and developing a multi-lingual intent dataset. We introduce a novel multi-label multi-class intent detection dataset (MLMCID-dataset) curated from existing benchmark datasets. We also propose a pointer network-based architecture (MLMCID) to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets.
  arXiv  Detail & Related papers  (2024-10-29T19:10:12Z)
• Towards Spoken Language Understanding via Multi-level Multi-grained Contrastive Learning [50.1035273069458]
  Spoken language understanding (SLU) is a core task in task-oriented dialogue systems. We propose a multi-level MMCL framework to apply contrastive learning at three levels, including utterance level, slot level, and word level. Our framework achieves new state-of-the-art results on two public multi-intent SLU datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:34:23Z)
• Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning [62.839109775887025]
  Slot Induction (SI) task whose objective is to induce slot boundaries without explicit knowledge of token-level slot annotations. We propose leveraging Unsupervised Pre-trained Language Model (PLM) Probing and Contrastive Learning mechanism to exploit unsupervised semantic knowledge extracted from PLM. Our approach is shown to be effective in SI task and capable of bridging the gaps with token-level supervised models on two NLU benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-09T05:08:57Z)
• D$^2$TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization [113.72253589338472]
  Many-to-many multimodal summarization (M$3$S) task aims to generate summaries in any language with document inputs in any language and the corresponding image sequence. We propose a dual knowledge distillation and target-oriented vision modeling framework for the M$3$S task.
  arXiv  Detail & Related papers  (2023-05-22T06:47:35Z)
• A Unified Framework for Multi-intent Spoken Language Understanding with prompting [14.17726194025463]
  We describe a Prompt-based Spoken Language Understanding (PromptSLU) framework, to intuitively unify two sub-tasks into the same form. In detail, ID and SF are completed by concisely filling the utterance into task-specific prompt templates as input, and sharing output formats of key-value pairs sequence. Experiment results show that our framework outperforms several state-of-the-art baselines on two public datasets.
  arXiv  Detail & Related papers  (2022-10-07T05:58:05Z)
• Joint Multiple Intent Detection and Slot Filling via Self-distillation [29.17761742391222]
  Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users' needs from their utterances. Most previous works assume that each utterance only corresponds to one intent, ignoring the fact that a user utterance in many cases could include multiple intents. We propose a novel Self-Distillation Joint NLU model (SDJN) for multi-intent NLU.
  arXiv  Detail & Related papers  (2021-08-18T08:45:03Z)
• GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling [31.833158491112005]
  Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. In this paper, we explore a non-autoregressive model for joint multiple intent detection and slot filling. Our framework achieves state-of-the-art performance while being 11.5 times faster.
  arXiv  Detail & Related papers  (2021-06-03T15:22:38Z)
• Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems [46.705058576039065]
  We present an acoustic based SLU system that converts speech to its phonetic transcription using a universal phone recognition system. We build a word-free natural language understanding module that does intent recognition and slot identification from these phonetic transcription. We observe more than 10% improvement for intent classification in Tamil and more than 5% improvement for intent classification in Sinhala.
  arXiv  Detail & Related papers  (2021-04-03T01:58:27Z)
• AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling [69.59096090788125]
  In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling. We introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information.
  arXiv  Detail & Related papers  (2020-04-21T15:07:34Z)
• Efficient Intent Detection with Dual Sentence Encoders [53.16532285820849]
  We introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that they outperform intent detectors based on fine-tuning the full BERT-Large model. We release our code, as well as a new challenging single-domain intent detection dataset.
  arXiv  Detail & Related papers  (2020-03-10T15:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.