Open Intent Extraction from Natural Language Interactions

@article{Vedula2020OpenIE,
  title={Open Intent Extraction from Natural Language Interactions},
  author={Nikhita Vedula and Nedim Lipka and Pranav Maneriker and Srinivasan Parthasarathy},
  journal={Proceedings of The Web Conference 2020},
  year={2020}
}
Accurately discovering user intents from their written or spoken language plays a critical role in natural language understanding and automated dialog response. Most existing research models this as a classification task with a single intent label per utterance, grouping user utterances into a single intent type from a set of categories known beforehand. Going beyond this formulation, we define and investigate a new problem of open intent discovery. It involves discovering one or more generic… 

Figures and Tables from this paper

Open Intent Extraction from Natural Language Interactions (Extended Abstract)
TLDR
A novel, domain-agnostic approach to open intent discovery is proposed, OPINE, which formulates the problem as a sequence tagging task in an open-world setting and employs a CRF on top of a bidirectional LSTM to extract intents in a consistent format, subject to constraints among intent tag labels.
Automatic Discovery of Novel Intents & Domains from Text Utterances
TLDR
A novel framework, ADVIN, is proposed to automatically discover novel domains and intents from large volumes of unlabeled data and significantly outperforms baselines on three benchmark datasets, and real user utterances from a commercial voice-powered agent.
Generalized Zero-shot Intent Detection via Commonsense Knowledge
TLDR
This work proposes RIDE: an intent detection model that leverages commonsense knowledge in an unsupervised fashion to overcome the issue of training data scarcity and shows that RIDE outperforms the state-of-the-art models.
Automatic Intent-Slot Induction for Dialogue Systems
TLDR
A new task of automatic intent-slot induction is explored and a novel domain-independent tool, the RCAP, is proposed, which opens pathways for schema induction on new domains and unseen intent- slot discovery for generalizable dialogue systems.
Graphire: Novel Intent Discovery with Pretraining on Prior Knowledge using Contrastive Learning
TLDR
Graphire, an intent discovery system leveraging pretraining on predefined intents to automatically discover novel intents for intelligent personal assistants (IPA), and a pretraining paradigm based on contrastive learning to distill prior knowledge from existing intents is proposed.
MovieChats: Chat like Humans in a Closed Domain
TLDR
This work takes a close look at the movie domain and presents a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
A Comparative Study on Schema-Guided Dialogue State Tracking
TLDR
In-depth comparative studies are conducted to understand the use of natural language description for schema in dialog state tracking and reveal the model robustness on both homogeneous and heterogeneous description styles in training and evaluation.
Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots
TLDR
This paper proposes a robust adversarial model-agnostic slot filling method that explicitly decouples local semantics inherent in open-vocabulary slot words from the global context and consistently outperforms other methods with a statistically significant margin.
Modeling knowledge and functional intent for context-aware pragmatic analysis
TLDR
Her research interests are at the intersection of data mining, natural language processing and social computing, and her work on detecting user intentions from their natural language interactions won the Best paper award at the Web Conference 2020.
...
1
2
...

References

SHOWING 1-10 OF 75 REFERENCES
Zero-shot User Intent Detection via Capsule Neural Networks
TLDR
Two capsule-based architectures are proposed: IntentC CapsNet that extracts semantic features from utterances and aggregates them to discriminate existing intents, and IntentCapsNet-ZSL which gives IntentCpsNet the zero-shot learning ability to discriminate emerging intents via knowledge transfer from existing intent.
ONENET: Joint domain, intent, slot prediction for spoken language understanding
TLDR
This work presents a unified neural network that jointly performs domain, intent, and slot predictions in spoken language understanding systems and adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task.
Easy contextual intent prediction and slot detection
TLDR
This paper investigates the incorporation of context into the SLU tasks of intent prediction and slot detection, using a corpus that contains session-level information and finds that including features indicating the slots appearing in the previous utterances gives no significant increase in performance.
A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
TLDR
New Bi-model based RNN semantic frame parsing network structures are designed to perform the intent detection and slot filling tasks jointly, by considering their cross-impact to each other using two correlated bidirectional LSTMs (BLSTM).
A Joint Model of Intent Determination and Slot Filling for Spoken Language Understanding
TLDR
A joint model is proposed based on the idea that the intent and semantic slots of a sentence are correlative, and it outperforms the state-of-the-art approaches on both tasks.
An CNN-LSTM Attention Approach to Understanding User Query Intent from Online Health Communities
TLDR
A CNN-LSTM attention model is proposed to predict user intents, and an unsupervised clustering method is applied to mine user intent taxonomy and experiment results demonstrate the effectiveness of the model.
Leveraging Linguistic Structure For Open Domain Information Extraction
TLDR
This work replaces this large pattern set with a few patterns for canonically structured sentences, and shifts the focus to a classifier which learns to extract self-contained clauses from longer sentences to determine the maximally specific arguments for each candidate triple.
Joint Slot Filling and Intent Detection via Capsule Neural Networks
TLDR
A capsule-based neural network model is proposed which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema and a re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation.
A Deep Learning Based Multi-task Ensemble Model for Intent Detection and Slot Filling in Spoken Language Understanding
TLDR
A deep learning based multi-task ensemble model that can perform both intent detection and slot filling tasks together and achieves better results than the individual models and the existing state-of-the-art systems is proposed.
Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM
TLDR
Experimental results show the power of a holistic multi-domain, multi-task modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system over alternative methods based on single domain/task deep learning.
...
1
2
3
4
5
...