Deep Bi-Directional LSTM Network for Query Intent Detection

Sreelakshmi, K.; Rafeeque, P C; Sreetha, S; Gayathri, E.

doi:10.1016/j.procs.2018.10.341

Cited by 25 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…− Tracking of the volume of demand: With such a solution in place it could be understood what keyword category causes issues and subsequent abilities to zoom in to more specific areas. In general, analysts would have granular control over the volume and demands of the searches on the domains of the organization [16]. − Keyword level information: With query categorization in place, keyword-level information could be managed efficiently [17].…”

Section: Need For Query Categorisationmentioning

confidence: 99%

Text grouping: a comprehensive guide

Palai

Agrawal

Mishra

et al. 2023

IJ-AI

View full text Add to dashboard Cite

Text keywords have huge variance and to bridge the gap between the country business segment which provides negligible information and the keywords that have a huge longtail it is imperative for us to categorize the queries that provide a middle ground and also serve a few other purposes. The paper will present those in-depth. Query categorization falls into the segment of 'Multi-Class Classification' in the domain of natural language processing (NLP). However, business requirements require the implementation of any technique that could provide as accurate results as possible. So, to solve this problem the paper discusses an amalgamation of approaches like TF-IDF (term frequency-inverse document frequency), neural networks, cosine similarity, transformers-all of which fix specific issues.

show abstract

Section: Need For Query Categorisationmentioning

confidence: 99%

Text grouping: a comprehensive guide

Palai

Agrawal

Mishra

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Intent detection methods based on DL techniques can be classified into methods using convolution neural networks [10], recurrent neural networks [11] and their variants (LSTMs and GRUs) [4,7], the Bidirectional Long short-term Memory (BLSTM) self-attention model [12], the capsule network model [13], the method of joint recognition [14], the use of distances to measure the text similarities (such as TF-IDF) [15], or methods combining several DL models [16,17]. Nonetheless, the appearance of BERT (Bidirectional Encoder Representations from Transformers) models greatly contributed to enhance natural language processing [18].…”

Section: Literature Reviewmentioning

confidence: 99%

Fine-Tuning BERT Models for Intent Recognition Using a Frequency Cut-Off Strategy for Domain-Specific Vocabulary Extension

et al. 2022

View full text Add to dashboard Cite

Intent recognition is a key component of any task-oriented conversational system. The intent recognizer can be used first to classify the user’s utterance into one of several predefined classes (intents) that help to understand the user’s current goal. Then, the most adequate response can be provided accordingly. Intent recognizers also often appear as a form of joint models for performing the natural language understanding and dialog management tasks together as a single process, thus simplifying the set of problems that a conversational system must solve. This happens to be especially true for frequently asked question (FAQ) conversational systems. In this work, we first present an exploratory analysis in which different deep learning (DL) models for intent detection and classification were evaluated. In particular, we experimentally compare and analyze conventional recurrent neural networks (RNN) and state-of-the-art transformer models. Our experiments confirmed that best performance is achieved by using transformers. Specifically, best performance was achieved by fine-tuning the so-called BETO model (a Spanish pretrained bidirectional encoder representations from transformers (BERT) model from the Universidad de Chile) in our intent detection task. Then, as the main contribution of the paper, we analyze the effect of inserting unseen domain words to extend the vocabulary of the model as part of the fine-tuning or domain-adaptation process. Particularly, a very simple word frequency cut-off strategy is experimentally shown to be a suitable method for driving the vocabulary learning decisions over unseen words. The results of our analysis show that the proposed method helps to effectively extend the original vocabulary of the pretrained models. We validated our approach with a selection of the corpus acquired with the Hispabot-Covid19 system obtaining satisfactory results.

show abstract

“…This is one of the main tasks for the NLU module in order to detect the dialogues acts in the user utterance and provide this information to the dialogue manager. A range of statistical techniques have been proposed to complete this task, from traditional techniques, such as Naive Bayes (McCallum & Nigam, 1998) or Support Vector Machines (Haffner, Tur, & Wright, 2003), to mainstream methods, such as Convolutional Neural Networks (Zhang, Song, Liu, Du, & Zhao, 2017), word embeddings (Liu & Lane, 2016) recurrent neural networks (Firdaus, Kumar, Ekbal, & Bhattacharyya, 2019), long short‐term memory networks (Sreelakshmi, Rafeeque, Sreetha, & Gayathri, 2018) or gated recurrent units (Mauajama Firdaus, B, & Golchha, 2020).…”

Section: State Of the Art: User‐adapted Conversational Interfacesmentioning

confidence: 99%

Adaptive dialogue management using intent clustering and fuzzy rules

et al. 2020

View full text Add to dashboard Cite

Conversational systems have become an element of everyday life for billions of users who use speech-based interfaces to services, engage with personal digital assistants on smartphones, social media chatbots, or smart speakers. One of the most complex tasks in the development of these systems is to design the dialogue model, the logic that provided a user input selects the next answer. The dialogue model must also consider mechanisms to adapt the response of the system and the interaction style according to different groups and user profiles. Rule-based systems are difficult to adapt to phenomena that were not taken into consideration at design-time. However, many of the systems that are commercially available are based on rules, and so are the most widespread tools for the development of chatbots and speech interfaces. In this article, we present a proposal to: (a) automatically generate the dialogue rules from a dialogue corpus through the use of evolving algorithms, (b) adapt the rules according to the detected user intention. We have evaluated our proposal with several conversational systems of different application domains, from which our approach provided an efficient way for adapting a set of dialogue rules considering user utterance clusters.

show abstract

Deep Bi-Directional LSTM Network for Query Intent Detection

Cited by 25 publications

References 7 publications

Text grouping: a comprehensive guide

Text grouping: a comprehensive guide

Fine-Tuning BERT Models for Intent Recognition Using a Frequency Cut-Off Strategy for Domain-Specific Vocabulary Extension

Adaptive dialogue management using intent clustering and fuzzy rules

Contact Info

Product

Resources

About