Tata Consultancy Services Limited

Mayur Patidar

Gautam Shroff

Lovekesh Vig

Puneet Kumar Agarwal

Rajat Kumar

Bagya Lakshmi Vasudevan

Prerna Khurana

Rohit Kumar

Sudesna Baruah

Vivek Bisht

Rachit Bansal

Prateek Sachan

Mahesh Prasad Singh

Vaibhav Varshney

Ashish Chaudhary

Meghna Kishor Mahajan

Puneet Agarwal

Existing semi-supervised and unsupervised approaches for intent discovery require an estimate of the number of new intents present in the user logs. The present disclosure receives labeled utterances from known intents and update parameters of a pre-trained language model (PLM). Representation learning and clustering is performed iteratively using labeled and unlabeled utterances from known intents and unlabeled utterances from unknown intents to fine-tune PLM and a plurality of clusters is generated. Cluster merger algorithm is executed iteratively on generated plurality of clusters. A query cluster is obtained by randomly selecting one cluster from the plurality of clusters and by obtaining a corresponding plurality of nearest neighbors based on a cosine-similarity. A response for merging the query cluster and corresponding plurality of nearest neighbors is obtained, and a new cluster is created. The corresponding cluster representation is recalculated and each of the new cluster is interpreted as an intent.

System and method for intent discovery from user logs using deep semi-supervised contrastive clustering

E-commerce industry is currently expanding rapidly, worldwide. A process of generating product copy for grocery items, which is very challenging as food items, do not have features in common, unlike fashion products. A data associated with one or more grocery products is received as an input. The data is processed to obtain one or more sorted similar grocery products. One or more relevant attributes and allergen information associated with the one or more sorted similar grocery products are extracted. A vocabulary model is created based the one or more relevant attributes and the allergen information associated with the one or more sorted similar grocery products. The vocabulary model is validated based on one or more assigned weights on training data. The one or more descriptive copies associated with grocery products are generated by mapping the validated vocabulary model with the training data.

Method and system for generation of descriptive copy of grocery products

Users have to assign labels to a ticket to route to right domain expert for resolving issue(s). In practice, labels are large and organized in form of a tree. Lack in clarity in problem description has resulted in inconsistent and incorrect labeling of data, making it hard for one to learn/interpret. Embodiments of the present disclosure provide systems and methods that identify relevant queries to obtain user response, for identification of right category and ticket logging there. This is achieved by implementing attention based sequence to sequence (seq2seq) hierarchical classification model to assign the hierarchical categories to tickets, followed by a slot filling model to enable identifying/deciding right set of queries, if the top-k model predictions are not consistent. Further, training data for slot filling model is automatically generated based on attention weight in the hierarchical classification model.

Systems and methods for conversational based ticket logging

In automated assistant systems, a deep-learning model in form of a long short-term memory (LSTM) classifier is used for mapping questions to classes, with each class having a manually curated answer. A team of experts manually create the training data used to train this classifier. Relying on human curation often results in such linguistic training biases creeping into training data, since every individual has a specific style of writing natural language and uses some words in specific context only. Deep models end up learning these biases, instead of the core concept words of the target classes. In order to correct these biases, meaningful sentences are automatically generated using a generative model, and then used for training a classification model. For example, a variational autoencoder (VAE) is used as the generative model for generating novel sentences and a language model (LM) is utilized for selecting sentences based on likelihood.

Techniques for correcting linguistic training bias in training data

Systems and methods for Deep Learning techniques based multi-purpose conversational agents for processing natural language queries. The traditional systems and methods provide for conversational systems for processing natural language queries but do not employ Deep Learning techniques, and thus are unable to process large number of intents. Embodiments of the present disclosure provide for Deep Learning techniques based multi-purpose conversational agents for processing the natural language queries by defining and logically integrating a plurality of components comprising of multi-purpose conversational agents, identifying an appropriate agent to process one or more natural language queries by a High Level Intent Identification technique, predicting a probable user intent, classifying the query, and generate a set of responses by querying or updating one or more knowledge graphs.

Deep learning techniques based multi-purpose conversational agents for processing natural language queries

Growing community of inventors

Noida, India

Mayur Patidar