Icon

JKISeason3-30_​tark

<p><strong>Do these Two Questions Have the Same Intent?</strong></p><p><strong>Challenge 30</strong></p><p><br><strong>Level: </strong>Hard<br><br><strong>Description: </strong>You work for a company that wants to improve its support for customers. Once a customer submits a question, a system should find similar questions that were submitted in the past in its database, fetch the answers that were given, and send all this data to a customer service representative. The representative should review these answers and leverage them to assist the current customer. As a first step to create this system, you should create a mechanism that recognizes whether two questions have the same intent. This will be key for finding relevant previous questions in the company’s database, leading to more effective support. Given a dataset of question pairs, annotated with whether or not they have the same intent, create a classifier that learns how to make this distinction. <strong>Hint:</strong> You can find more information about the datasets <strong>here</strong>. <strong>Hint 2:</strong> The <strong>KNIME Textprocessing extension</strong> is helpful for creating features to represent the questions.<br><br><strong>Author: Aline Bessa</strong><br><br><strong>Dataset:</strong> <strong>Questions Data in the KNIME Community Hub</strong></p>

URL: Just KNIME It https://www.knime.com/just-knime-it
URL: This challenge thread https://forum.knime.com/t/solutions-to-just-knime-it-challenge-30-season-3/85242
URL: Dataset https://hub.knime.com/alinebessa/spaces/Just%20KNIME%20It!%20Season%203%20-%20Datasets/Challenge%2030%20-%20Dataset~ceSHb705qrMSl269/
URL: Reference workflow: Train an LSTM for Sentiment Analysis https://hub.knime.com/lada/spaces/01%20Machine%20learning,%20autoML,%20model%20productionization/Neural%20networks/Train%20an%20LSTM%20for%20Sentiment%20Analysis~Y050zO2lNp60mSAG/current-state

Nodes

Extensions

Links