Combining word embeddings and convolutional neural networks to detect duplicated questions
- Detecting semantic similarities between sentences is still a challenge today due to the ambiguity of natural languages. In this work, we propose a simple approach to identifying semantically similar questions by combining the strengths of word embeddings and Convolutional Neural Networks (CNNs). In addition, we demonstrate how the cosine similarity metric can be used to effectively compare feature vectors. Our network is trained on the Quora dataset, which contains over 400k question pairs. We experiment with different embedding approaches such as Word2Vec, Fasttext, and Doc2Vec and investigate the effects these approaches have on model performance. Our model achieves competitive results on the Quora dataset and complements the well-established evidence that CNNs can be utilized for paraphrase recognition tasks.
| Author of HS Reutlingen | Dimitrov, Yoan |
|---|---|
| URN: | urn:nbn:de:bsz:rt2-opus4-27505 |
| ISBN: | 978-3-00-065431-2 |
| Erschienen in: | Connect(IT) : Informatik-Konferenz der Hochschule Reutlingen ; 20. Mai 2020 : Tagungsband. - (Informatics Inside ; 20) |
| Publisher: | Hochschule Reutlingen |
| Place of publication: | Reutlingen |
| Document Type: | Conference proceeding |
| Language: | English |
| Publication year: | 2020 |
| Tag: | convolutional neural networks; deep learning; natural language processing; sentence classification; word embeddings |
| Page Number: | 9 |
| First Page: | 74 |
| Last Page: | 82 |
| DDC classes: | 004 Informatik |
| Open access?: | Ja |
| Licence (German): |  Open Access |
