Published paper: https://link.springer.com/chapter/10.1007/978-3-319-71746-3_22
In the rapidly evolving domain of Natural Language Proces...
Published paper: https://link.springer.com/chapter/10.1007/978-3-319-71746-3_22
In the rapidly evolving domain of Natural Language Processing (NLP) and Machine Learning (ML), the ability to accurately detect paraphrases presents a pivotal challenge with significant implications across various applications, from plagiarism detection to enhancing conversational AI. This project introduces an innovative paraphrase detection system to address this challenge. This system sets a new benchmark for accuracy and efficiency in identifying paraphrased content.
Python
JSON
YAML
JavaScript
View more
Published paper: https://aclanthology.org/S18-1025.pdf
I performed experiments with manually created sentiment lexicons and word embeddin...
Published paper: https://aclanthology.org/S18-1025.pdf
I performed experiments with manually created sentiment lexicons and word embeddings. Then tested their performance on twitter affect detection task to determine which features produce the most informative representation of a sentence. I demonstrated that general-purpose word embeddings produces more informative sentence representation than lexicon features. However, combining lexicon features with embeddings yields higher performance than embeddings alone.
This is a solution for the task:
https://competitions.codalab.org/competitions/17751