DT_Team at SemEval-2017 Task 1: Semantic Similarity Using Alignments, Sentence-Level Embeddings and Gaussian Mixture Model Output
By Nabin Maharjan, Rajendra Banjade, Dipesh Gautam, Lasang Jimba Tamang, Vasile Rus. 2017
18 citations recorded by the source corpus.
We describe our system (DT Team) submitted at SemEval-2017 Task 1, Semantic Textual Similarity (STS) challenge for English (Track 5). We developed three different models with various features including similarity scores calculated using word and chunk alignments, word/sentence embeddings, and Gaussian Mixture Model(GMM). The correlation between our system’s output and the human judgments were up to 0.8536, which is more than 10% above baseline, and almost as good as the best performing system which was at 0.8547 correlation (the difference is just about 0.1%). Also, our system produced leading results when evaluated with a separate STS benchmark dataset. The word alignment and sentence embeddings based features were found to be very effective.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Daniel Matthew Cer
- Graham Neubig
- Iryna Gurevych
- Eneko Agirre
- Mona T. Diab
- John Wieting
- Kevin Gimpel
- Jimmy J. Lin
In Natural Language Processing
- John Wieting
- Kevin Gimpel
- Daniel Matthew Cer
- Kawin Ethayarajh
- Iryna Gurevych
- Mona T. Diab
- Eneko Agirre
- Nils Reimers
Citations in the corpus
- SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, methodology): “2 and skip-thought models (Maharjan et al., 2017) UdL Feature eng.”
- Evaluation of Text Generation: A Survey (2020, neutral): “The higher the score, the better the the similarity prediction result from the algorithm (Maharjan et al., 2017; Cer et al., 2017).”