ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity
By Junfeng Tian, Zhi-Min Zhou, Man Lan, Yuanbin Wu. 2017
79 citations recorded by the source corpus.
To address semantic similarity on multilingual and cross-lingual sentences, we firstly translate other foreign languages into English, and then feed our monolingual English system with various interactive features. Our system is further supported by combining with deep learning semantic similarity and our best run achieves the mean Pearson correlation 73.16% in primary track.
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
- Yinfei Yang
- Daniel Matthew Cer
- Noah Constant
- Iryna Gurevych
- Brian Strope
- R. Kurzweil
- Yun-Hsuan Sung
- Nils Reimers
In Natural Language Processing
- Yinfei Yang
- Daniel Matthew Cer
- Noah Constant
- Brian Strope
- Iryna Gurevych
- R. Kurzweil
- Yun-Hsuan Sung
- Nils Reimers
Citations in the corpus
- Learning Semantic Textual Similarity from Conversations (2018, methodology): “, 2015), ECNU (Tian et al., 2017) and BIT (Wu et al.”
- Improving Language Understanding by Generative Pre-Training (2018, unknown): “0 - - ECNU (mixed ensemble) [60] - - - 81.”
- Predicting Translation Performance with Referential Translation Machines (2017, methodology): “• additional learning models including KNN, AdaBoost, and gradient boosting regressor (GBR) (Tian et al., 2017; Hastie et al., 2009).”