HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate Semantic Textual Similarity
By Yang Shao. 2017
69 citations recorded by the source corpus.
This paper describes our convolutional neural network (CNN) system for Semantic Textual Similarity (STS) task. We calculated semantic similarity score between two sentences by comparing their semantic vectors. We generated semantic vector of every sentence by max pooling every dimension of their word vectors. There are mainly two trick points in our system. One is that we trained a CNN to transfer GloVe word vectors to a more proper form for STS task before pooling. Another is that we trained a fully-connected neural network (FCNN) to transfer difference of two semantic vectors to probability of every similarity score. We decided all hyper parameters empirically. In spite of the simplicity of our neural network system, we achieved a good accuracy and ranked 3rd in primary track of SemEval 2017.
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
- John Wieting
- Kevin Gimpel
- Daniel Matthew Cer
- Yinfei Yang
- Graham Neubig
- Iryna Gurevych
- Ivan Vulic
- Jianfeng Gao
In Natural Language Processing
- John Wieting
- Kevin Gimpel
- Daniel Matthew Cer
- Yinfei Yang
- Iryna Gurevych
- Graham Neubig
- Kawin Ethayarajh
- Hinrich Schütze
Citations in the corpus
- SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation (2017, methodology): “15Within the highlighted submissions, the following use a monolingual English system fed by MT: ECNU, BIT, HCTI and MITRE.”
- Learning Semantic Textual Similarity from Conversations (2018, methodology): “model CNN (HCTI) (Shao, 2017) and other systems in Cer et al.”
- Universal Sentence Encoder for English (2018, methodology): “On the STS Benchmark, we compare with InferSent and the state-of-the-art neural STS systems CNN (HCTI) (Shao, 2017) and gConv (Yang et al., 2018).”
- ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations (2017, background): “al., 2013) 56.5 (Pagliardini et al., 2017) 75.5 Supervised (Tai et al., 2015) LSTM 70.5 (Tai et al., 2015) BiLSTM 71.1 (Tai et al., 2015) Dep. Tree LSTM 71.2 (Tai et al., 2015) Const. Tree LSTM 71.9 (Shao, 2017) 78.4 Table 9: Pearson’s ron the test set of the STS Benchmark. Models Avg. Abs. Pearson’”
- Evolution of Semantic Similarity—A Survey (2020, background): “• Yang Shao [86] proposed a semantic similarity algorithm that exploits, the recent development in neural networks using GloVe word embeddings.”
- Unsupervised Random Walk Sentence Embeddings: A Strong but Simple Baseline (2018, unknown): “9 CNN (HCTI) (Shao, 2017) 78.”
- Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations (2017, background): “al., 2013) 56.5 (Pagliardini et al., 2017) 75.5 Supervised (Tai et al., 2015) LSTM 70.5 (Tai et al., 2015) BiLSTM 71.1 (Tai et al., 2015) Dep. Tree LSTM 71.2 (Tai et al., 2015) Const. Tree LSTM 71.9 (Shao, 2017) 78.4 Table 9: Pearson’s ron the test set of the STS Benchmark. Models Avg. Abs. Pearson’”