UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement
By Hua He, John Wieting, Kevin Gimpel, Jinfeng Rao, Jimmy J. Lin. 2016
31 citations recorded by the source corpus.
We describe an attention-based convolutional neural network for the English semantic textual similarity (STS) task in the SemEval2016 competition (Agirre et al., 2016). We develop an attention-based input interaction layer and incorporate it into our multiperspective convolutional neural network (He et al., 2015), using the PARAGRAM-PHRASE word embeddings (Wieting et al., 2016) trained on paraphrase pairs. Without using any sparse features, our final model outperforms the winning entry in STS2015 when evaluated on the STS2015 data.
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
- Jimmy J. Lin
- John Wieting
- Rada Mihalcea
- Eneko Agirre
- Kevin Gimpel
- Graham Neubig
- Kawin Ethayarajh
- Daniel Matthew Cer
In Natural Language Processing
- John Wieting
- Kevin Gimpel
- Kawin Ethayarajh
- Jimmy J. Lin
- Ernie Chang
- Daniel Matthew Cer
- Iryna Gurevych
- Wenlin Zhuang
Citations in the corpus
- Distilling Task-Specific Knowledge from BERT into Simple Neural Networks (2019, background): “These generic architectures can be applied to tasks like sentence classification (Zhang et al., 2015; Conneau et al., 2016) and sentence matching (Wan et al., 2016; He et al., 2016), but the model is trained only on data of a particular task.”
- SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation (2016, methodology): “The next team in the rankings, UMD-TTIC-UW, only makes use of a single deep learning model (He et al., 2016).”
- Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model (2017, methodology): “UMD-TTICUW (He et al., 2016) proposes the MPCNN model that requires no feature engineering and managed to perform competitively at 6th place.”