Handling Multiword Expressions in Causality Estimation

By Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki, Kentaro Inui. 2017

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Ali Emami
2. Adam Trischler
3. Kaheer Suleman
4. Jackie Chi Kit Cheung
5. Noelia De La Cruz
6. Keisuke Sakaguchi
7. Vid Kocijan
8. Shuohang Wang

Citations in the corpus

• WinoGrande (2019, neutral): “mami et al. (2019) 65.0 RoBERTa-DPR? (This work) 84.2 RoBERTa-WinoGrande? (This work) 85.6 Humans (Emami et al. 2019) 92.0 COPA (Roemmele, Bejan, and Gordon 2011) Gordon, Bejan, and Sagae (2011) 65.4 Sasaki et al. (2017) 76.4 RoBERTa-WinoGrande? (This work) 84.4 RoBERTa-ft (This work) 86.4z RoBERTa-”
• A Knowledge Hunting Framework for Common Sense Reasoning (2018, methodology): “It has also been shown that multi-word expressions are prevalent and important for COPA ( Sasaki et al., 2017), which we have not specifically attempted to handle with our method.”
• Guided Generation of Cause and Effect (2020, unknown): “PMI [Jabeen et al. , 2014] 58.8 PMI EX [Gordon et al. , 2011] 65.4 CS [Luo et al. , 2016] 70.2 CS MWP [Sasaki et al. , 2017] 71.2 Google T5-base [Raffel et al. , 2019] 71.2 BERT-base [Li et al. , 2019a] 75.4 CausalBERT-base (ours) 78.6 Google T5-11B [Raffel et al. , 2019] 94.8 Four graduate…”