Update README.md
Browse files
README.md
CHANGED
|
@@ -9,4 +9,20 @@ pinned: false
|
|
| 9 |
|
| 10 |
CLUTRR: **C**ompositional **L**anguage **U**nderstanding with **T**ext based **R**elational **R**easoning
|
| 11 |
|
| 12 |
-
A benchmark dataset generator to test relational reasoning on text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
CLUTRR: **C**ompositional **L**anguage **U**nderstanding with **T**ext based **R**elational **R**easoning
|
| 11 |
|
| 12 |
+
A benchmark dataset generator to test relational reasoning on text
|
| 13 |
+
|
| 14 |
+
- Official repo: https://github.com/facebookresearch/clutrr
|
| 15 |
+
|
| 16 |
+
<img src="https://www.cs.mcgill.ca/~ksinha4/assets/img/clutrr_text.png" alt="CLUTRR" width="500"/>
|
| 17 |
+
|
| 18 |
+
If our work is useful for your research, consider citing it using the following bibtex:
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
@article{sinha2019clutrr,
|
| 22 |
+
Author = {Koustuv Sinha and Shagun Sodhani and Jin Dong and Joelle Pineau and William L. Hamilton},
|
| 23 |
+
Title = {CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text},
|
| 24 |
+
Year = {2019},
|
| 25 |
+
journal = {Empirical Methods of Natural Language Processing (EMNLP)},
|
| 26 |
+
arxiv = {1908.06177}
|
| 27 |
+
}
|
| 28 |
+
```
|