alirezamsh
commited on
Commit
•
1222138
1
Parent(s):
17a0e49
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
---
|
2 |
license: bsd-3-clause
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: bsd-3-clause
|
3 |
+
datasets:
|
4 |
+
- mocha
|
5 |
+
language:
|
6 |
+
- en
|
7 |
---
|
8 |
+
|
9 |
+
# Answer Overlap Module of QAFactEval Metric
|
10 |
+
|
11 |
+
|
12 |
+
This is the span scorer module, used in [RQUGE paper]() to evaluate the generated questions of the question generation task.
|
13 |
+
The model was originally used in [QAFactEval]() for computing the semantic similarity of the generated answer span, given the reference answer, context, and question in the question answering task.
|
14 |
+
It outputs a 1-5 answer overlap score. The scorer is trained on their MOCHA dataset (initialized from [Jia et al. (2021)]()), consisting of 40k crowdsourced judgments on QA model outputs.
|
15 |
+
|
16 |
+
The input to the model is defined as:
|
17 |
+
```
|
18 |
+
[CLS] cand. question [q] gold answer [r] pred answer [c] context
|
19 |
+
```
|
20 |
+
|
21 |
+
# Citations
|
22 |
+
|
23 |
+
```
|
24 |
+
@inproceedings{fabbri-etal-2022-qafacteval,
|
25 |
+
title = "{QAF}act{E}val: Improved {QA}-Based Factual Consistency Evaluation for Summarization",
|
26 |
+
author = "Fabbri, Alexander and
|
27 |
+
Wu, Chien-Sheng and
|
28 |
+
Liu, Wenhao and
|
29 |
+
Xiong, Caiming",
|
30 |
+
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
|
31 |
+
month = jul,
|
32 |
+
year = "2022",
|
33 |
+
address = "Seattle, United States",
|
34 |
+
publisher = "Association for Computational Linguistics",
|
35 |
+
url = "https://aclanthology.org/2022.naacl-main.187",
|
36 |
+
doi = "10.18653/v1/2022.naacl-main.187",
|
37 |
+
pages = "2587--2601",
|
38 |
+
abstract = "Factual consistency is an essential quality of text summarization models in practical settings. Existing work in evaluating this dimension can be broadly categorized into two lines of research, entailment-based and question answering (QA)-based metrics, and different experimental setups often lead to contrasting conclusions as to which paradigm performs the best. In this work, we conduct an extensive comparison of entailment and QA-based metrics, demonstrating that carefully choosing the components of a QA-based metric, especially question generation and answerability classification, is critical to performance. Building on those insights, we propose an optimized metric, which we call QAFactEval, that leads to a 14{\%} average improvement over previous QA-based metrics on the SummaC factual consistency benchmark, and also outperforms the best-performing entailment-based metric. Moreover, we find that QA-based and entailment-based metrics can offer complementary signals and be combined into a single metric for a further performance boost.",
|
39 |
+
}
|
40 |
+
|
41 |
+
@misc{mohammadshahi2022rquge,
|
42 |
+
title={RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question},
|
43 |
+
author={Alireza Mohammadshahi and Thomas Scialom and Majid Yazdani and Pouya Yanki and Angela Fan and James Henderson and Marzieh Saeidi},
|
44 |
+
year={2022},
|
45 |
+
eprint={2211.01482},
|
46 |
+
archivePrefix={arXiv},
|
47 |
+
primaryClass={cs.CL}
|
48 |
+
}
|
49 |
+
```
|