From 8677fce7f4708b9f0e22a1244dfa654e66d61bf6 Mon Sep 17 00:00:00 2001 From: Matteo Manica Date: Tue, 8 Jun 2021 22:45:04 +0200 Subject: [PATCH] fix: adjusting indexing for the labels. Now it reflects the content of dataset_infos.json. Signed-off-by: Matteo Manica --- datasets/climate_fever/README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/datasets/climate_fever/README.md b/datasets/climate_fever/README.md index bda39047143..905a137e9fc 100644 --- a/datasets/climate_fever/README.md +++ b/datasets/climate_fever/README.md @@ -80,7 +80,7 @@ The text in the dataset is in English, as found in real-world claims about clima { "claim_id": "0", "claim": "Global warming is driving polar bears toward extinction", - "claim_label": 1, # "SUPPORTS" + "claim_label": 0, # "SUPPORTS" "evidences": [ { "evidence_id": "Extinction risk from global warming:170", @@ -98,7 +98,7 @@ The text in the dataset is in English, as found in real-world claims about clima }, { "evidence_id": "Global warming:14", - "evidence_label": 1, # "SUPPORTS" + "evidence_label": 0, # "SUPPORTS" "article": "Global warming", "evidence": "Environmental impacts include the extinction or relocation of many species as their ecosystems change, most immediately the environments of coral reefs, mountains, and the Arctic.", "entropy": 0.0, @@ -126,7 +126,7 @@ The text in the dataset is in English, as found in real-world claims about clima }, { "evidence_id": "Habitat destruction:61", - "evidence_label": 1, # "SUPPORTS" + "evidence_label": 0, # "SUPPORTS" "article": "Habitat destruction", "evidence": "Rising global temperatures, caused by the greenhouse effect, contribute to habitat destruction, endangering various species, such as the polar bear.", "entropy": 0.0, @@ -160,10 +160,10 @@ The text in the dataset is in English, as found in real-world claims about clima - `claim_id`: a `string` feature, unique claim identifier. - `claim`: a `string` feature, claim text. -- `claim_label`: a `int` feature, overall label assigned to claim (based on evidence majority vote). The label correspond to 0: "refutes", 1: "supports" and 2: "not enough info" +- `claim_label`: a `int` feature, overall label assigned to claim (based on evidence majority vote). The label correspond to 0: "supports", 1: "refutes", 2: "not enough info" and 3: "disputed". - `evidences`: a list of evidences with fields: - `evidence_id`: a `string` feature, unique evidence identifier. - - `evidence_label`: a `int` feature, micro-verdict label. The label correspond to 0: "refutes", 1: "supports" and 2: "not enough info" + - `evidence_label`: a `int` feature, micro-verdict label. The label correspond to 0: "supports", 1: "refutes" and 2: "not enough info". - `article`: a `string` feature, title of source article (Wikipedia page). - `evidence`: a `string` feature, evidence sentence. - `entropy`: a `float32` feature, entropy reflecting uncertainty of `evidence_label`. @@ -242,4 +242,4 @@ This benchmark dataset currently consists of a single data split `test` that con ### Contributions -Thanks to [@tdiggelm](https://github.com/tdiggelm) for adding this dataset. \ No newline at end of file +Thanks to [@tdiggelm](https://github.com/tdiggelm) for adding this dataset.