{"task":"Table-to-Text Generation","dataset":"DART","metric_names":["METEOR","BLEU","BERT","BLEURT","Mover","TER","FactSpotter"],"rows":[{"id":29259,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"T5B Baseline","metrics":{"BERT":"0.9505","BLEU":"48.47","BLEURT":"0.6749","FactSpotter":"96.65","METEOR":"0.4074"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29260,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"FactT5B","metrics":{"BERT":"0.9505","BLEU":"48.37","BLEURT":"0.6743","FactSpotter":"97.60","METEOR":"0.4072"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29261,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"JointGT Baseline","metrics":{"BERT":"0.9492","BLEU":"47.51","BLEURT":"0.6733","FactSpotter":"95.86","METEOR":"0.4043"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29262,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"FactJointGT","metrics":{"BERT":"0.9492","BLEU":"47.39","BLEURT":"0.6726","FactSpotter":"97.25","METEOR":"0.4032"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29263,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"HTLM (fine-tuning)","metrics":{"BERT":"0.94","BLEU":"47.2","BLEURT":"0.4","METEOR":"0.39","Mover":"0.51","TER":"0.44"},"paper_url":"https://arxiv.org/abs/2107.06955v1","paper_title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","paper_date":"2021-07-14","code_links":[],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29264,"task":"Table-to-Text Generation","parent_task":"Text Generation","dataset":"DART","model_name":"GPT-2-Large (fine-tuning)","metrics":{"BERT":"0.94","BLEU":"47.0","BLEURT":"0.4","METEOR":"0.39","Mover":"0.51","TER":"0.46"},"paper_url":"https://arxiv.org/abs/2107.06955v1","paper_title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","paper_date":"2021-07-14","code_links":[],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89362,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"T5B Baseline","metrics":{"BERT":"0.9505","BLEU":"48.47","BLEURT":"0.6749","FactSpotter":"96.65","METEOR":"0.4074"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89363,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"FactT5B","metrics":{"BERT":"0.9505","BLEU":"48.37","BLEURT":"0.6743","FactSpotter":"97.60","METEOR":"0.4072"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89364,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"JointGT Baseline","metrics":{"BERT":"0.9492","BLEU":"47.51","BLEURT":"0.6733","FactSpotter":"95.86","METEOR":"0.4043"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89365,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"FactJointGT","metrics":{"BERT":"0.9492","BLEU":"47.39","BLEURT":"0.6726","FactSpotter":"97.25","METEOR":"0.4032"},"paper_url":"https://dumas.ccsd.cnrs.fr/INRIA-SACLAY/hal-04257838v1","paper_title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","paper_date":"2023-10-25","code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89366,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"HTLM (fine-tuning)","metrics":{"BERT":"0.94","BLEU":"47.2","BLEURT":"0.4","METEOR":"0.39","Mover":"0.51","TER":"0.44"},"paper_url":"https://arxiv.org/abs/2107.06955v1","paper_title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","paper_date":"2021-07-14","code_links":[],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":89367,"task":"Table-to-Text Generation","parent_task":null,"dataset":"DART","model_name":"GPT-2-Large (fine-tuning)","metrics":{"BERT":"0.94","BLEU":"47.0","BLEURT":"0.4","METEOR":"0.39","Mover":"0.51","TER":"0.46"},"paper_url":"https://arxiv.org/abs/2107.06955v1","paper_title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","paper_date":"2021-07-14","code_links":[],"metrics_order":"[\"METEOR\", \"BLEU\", \"BERT\", \"BLEURT\", \"Mover\", \"TER\", \"FactSpotter\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}