update data

database/database.json

@@ -38514,5 +38514,34 @@
             "gliner",
             "ner"
         ]
+    },
+    "https://aclanthology.org/2024.naacl-long.307": {
+        "extra-tags": [
+            "retrieval",
+            "text"
+        ],
+        "title": "Multimodal Chart Retrieval: A Comparison of Text, Table and Image Based Approaches",
+        "summary": "We investigate multimodal chart retrieval, addressing the challenge of retrieving image-based charts using textual queries. We compare four approaches: (a) OCR with text retrieval, (b) chart derendering (DePlot) followed by table retrieval, (c) a direct image understanding model (PaLI-3), and (d) a combined PaLI-3 + DePlot approach. As the table retrieval component we introduce Tab-GTR, a text retrieval model augmented with table structure embeddings, achieving state-of-the-art results on the NQ-Tables benchmark with 48.88% R@1. On in-distribution data, the DePlot-based method (b) outperforms PaLI-3 (c), while being significantly more efficient (300M vs 3B trainable parameters). However, DePlot struggles with complex charts, indicating a need for improvements in chart derendering - specifically in terms of chart data diversity and the richness of text/table representations. We found no clear winner between methods (b) and (c) in general, with the best performance achieved by the combined approach (d), and further show that it benefits the most from multi-task training.",
+        "date": "2024-07-12",
+        "tags": [
+            "chart",
+            "information retrieval",
+            "table"
+        ]
+    },
+    "https://huggingface.co/datasets/Universal-NER/Pile-NER-type": {
+        "extra-tags": [
+            "datasets",
+            "source",
+            "science"
+        ],
+        "title": "Universal-NER/Pile-NER-type \u00b7 Datasets at Hugging Face",
+        "summary": "We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.",
+        "date": "2024-07-12",
+        "tags": [
+            "dataset",
+            "ner",
+            "pile ner"
+        ]
     }
 }

database/triples.json

@@ -175894,5 +175894,101 @@
     {
         "head": "llms",
         "tail": "named entity recognition"
+    },
+    {
+        "head": "chart",
+        "tail": "information retrieval"
+    },
+    {
+        "head": "chart",
+        "tail": "table"
+    },
+    {
+        "head": "chart",
+        "tail": "retrieval"
+    },
+    {
+        "head": "chart",
+        "tail": "text"
+    },
+    {
+        "head": "information retrieval",
+        "tail": "table"
+    },
+    {
+        "head": "information retrieval",
+        "tail": "retrieval"
+    },
+    {
+        "head": "information retrieval",
+        "tail": "text"
+    },
+    {
+        "head": "table",
+        "tail": "retrieval"
+    },
+    {
+        "head": "table",
+        "tail": "text"
+    },
+    {
+        "head": "retrieval",
+        "tail": "text"
+    },
+    {
+        "head": "dataset",
+        "tail": "ner"
+    },
+    {
+        "head": "dataset",
+        "tail": "pile ner"
+    },
+    {
+        "head": "dataset",
+        "tail": "source"
+    },
+    {
+        "head": "dataset",
+        "tail": "science"
+    },
+    {
+        "head": "ner",
+        "tail": "pile ner"
+    },
+    {
+        "head": "ner",
+        "tail": "datasets"
+    },
+    {
+        "head": "ner",
+        "tail": "source"
+    },
+    {
+        "head": "ner",
+        "tail": "science"
+    },
+    {
+        "head": "pile ner",
+        "tail": "datasets"
+    },
+    {
+        "head": "pile ner",
+        "tail": "source"
+    },
+    {
+        "head": "pile ner",
+        "tail": "science"
+    },
+    {
+        "head": "datasets",
+        "tail": "source"
+    },
+    {
+        "head": "datasets",
+        "tail": "science"
+    },
+    {
+        "head": "source",
+        "tail": "science"
     }
 ]