https://github.com/ArneBinder/pie-document-level/pull/312

configs/demo.yaml

@@ -0,0 +1,73 @@
+# model details
+default_model_name: "ArneBinder/sam-pointer-bart-base-v0.3.1"
+default_model_revision: "d090d5385380692933e8a3bc466236e3a905492d"
+# Whether to handle segmented entities in the document. If True, labeled_spans are converted
+# to labeled_multi_spans and binary_relations with label "parts_of_same" are used to merge them.
+# This requires the networkx package to be installed.
+handle_parts_of_same: true
+# Split the document text into sections that are processed separately.
+default_split_regex: "\n\n\n+"
+
+# retriever details
+default_retriever_config_path: "configs/retriever/related_span_retriever_with_relations_from_other_docs.yaml"
+default_min_similarity: 0.95
+
+# data import details
+default_arxiv_id: "1706.03762"
+default_load_pie_dataset_kwargs:
+  path: "pie/sciarg"
+  name: "resolve_parts_of_same"
+  split: "train"
+
+# for better readability in the UI
+render_mode_captions:
+  displacy: "displaCy + highlighted arguments"
+  pretty_table: "Pretty Table"
+layer_caption_mapping:
+  labeled_multi_spans: "adus"
+  binary_relations: "relations"
+  labeled_partitions: "partitions"
+relation_name_mapping:
+  supports_reversed: "supported by"
+  contradicts_reversed: "contradicts"
+
+default_render_mode: "displacy"
+default_render_kwargs:
+  entity_options:
+    # we need to have the keys as uppercase because the spacy rendering function converts the labels to uppercase
+    colors:
+      OWN_CLAIM: "#009933"
+      BACKGROUND_CLAIM: "#99ccff"
+      DATA: "#993399"
+  colors_hover:
+    selected: "#ffa"
+    # tail options for relationships
+    tail:
+      # green
+      supports: "#9f9"
+      # red
+      contradicts: "#f99"
+      # do not highlight
+      parts_of_same: null
+    head: null # "#faf"
+    other: null
+
+example_text: >
+  Scholarly Argumentation Mining (SAM) has recently gained attention due to its
+  potential to help scholars with the rapid growth of published scientific literature.
+  It comprises two subtasks: argumentative discourse unit recognition (ADUR) and
+  argumentative relation extraction (ARE), both of which are challenging since they
+  require e.g. the integration of domain knowledge, the detection of implicit statements,
+  and the disambiguation of argument structure.
+
+  While previous work focused on dataset construction and baseline methods for
+  specific document sections, such as abstract or results, full-text scholarly argumentation
+  mining has seen little progress. In this work, we introduce a sequential pipeline model
+  combining ADUR and ARE for full-text SAM, and provide a first analysis of the
+  performance of pretrained language models (PLMs) on both subtasks.
+
+  We establish a new SotA for ADUR on the Sci-Arg corpus, outperforming the previous best
+  reported result by a large margin (+7% F1). We also present the first results for ARE, and
+  thus for the full AM pipeline, on this benchmark dataset. Our detailed error analysis reveals
+  that non-contiguous ADUs as well as the interpretation of discourse connectors pose major
+  challenges and that data annotation needs to be more consistent.