larc-iu/topdown_biaffine-rstdt-coarse

A pretrained Top-down Biaffine RST parser trained with IUDEX.

This model uses SpanBERT/spanbert-base-cased as its underlying encoder.

Data

RST Discourse Treebank (RST-DT) (English). 385 WSJ articles from the Penn Treebank, annotated in RST with a fine-grained relation inventory.RST-DT is the traditional English benchmark for RST parsing.

Relation labels: Mapped from an original label inventory with 111 items to 18 labels. Mapped labels:

attribution, background, cause, comparison, condition, contrast, elaboration, enablement, evaluation, explanation, joint, manner-means, same-unit, summary, temporal, textual-organization, topic-change, topic-comment

Metrics

Split	span_f1	nuc_f1	rel_f1	full_f1
dev	0.7576	0.6422	0.5383	0.5210
test	0.7552	0.6330	0.5257	0.5135

Usage

Programmatic:

from iudex.rst.parsers.topdown_biaffine.modeling_topdown_biaffine import TopdownBiaffineParser

parser = TopdownBiaffineParser.from_pretrained("larc-iu/topdown_biaffine-rstdt-coarse")
# This parser requires gold EDU segmentation, so the input must be an RS3/RS4 file.
from iudex.rst.data.reader import read_rst_file
gold = read_rst_file(
    "doc.rs3",
    relation_types=parser.config.relation_types,
    relation_map=parser.config.relation_map,
)
tree = parser.predict(gold)

CLI:

python -m iudex topdown_biaffine predict --hub-id larc-iu/topdown_biaffine-rstdt-coarse --input <doc.rs3> --output-dir out/

Citation

If you use this model, please cite both the underlying paper:

@inproceedings{topdown_biaffine_paper,
  title = {A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing},
  author = {Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata},
  booktitle = {Findings of EMNLP 2022},
  url = {https://aclanthology.org/2022.findings-emnlp.501/},
}

And the IUDEX library:

@misc{gessler-iudex-2026,
  author       = {Gessler, Luke},
  title        = {{IUDEX: The Indiana University Discourse Exhibition}},
  year         = {2026},
  howpublished = {\url{https://github.com/larc-iu/iudex}},
}

Full training configuration

See below for the full training configuration this model was trained with.

{
  "train_dir": "data/rstdt/train",
  "dev_dir": "data/rstdt/dev",
  "test_dir": "data/rstdt/test",
  "relation_types": [
    [
      "attribution",
      "rst"
    ],
    [
      "background",
      "rst"
    ],
    [
      "cause",
      "multinuc"
    ],
    [
      "cause",
      "rst"
    ],
    [
      "comparison",
      "multinuc"
    ],
    [
      "comparison",
      "rst"
    ],
    [
      "condition",
      "multinuc"
    ],
    [
      "condition",
      "rst"
    ],
    [
      "contrast",
      "multinuc"
    ],
    [
      "contrast",
      "rst"
    ],
    [
      "elaboration",
      "rst"
    ],
    [
      "enablement",
      "rst"
    ],
    [
      "evaluation",
      "multinuc"
    ],
    [
      "evaluation",
      "rst"
    ],
    [
      "explanation",
      "multinuc"
    ],
    [
      "explanation",
      "rst"
    ],
    [
      "joint",
      "multinuc"
    ],
    [
      "manner-means",
      "rst"
    ],
    [
      "same-unit",
      "multinuc"
    ],
    [
      "summary",
      "rst"
    ],
    [
      "temporal",
      "multinuc"
    ],
    [
      "temporal",
      "rst"
    ],
    [
      "textual-organization",
      "multinuc"
    ],
    [
      "topic-change",
      "multinuc"
    ],
    [
      "topic-change",
      "rst"
    ],
    [
      "topic-comment",
      "multinuc"
    ],
    [
      "topic-comment",
      "rst"
    ]
  ],
  "relation_map": {
    "Analogy": "comparison",
    "Cause-Result": "cause",
    "Comment-Topic": "topic-comment",
    "Comparison": "comparison",
    "Consequence": "cause",
    "Contrast": "contrast",
    "Disjunction": "joint",
    "Evaluation": "evaluation",
    "Interpretation": "evaluation",
    "Inverted-Sequence": "temporal",
    "List": "joint",
    "Otherwise": "condition",
    "Problem-Solution": "topic-comment",
    "Proportion": "comparison",
    "Question-Answer": "topic-comment",
    "Reason": "explanation",
    "Same-Unit": "same-unit",
    "Sequence": "temporal",
    "Statement-Response": "topic-comment",
    "Temporal-Same-Time": "temporal",
    "TextualOrganization": "textual-organization",
    "Topic-Comment": "topic-comment",
    "Topic-Drift": "topic-change",
    "Topic-Shift": "topic-change",
    "analogy": "comparison",
    "analogy-e": "comparison",
    "antithesis": "contrast",
    "antithesis-e": "contrast",
    "attribution": "attribution",
    "attribution-e": "attribution",
    "attribution-n": "attribution",
    "background": "background",
    "background-e": "background",
    "cause": "cause",
    "circumstance": "background",
    "circumstance-e": "background",
    "comment": "evaluation",
    "comment-e": "evaluation",
    "comparison": "comparison",
    "comparison-e": "comparison",
    "concession": "contrast",
    "concession-e": "contrast",
    "conclusion": "evaluation",
    "condition": "condition",
    "condition-e": "condition",
    "consequence-n": "cause",
    "consequence-n-e": "cause",
    "consequence-s": "cause",
    "consequence-s-e": "cause",
    "contingency": "condition",
    "definition": "elaboration",
    "definition-e": "elaboration",
    "elaboration-additional": "elaboration",
    "elaboration-additional-e": "elaboration",
    "elaboration-general-specific": "elaboration",
    "elaboration-general-specific-e": "elaboration",
    "elaboration-object-attribute": "elaboration",
    "elaboration-object-attribute-e": "elaboration",
    "elaboration-part-whole": "elaboration",
    "elaboration-part-whole-e": "elaboration",
    "elaboration-process-step": "elaboration",
    "elaboration-process-step-e": "elaboration",
    "elaboration-set-member": "elaboration",
    "elaboration-set-member-e": "elaboration",
    "enablement": "enablement",
    "enablement-e": "enablement",
    "evaluation-n": "evaluation",
    "evaluation-s": "evaluation",
    "evaluation-s-e": "evaluation",
    "evidence": "explanation",
    "evidence-e": "explanation",
    "example": "elaboration",
    "example-e": "elaboration",
    "explanation-argumentative": "explanation",
    "explanation-argumentative-e": "explanation",
    "hypothetical": "condition",
    "interpretation-n": "evaluation",
    "interpretation-s": "evaluation",
    "interpretation-s-e": "evaluation",
    "manner": "manner-means",
    "manner-e": "manner-means",
    "means": "manner-means",
    "means-e": "manner-means",
    "otherwise": "condition",
    "preference": "comparison",
    "preference-e": "comparison",
    "problem-solution-n": "topic-comment",
    "problem-solution-s": "topic-comment",
    "purpose": "enablement",
    "purpose-e": "enablement",
    "question-answer-n": "topic-comment",
    "question-answer-s": "topic-comment",
    "reason": "explanation",
    "reason-e": "explanation",
    "restatement": "summary",
    "restatement-e": "summary",
    "result": "cause",
    "result-e": "cause",
    "rhetorical-question": "topic-comment",
    "statement-response-n": "topic-comment",
    "statement-response-s": "topic-comment",
    "summary-n": "summary",
    "summary-s": "summary",
    "temporal-after": "temporal",
    "temporal-after-e": "temporal",
    "temporal-before": "temporal",
    "temporal-before-e": "temporal",
    "temporal-same-time": "temporal",
    "temporal-same-time-e": "temporal",
    "topic-drift": "topic-change",
    "topic-shift": "topic-change"
  },
  "model_name": "SpanBERT/spanbert-base-cased",
  "ffn_hidden_size": 512,
  "dropout": 0.2,
  "stride": 100,
  "lr": 0.0002,
  "encoder_lr": 1e-05,
  "max_epochs": 30,
  "grad_accum": 1,
  "patience": 10,
  "max_grad_norm": 1,
  "weight_decay": 0.01,
  "num_warmup_steps": 1000,
  "log_every": 50,
  "validate_every": null,
  "checkpoint_every": null,
  "checkpoint_dir": "checkpoints",
  "run_name": null,
  "seed": 42,
  "val_metric_name": "span_f1"
}