Pith Number

pith:WYQWO77D

pith:2026:WYQWO77DNXZRWH2GZXBOZJMNNS

not attested not anchored not stored refs resolved

Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing

Cristina Outeiri\~no Cid, Daniel Fern\'andez-Gonz\'alez

Pre-trained encoder-decoder models like BART and T5, when fine-tuned to output linearized parse trees, outperform earlier sequence-to-sequence parsers and compete with specialized constituent parsers on continuous data.

arxiv:2605.13373 v1 · 2026-05-13 · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WYQWO77DNXZRWH2GZXBOZJMNNS}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our results demonstrate that our approach outperforms all prior sequence-to-sequence models and performs competitively with leading task-specific constituent parsers on continuous constituent parsing.

C2weakest assumption

That standard fine-tuning of encoder-decoder models on linearized trees is sufficient to capture the full syntactic structure without additional task-specific mechanisms or architectural changes.

C3one line summary

Pre-trained encoder-decoder transformers fine-tuned for sequence-to-sequence constituent parsing outperform prior seq2seq models and compete with specialized parsers on continuous treebanks.

References

62 extracted · 62 resolved · 2 Pith anchors

[1] J. G¯ u, H. S. Shavarani, A. Sarkar, Top-down tree structured decoding with syntactic connections for neural machine translation and parsing, in: Proceedings of the 2018 Conference on Empirical Method 2018 · doi:10.18653/v1/d18-1037

[2] X. Wang, H. Pham, P. Yin, G. Neubig, A tree-based decoder for neu- ral machine translation, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for 2018

[3] A. Currey, K. Heafield, Incorporating source syntax into transformer- based neural machine translation, in: Proceedings of the Fourth Con- ference on Machine Translation (Volume 1: Research Papers), A 2019

[4] D. Bouras, M. Amroune, H. Bendjenna, I. Bendib, Improving fine- grained opinion mining approach with a deep constituency tree-long short term memory network and word embedding, Recent Advances in Comp 2022 · doi:10.2174/2666255813999200922142212

[5] Sentibert: A transferable transformer-based architecture for composi- tional sentiment semantics 2020 · doi:10.18653/v1/2020.acl-main.341

Receipt and verification

First computed	2026-05-18T02:44:47.944465Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b621677fe36df31b1f46cdc2eca58d6c9b0fb446a02c8885a67c7e672ec2773b

Aliases

arxiv: 2605.13373 · arxiv_version: 2605.13373v1 · doi: 10.48550/arxiv.2605.13373 · pith_short_12: WYQWO77DNXZR · pith_short_16: WYQWO77DNXZRWH2G · pith_short_8: WYQWO77D

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/WYQWO77DNXZRWH2GZXBOZJMNNS \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b621677fe36df31b1f46cdc2eca58d6c9b0fb446a02c8885a67c7e672ec2773b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1756df113789681676cfe85ce64e1757ad9fc0106825210a078e8136a0442093",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T11:28:56Z",
    "title_canon_sha256": "61239da1604aa1d52a774821fa098d5e5613f472da5c15cb049ab35e32716c21"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13373",
    "kind": "arxiv",
    "version": 1
  }
}