SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.03035 · ACL · 2020

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches

Tianze Shi, Lillian Lee

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2005.03035.json · badge: /api/ran/2005.03035.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
tzshi/flat-mwe-parsing community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
MWEJointDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
tzshi/flat-mwe-parsing/cdpt/modules.py
code served (permissive licence) · get_code("477cce7edf2658bd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, MWEJointDecoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.nn.functional as F


torch.manual_seed(0)


# Build minimal head selector parser module
class MinimalHeadSelParser(nn.Module):
    def __init__(self, hidden_dim=4, vocab_size=10):
        super().__init__()
        self.head_mlp = nn.Linear(hidden_dim, hidden_dim)
        self.dep_mlp = nn.Linear(hidden_dim, hidden_dim)
        self.attention = nn.Bilinear(hidden_dim, hidden_dim, 1)
    
    def batch_cand_mask(self, batch):
        batch_size = batch['mask'].size(0)
        seq_len = batch['mask'].size(1)
        return torch.ones(batch_size, seq_len, seq_len)


# Build minimal relation labeler module
class MinimalRelLabeler(nn.Module):
    def __init__(self, hidden_dim=4, num_rels=5):
        super().__init__()
        self.num_rels = num_rels
        self.scorer = nn.Linear(hidden_dim, num_rels)
    
    def scores(self, lstm_features, batch):
        batch_size = lstm_features.size(0)
        seq_len = lstm_features.size(1)
        # Return shape (num_rels, seq_len, seq_len)
        scores = torch.randn(batch_size, self.num_rels, seq_len, seq_len)
        return scores


# Build minimal NER BIO tagger module
class MinimalNERBIOTagger(nn.Module):
    def __init__(self, hidden_dim=4, num_tags=3):
        super().__init__()
        self.num_tags = num_tags
        self.scorer = nn.Linear(hidden_dim, num_tags)
    
    def scores(self, lstm_features, batch):
        batch_size = lstm_features.size(0)
        seq_len = lstm_features.size(1)
        scores = torch.randn(batch_size, seq_len, self.num_tags)
        return scores


# Minimal parser object with required attributes
class MinimalParser:
    def __init__(self):
        self._rels = {
            'mwe_NNP': [0, 1, 2],
            'flat': [1, 2],
            'punct': [2]
        }


# Helper functions from the forward pass
def parse_mwe(s, rel_scores, t, rels):
    seq_len = s.shape[1]
    heads = [0] * seq_len
    rels_out = [0] * seq_len
    return heads, rels_out


def parse_mwe_ud(s, rel_scores, t, flat_rel, punct_rel):
    seq_len = s.shape[1]
    heads = [0] * seq_len
    rels_out = [0] * seq_len
    return heads, rels_out


# Create instances
hselparser = MinimalHeadSelParser(hidden_dim=4, vocab_size=10)
rellabeler = MinimalRelLabeler(hidden_dim=4, num_rels=5)
nerbiotagger = MinimalNERBIOTagger(hidden_dim=4, num_tags=3)

ARGS = {
    'hselparser': hselparser,
    'rellabeler': rellabeler,
    'nerbiotagger': nerbiotagger,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MWEJointDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MWEJointDecoder output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ParserModule Not yet run
unverified (harvested, no recorded run)
tzshi/flat-mwe-parsing/cdpt/modules.py
code served (permissive licence) · get_code("4f881a086c28efcb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

An interesting and frequent type of multiword expression (MWE) is the headless MWE, for which there are no true internal syntactic dominance relations; examples include many named entities ("Wells Fargo") and dates ("July 5, 2020") as well as certain productive constructions ("blow for blow", "day after day"). Despite their special status and prevalence, current dependency-annotation schemes require treating such flat structures as if they had internal syntactic heads, and most current parsers handle them in the same fashion as headed constructions. Meanwhile, outside the context of parsing, taggers are typically used for identifying MWEs, but taggers might benefit from structural information. We empirically compare these two common strategies-parsing and tagging-for predicting flat MWEs. Additionally, we propose an efficient joint decoding algorithm that combines scores from both strategies. Experimental results on the MWE-Aware English Dependency Corpus and on six non-English dependency treebanks with frequent flat structures show that: (1) tagging is more accurate than parsing for identifying flat-structure MWEs, (2) our joint decoder reconciles the two different views and, for non-BERT features, leads to higher accuracies, and (3) most of the gains result from feature sharing between the parsers and taggers.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.03035")
get_code_for_paper("2005.03035")
have("2005.03035")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.03035.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.03035.svg)](https://syntology.ai/paper/2005.03035)

Connect an agent — have() is free.