Merge branch 'master' of https://gitlab.fi.muni.cz/xstefan3/arqmath-eval

ntcir-11-math-2-main/README.md

+This table contains the best result for every user on the *ntcir-11-math-2-main* task.
+
+| nDCG | Result name | User |
+|:-----|:------------|------|
+| *0.6894* | *random* | *xrando42* |

ntcir-12-mathir-arxiv-main/README.md

+This table contains the best result for every user on the *ntcir-12-mathir-arxiv-main* task.
+
+| nDCG | Result name | User |
+|:-----|:------------|------|
+| *0.6471* | *random* | *xrando42* |

ntcir-12-mathir-math-wiki-formula/README.md

+This table contains the best result for every user on the *ntcir-12-mathir-math-wiki-formula* task.
+
+| nDCG | Result name | User |
+|:-----|:------------|------|
+| *0.7336* | *random* | *xrando42* |

scripts/configuration.py

@@ -4,10 +4,10 @@ from pytrec_eval import parse_qrel, RelevanceEvaluator
 
 
 TASK_README_HEAD = r'''
-This table contains the best result for every user.
+This table contains the best result for every user on the *%s* task.
 
-| nDCG | User | Result name |
-|:-----|------|:------------|
+| nDCG | Result name | User |
+|:-----|:------------|------|
 '''.strip()
 USER_README_HEAD = r'''
 This table contains all results for user *%s* in descending order of task
@@ -42,8 +42,12 @@ RELEVANCE_JUDGEMENTS = {
         'ntcir-12-mathir-arxiv-main': 'NTCIR12_Math-qrels_agg-test.dat',
         'ntcir-12-mathir-math-wiki-formula': 'NTCIR12_MathWikiFrm-qrels_agg-test.dat',
     },
+    'all': {
+        'task1-votes.V1.2': 'votes-qrels.V1.2.tsv',
+        'task2-topics-formula_ids.V.1.1': 'topics-formula_ids-qrels.V1.1.tsv',
+    }
 }
-TASKS = list(RELEVANCE_JUDGEMENTS['test'].keys())
+TASKS = list(RELEVANCE_JUDGEMENTS['validation'].keys())
 PARSED_RELEVANCE_JUDGEMENTS = {}
 EVALUATORS = {}
 for subset, filenames in RELEVANCE_JUDGEMENTS.items():

scripts/evaluate.py

@@ -9,7 +9,7 @@ from pytrec_eval import parse_run
 from tqdm import tqdm
 
 from .common import get_ndcg, get_random_ndcg
-from .configuration import TASKS, USER_README_HEAD
+from .configuration import TASKS, USER_README_HEAD, TASK_README_HEAD
 
 
 def evaluate_worker(result_filename):
@@ -24,6 +24,7 @@ if __name__ == '__main__':
     for task in TASKS:
         random_ndcg = get_random_ndcg(task, 'validation')
         users = glob(os.path.join(task, '*', ''))
+        task_results = [(random_ndcg, 'random', 'xrando42')]
         for user in users:
             user = os.path.normpath(user)
             user_name = os.path.basename(user)
@@ -37,6 +38,7 @@ if __name__ == '__main__':
                     with open(os.path.join(user, 'README.md'), 'wt') as f_readme:
                         f_readme.write(USER_README_HEAD % user_name)
                         f_readme.write('\n')
+                        task_results.append((*max(user_results), user_name))
                         for ndcg, result_name in sorted(user_results, reverse=True):
                             if result_name == 'random':
                                 f_readme.write('| *%.4f* | *%s* |\n' % (ndcg, result_name))
@@ -48,4 +50,11 @@ if __name__ == '__main__':
                                 f_readme.write(f_legend.read())
                         except IOError:
                             pass
-
+        with open(os.path.join(task, 'README.md'), 'wt') as f_readme:
+            f_readme.write(TASK_README_HEAD % task)
+            f_readme.write('\n')
+            for ndcg, result_name, user_name in sorted(task_results, reverse=True):
+                if result_name == 'random':
+                    f_readme.write('| *%.4f* | *%s* | *%s* |\n' % (ndcg, result_name, user_name))
+                else:
+                    f_readme.write('|  %.4f  |  %s  |  %s  |\n' % (ndcg, result_name, user_name))

scripts/topics-formula_ids-qrels.V1.1.tsv

+q_4	xxx	B.1	0
+q_55	xxx	B.10	0
+q_71	xxx	B.11	0
+q_73	xxx	B.12	0
+q_76	xxx	B.13	0
+q_77	xxx	B.14	0
+q_82	xxx	B.15	0
+q_92	xxx	B.16	0
+q_97	xxx	B.17	0
+q_111	xxx	B.18	0
+q_9	xxx	B.2	0
+q_130	xxx	B.20	0
+q_136	xxx	B.21	0
+q_172	xxx	B.24	0
+q_199	xxx	B.25	0
+q_205	xxx	B.26	0
+q_207	xxx	B.27	0
+q_213	xxx	B.28	0
+q_238	xxx	B.29	0
+q_13	xxx	B.3	0
+q_245	xxx	B.30	0
+q_262	xxx	B.32	0
+q_267	xxx	B.33	0
+q_278	xxx	B.34	0
+q_290	xxx	B.35	0
+q_294	xxx	B.36	0
+q_305	xxx	B.37	0
+q_319	xxx	B.38	0
+q_22	xxx	B.4	0
+q_329	xxx	B.40	0
+q_336	xxx	B.41	0
+q_340	xxx	B.43	0
+q_351	xxx	B.44	0
+q_362	xxx	B.45	0
+q_370	xxx	B.46	0
+q_402	xxx	B.47	0
+q_427	xxx	B.48	0
+q_459	xxx	B.50	0
+q_472	xxx	B.51	0
+q_479	xxx	B.52	0
+q_501	xxx	B.53	0
+q_503	xxx	B.54	0
+q_504	xxx	B.55	0
+q_510	xxx	B.56	0
+q_514	xxx	B.57	0
+q_525	xxx	B.58	0
+q_528	xxx	B.59	0
+q_25	xxx	B.6	0
+q_535	xxx	B.60	0
+q_561	xxx	B.62	0
+q_569	xxx	B.63	0
+q_574	xxx	B.64	0
+q_604	xxx	B.65	0
+q_612	xxx	B.66	0
+q_616	xxx	B.67	0
+q_620	xxx	B.68	0
+q_637	xxx	B.69	0
+q_643	xxx	B.70	0
+q_646	xxx	B.71	0
+q_663	xxx	B.73	0
+q_690	xxx	B.74	0
+q_698	xxx	B.75	0
+q_707	xxx	B.76	0
+q_727	xxx	B.77	0
+q_739	xxx	B.79	0
+q_49	xxx	B.8	0
+q_743	xxx	B.80	0
+q_754	xxx	B.81	0
+q_807	xxx	B.82	0
+q_819	xxx	B.83	0
+q_825	xxx	B.84	0
+q_840	xxx	B.85	0
+q_849	xxx	B.86	0
+q_854	xxx	B.87	0
+q_883	xxx	B.88	0
+q_884	xxx	B.89	0
+q_52	xxx	B.9	0
+q_894	xxx	B.90	0
+q_931	xxx	B.92	0
+q_940	xxx	B.93	0
+q_944	xxx	B.94	0
+q_954	xxx	B.95	0
+q_977	xxx	B.96	0
+q_997	xxx	B.97	0
+q_1010	xxx	B.98	0

setup.py

@@ -5,7 +5,7 @@ from setuptools import setup
 
 setup(
     name='arqmath_eval',
-    version='0.0.8',
+    version='0.0.12',
     description='Evaluation of ARQMath systems',
     packages=['arqmath_eval'],
     package_dir={'arqmath_eval': 'scripts'},
@@ -32,6 +32,8 @@ setup(
             'votes-qrels-small-validation.V1.0.tsv',
             'votes-qrels-validation.V1.0.tsv',
             'votes-qrels-test.V1.0.tsv',
+            'votes-qrels.V1.2.tsv',
+            'topics-formula_ids-qrels.V1.1.tsv',
         ],
     },
     include_package_data=True,

task1-votes/README.md

+This table contains the best result for every user on the *task1-votes* task.
+
+| nDCG | Result name | User |
+|:-----|:------------|------|
+|  0.7796  |  sbert, validation, html-removal, exid9  |  xstefan3  |
+|  0.7614  |  prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=800, symmetric=True, exponent=4.0, threshold=-1.0  |  xnovot32  |
+|  0.7604  |  prefix, phrases=2, alpha=0.1, dm=0, dm-concat=1, epochs=5, hs=0, min-alpha=0, min-count=5, negative=12, vector-size=300, window=8  |  ayetiran  |
+| *0.7578* | *random* | *xrando42* |

task1-votes/ayetiran/LEGEND.md

 The [Formula2Vec system][scm-at-arqmath] recogizes the following parameters:
 
 - Dataset:
-  - arxmliv, 08, 2019, no-problem – the no\_problem subset (150,701 documents) of [the arXMLiv 08.2019 dataset][arxmliv-08-2019]
   - phrases – how many times [collocation detection][] and bigram merging are iteratively applied to the corpus:
     - 0 – the text and math tokens in the corpus are unchanged,
     - N –  [collocation detection][] and bigram merging are iteratively applied to both text and math tokens in the corpus N times
@@ -21,10 +20,8 @@ The [Formula2Vec system][scm-at-arqmath] recogizes the following parameters:
   - min-count – the minimum term frequency
   - vector-size – vector dimensions
   - window – window size
-  - workers – the number of threads used for [hogwild][]
   - epochs – the number of epochs
 
  [arxmliv-08-2019]: https://sigmathling.kwarc.info/resources/arxmliv-dataset-082019/
  [collocation detection]: https://radimrehurek.com/gensim/models/phrases.html
- [hogwild]: https://papers.nips.cc/paper/4390-hogwild-a-lock-free-approach-to-parallelizing-stochastic-gradient-descent
  [scm-at-arqmath]: https://gitlab.fi.muni.cz/xnovot32/scm-at-arqmath (Soft Cosine Measure at ARQMath)

task1-votes/ayetiran/README.md

@@ -4,7 +4,8 @@ underscores (`_`) replaced with a comma and a space for improved readability.
 
 | nDCG | Result name |
 |------|:------------|
-| 0.7580 | prefix, phrases=2, alpha=0.05, dm=1, dm-concat=1, epochs=5, hs=1, min-alpha=0, min-count=5, vector-size=400, window=4, workers=64 |
+| 0.7604 | prefix, phrases=2, alpha=0.1, dm=0, dm-concat=1, epochs=5, hs=0, min-alpha=0, min-count=5, negative=12, vector-size=300, window=8 |
+| 0.7579 | prefix, phrases=2, alpha=0.05, dm=1, dm-concat=1, epochs=5, hs=1, min-alpha=0, min-count=5, vector-size=400, window=4 |
 | *0.7578* | *random* |
 
 ## Legend
@@ -12,7 +13,6 @@ underscores (`_`) replaced with a comma and a space for improved readability.
 The [Formula2Vec system][scm-at-arqmath] recogizes the following parameters:
 
 - Dataset:
-  - arxmliv, 08, 2019, no-problem – the no\_problem subset (150,701 documents) of [the arXMLiv 08.2019 dataset][arxmliv-08-2019]
   - phrases – how many times [collocation detection][] and bigram merging are iteratively applied to the corpus:
     - 0 – the text and math tokens in the corpus are unchanged,
     - N –  [collocation detection][] and bigram merging are iteratively applied to both text and math tokens in the corpus N times
@@ -32,10 +32,8 @@ The [Formula2Vec system][scm-at-arqmath] recogizes the following parameters:
   - min-count – the minimum term frequency
   - vector-size – vector dimensions
   - window – window size
-  - workers – the number of threads used for [hogwild][]
   - epochs – the number of epochs
 
  [arxmliv-08-2019]: https://sigmathling.kwarc.info/resources/arxmliv-dataset-082019/
  [collocation detection]: https://radimrehurek.com/gensim/models/phrases.html
- [hogwild]: https://papers.nips.cc/paper/4390-hogwild-a-lock-free-approach-to-parallelizing-stochastic-gradient-descent
  [scm-at-arqmath]: https://gitlab.fi.muni.cz/xnovot32/scm-at-arqmath (Soft Cosine Measure at ARQMath)

task1-votes/xnovot32/LEGEND.md

 The [SCM system][scm-at-arqmath] recogizes the following parameters:
 
 - Dataset:
-  - arxmliv, 08, 2019, no-problem – the no\_problem subset (150,701 documents) of [the arXMLiv 08.2019 dataset][arxmliv-08-2019]
   - phrases – how many times [collocation detection][] and bigram merging are iteratively applied to the corpus:
     - 0 – the text and math tokens in the corpus are unchanged,
     - N –  [collocation detection][] and bigram merging are iteratively applied to both text and math tokens in the corpus N times
@@ -24,7 +23,6 @@ The [SCM system][scm-at-arqmath] recogizes the following parameters:
   - sg – the skipgram model
   - size – vector dimensions
   - window – window size
-  - workers – the number of threads used for [hogwild][]
 - Soft Cosine Measure:
   - dominant – whether the term similarity matrix will be strongly diagonally dominant
   - nonzero-limit – the maximum number of non-zero elements outside the diagonal in a single column of the term similarity matrix
@@ -34,6 +32,5 @@ The [SCM system][scm-at-arqmath] recogizes the following parameters:
 
  [arxmliv-08-2019]: https://sigmathling.kwarc.info/resources/arxmliv-dataset-082019/
  [collocation detection]: https://radimrehurek.com/gensim/models/phrases.html
- [hogwild]: https://papers.nips.cc/paper/4390-hogwild-a-lock-free-approach-to-parallelizing-stochastic-gradient-descent
  [scm-at-arqmath]: https://gitlab.fi.muni.cz/xnovot32/scm-at-arqmath (Soft Cosine Measure at ARQMath)
  [term similarity matrix formula]: https://arxiv.org/pdf/2003.05019.pdf#page=4

task1-votes/xnovot32/README.md

@@ -4,36 +4,43 @@ underscores (`_`) replaced with a comma and a space for improved readability.
 
 | nDCG | Result name |
 |------|:------------|
-| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=800, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=200, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=50, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=6, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=5, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=200, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=1600, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=1, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=800, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=0, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=400, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7613 | infix, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=50, symmetric=False, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=10, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=1600, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=1000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=400, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=3, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=8000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7611 | prefix, phrases=2, alpha=0.05, bucket=4000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7610 | prefix, phrases=4, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7607 | slt, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7606 | opt, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7602 | latex, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7600 | nomath, phrases=0, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7598 | nomath, phrases=1, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
-| 0.7596 | nomath, phrases=2, alpha=0.05, bucket=2000000, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, workers=64, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=800, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=200, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=50, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7614 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=6, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=5, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=200, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=1600, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=1, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=800, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=0, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=400, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=50, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7613 | infix, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=400, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7613 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=50, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=10, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=1600, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=1M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=400, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=3, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=50, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7612 | prefix, phrases=2, alpha=0.05, bucket=8M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7611 | prefix, phrases=2, alpha=0.05, bucket=4M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7611 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=200, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7610 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=200, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7610 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7610 | prefix, phrases=4, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7610 | prefix, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=False, nonzero-limit=100, symmetric=False, exponent=4.0, threshold=-1.0 |
+| 0.7607 | slt, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7606 | opt, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7602 | latex, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7600 | nomath, phrases=0, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7598 | nomath, phrases=1, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
+| 0.7596 | nomath, phrases=2, alpha=0.05, bucket=2M, iter=5, max-n=6, min-alpha=0, min-count=5, min-n=3, negative=5, sample=0.0001, sg=1, size=300, window=5, dominant=True, nonzero-limit=100, symmetric=True, exponent=4.0, threshold=-1.0 |
 | *0.7578* | *random* |
 
 ## Legend
@@ -41,7 +48,6 @@ underscores (`_`) replaced with a comma and a space for improved readability.
 The [SCM system][scm-at-arqmath] recogizes the following parameters:
 
 - Dataset:
-  - arxmliv, 08, 2019, no-problem – the no\_problem subset (150,701 documents) of [the arXMLiv 08.2019 dataset][arxmliv-08-2019]
   - phrases – how many times [collocation detection][] and bigram merging are iteratively applied to the corpus:
     - 0 – the text and math tokens in the corpus are unchanged,
     - N –  [collocation detection][] and bigram merging are iteratively applied to both text and math tokens in the corpus N times
@@ -64,7 +70,6 @@ The [SCM system][scm-at-arqmath] recogizes the following parameters:
   - sg – the skipgram model
   - size – vector dimensions
   - window – window size
-  - workers – the number of threads used for [hogwild][]
 - Soft Cosine Measure:
   - dominant – whether the term similarity matrix will be strongly diagonally dominant
   - nonzero-limit – the maximum number of non-zero elements outside the diagonal in a single column of the term similarity matrix
@@ -74,6 +79,5 @@ The [SCM system][scm-at-arqmath] recogizes the following parameters:
 
  [arxmliv-08-2019]: https://sigmathling.kwarc.info/resources/arxmliv-dataset-082019/
  [collocation detection]: https://radimrehurek.com/gensim/models/phrases.html
- [hogwild]: https://papers.nips.cc/paper/4390-hogwild-a-lock-free-approach-to-parallelizing-stochastic-gradient-descent
  [scm-at-arqmath]: https://gitlab.fi.muni.cz/xnovot32/scm-at-arqmath (Soft Cosine Measure at ARQMath)
  [term similarity matrix formula]: https://arxiv.org/pdf/2003.05019.pdf#page=4