forked from castorini/anserini
-
Notifications
You must be signed in to change notification settings - Fork 0
/
msmarco-v1-doc-segmented.yaml
202 lines (198 loc) · 5.51 KB
/
msmarco-v1-doc-segmented.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
---
corpus: msmarco-doc-segmented
corpus_path: collections/msmarco/msmarco-doc-segmented/
index_path: indexes/lucene-inverted.msmarco-v1-doc-segmented/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -storePositions -storeDocvectors -storeRaw
index_stats:
documents: 20545677
documents (non-empty): 20545677
total terms: 3200522554
metrics:
- metric: AP@1000
command: bin/trec_eval
params: -c -m map
separator: "\t"
parse_index: 2
metric_precision: 4
can_combine: false
- metric: RR@100
command: bin/trec_eval
params: -c -M 100 -m recip_rank
separator: "\t"
parse_index: 2
metric_precision: 4
can_combine: false
- metric: R@100
command: bin/trec_eval
params: -c -m recall.100
separator: "\t"
parse_index: 2
metric_precision: 4
can_combine: false
- metric: R@1000
command: bin/trec_eval
params: -c -m recall.1000
separator: "\t"
parse_index: 2
metric_precision: 4
can_combine: false
topic_reader: TsvInt
topics:
- name: "[MS MARCO Doc: Dev](https://github.com/microsoft/MSMARCO-Document-Ranking)"
id: dev
path: topics.msmarco-doc.dev.txt
qrel: qrels.msmarco-doc.dev.txt
models:
- name: bm25-default
display: BM25 (default)
params: -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
results:
AP@1000:
- 0.2690
RR@100:
- 0.2684
R@100:
- 0.7847
R@1000:
- 0.9178
# PRF regressions are no longer maintained for sparse judgments to reduce running times.
# (commenting out instead of removing; in case these numbers are needed, just uncomment and rerun.)
#
# - name: bm25-default+rm3
# display: +RM3
# params: -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2420
# RR@100:
# - 0.2413
# R@100:
# - 0.7891
# R@1000:
# - 0.9351
# - name: bm25-default+rocchio
# display: +Rocchio
# params: -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2453
# RR@100:
# - 0.2447
# R@100:
# - 0.7915
# R@1000:
# - 0.9351
# - name: bm25-default+rocchio-neg
# display: +Rocchio*
# params: -bm25 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2464
# RR@100:
# - 0.2458
# R@100:
# - 0.7888
# R@1000:
# - 0.9339
# - name: bm25-default+ax
# display: +Ax
# params: -bm25 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2208
# RR@100:
# - 0.2201
# R@100:
# - 0.7710
# R@1000:
# - 0.9264
# - name: bm25-default+prf
# display: +PRF
# params: -bm25 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2325
# RR@100:
# - 0.2318
# R@100:
# - 0.7722
# R@1000:
# - 0.9185
- name: bm25-tuned
display: BM25 (tuned)
params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
results:
AP@1000:
- 0.2762
RR@100:
- 0.2756
R@100:
- 0.8013
R@1000:
- 0.9311
# PRF regressions are no longer maintained for sparse judgments to reduce running times.
# (commenting out instead of removing; in case these numbers are needed, just uncomment and rerun.)
#
# - name: bm25-tuned+rm3
# display: +RM3
# params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2455
# RR@100:
# - 0.2448
# R@100:
# - 0.7978
# R@1000:
# - 0.9359
# - name: bm25-tuned+rocchio
# display: +Rocchio
# params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2482
# RR@100:
# - 0.2475
# R@100:
# - 0.8013
# R@1000:
# - 0.9395
# - name: bm25-tuned+rocchio-neg
# display: +Rocchio*
# params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2497
# RR@100:
# - 0.2491
# R@100:
# - 0.8042
# R@1000:
# - 0.9395
# - name: bm25-tuned+ax
# display: +Ax
# params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2330
# RR@100:
# - 0.2324
# R@100:
# - 0.7888
# R@1000:
# - 0.9353
# - name: bm25-tuned+prf
# display: +PRF
# params: -bm25 -bm25.k1 2.16 -bm25.b 0.61 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
# results:
# AP@1000:
# - 0.2276
# RR@100:
# - 0.2269
# R@100:
# - 0.7687
# R@1000:
# - 0.9157