This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: Snowflake/snowflake-arctic-embed-l
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("kamkol/ab_testing_finetuned_arctic_ft-36dfff22-0696-40d2-b3bf-268fe2ff2aec")
# Run inference
sentences = [
    'who jacob cohen say about power analysis?',
    '#3: Need over 200K Visitors in Online Experiment • Maybe you need half or double this, but do not trust online controlled experiments with 2,000 users • Let me start with the assumptions required for this default: • Alpha=0.05 to declare stat-sig (industry standard, default #1 in this talk). Lower values, which are appropriate sometimes, will result in increasing sample size • Power=80%. We’ll discuss power over the next few slides, but this is a minimum. Going to higher power will increase the sample size. • Conversion rate is 5%. Even if you’re optimizing for something else, it is very common to build a guardrail on conversions. Sites are typically 2%-5%. A lower number will increase the sample size • MDE (minimum detectable effect) is relative 5%. It is rare to see experiments improve key metrics by 5%, but we’ll be aggressive looking for big wins. A small MDE will increase the sample size #16 When I finally stumbled onto power analysis… it was as if I had died and gone to heaven -- Jacob Cohen (1990) © 2022 Ron Kohavi #3: The Sobering Math • The power formula is simple: • For conversions, 𝜎2 = 𝑝∗(1−𝑝)(binomial distribution). We assume p=5%, so 𝜎2 = 0.05∗0.95 • Our MDE is 5% relative, so 𝛿 = 5%∗5%(absolute) • Plug it in, and n=121,600 per variant, or 243,200 for A/B test • 200K is therefore conservative minimum for these assumptions • Lower alpha, increase power, lower conversion rate, or lower the MDE, and you need a larger sample #17 © 2022 Ron Kohavi #3: What is Power? • Statistical power is the probability of detecting a given difference between the variants when there really is one • Given H0 (left) and H1 (right) separated by 𝛿 • Stat-sig is noted by the dark area (only the right one matters here) • The vertical lines indicate β, which is our type-II error (power= 1-β) • With low power, the right normal moves left and the vertical lines cover most of that distribution. You have to be “lucky” to get stat-sig #18 Diagram from van Belle (2011) © 2022 Ron Kohavi Winner’s Curse • A stat-sig result with low power has a high probability of exaggerating the actual number as follows → (Gelman and Carlin 2014) • GuessTheTest on 16 Dec 2021, shared an example with ~80 users in each variant and 337% improvement • It had 3% power to detect even a 10% delta, so it is 63% likely to be a false positive and highly likely to exaggerate effect. See http://bit.ly/ABTestingIntuitionBusters #19 © 2022 Ron Kohavi A Visualization of Power • If the null hypothesis is true (no difference, or effect is zero), the distribution of p-values is uniform • Using p-value of 0.05, about 5% of the time you’ll declare something stat-sig • We’ll look at the p-value distribution of 10,000 experiments where the treatment has a 5% lift (relative improvement) #20 © 2022 Ron Kohavi Power = 3% (N=100 per variant) Delta of 1 Delta 0Delta of 2 Delta of 3 Delta of 4 With so few users, only a few conversion combinations are possible, hence only a few p-values are possible © 2022 Ron Kohavi Power = 3% (N=100 per variant) cont • With small numbers, you get extreme results – winner’s curse • C had 13 conversions, T had 0 conversions ( -100%, p-value 0.00003) • C had 1 conversion, T had 13 conversions (+1200%, p-value 0.0001) • Average lift (absolute value) for stat-sig results was 271% Remember: true lift is 5%, so exaggeration factor is 54 times for average! • The maximum was 1200% lift, so 240 times the true value. • Wrong sign for stat-sig result: 36% of the time The truth was that there was a 5% lift, but we got a stat-sig negative lift! #22 © 2022 Ron Kohavi Power = ~10% (N=7,000 per variant) #23 Looks almost uniform (remember, our goal is for p-value < 0.05) Stat-sig only ~10% of the time (vs. 5% expected if there was no difference) Winner’s curse: when stat-sig, exaggeration factor of 3.9 (19.3% lift) © 2022 Ron Kohavi Power = ~30% (N=32,000 per variant) #24 Starts to put more mass below 0.05 Winner’s curse: when stat-sig, exaggeration factor of 1.9 (9.3% average lift) Could even get the sign wrong 0.1% of the time when stat-sig © 2022 Ron Kohavi Power = ~80% (N=122,000) #25 That’s the minimum we want: ~80% of the time, p-value < 0.05 Small exaggeration factor of 1.1 (5.6% average lift vs. real value of 5%) Never get the sign wrong when stat-sig © 2022 Ron Kohavi Power = ~90% (N=163,000) #26 Extending experiment from 122K users to 163K users (e.g., 34% longer) gives us great 90% power © 2022 Ron Kohavi References • Excel spreadsheet with the visualizations here (Nov 2022) • Low power LinkedIn post (Sept 2022) • A/B Testing Intuition Busters(Aug 2022) • Gelman, This is what “power = .06” looks like. Get used to it (11/2014) #27 © 2022 Ron Kohavi',
    '<1-hop>\n\n3 ESTIMATING THE FALSE POSITIVE RISK P-values are commonly misinterpreted as the probability of making a mistake when choosing the Treatment over Control when the observed metric of interest is statistically significantly different [25; 26; 27]. Multiple examples of this misinterpretation by A/B vendors, book authors, and in courts were provided by Kohavi, Deng, and Vermeer [14]. What is the p-value then? The p-value is the probability of obtaining a result equal to or more extreme than what was observed, assuming that all the modeling assumptions, including the null hypothesis, 𝐻\u0b34, are true [26]. Conditioning1 on the null hypothesis is critical and most often misunderstood. In probabilistic terms, we have p-value = 𝑃(Δ 𝑜𝑏𝑠𝑒𝑟𝑣𝑒𝑑 𝑜𝑟 𝑚𝑜𝑟𝑒 𝑒𝑥𝑡𝑟𝑒𝑚𝑒|𝐻\u0b34 𝑖𝑠 𝑡𝑟𝑢𝑒). What we are looking for most of the time is the opposite conditional probability: 𝑃(𝐻\u0b34 𝑖𝑠 𝑡𝑟𝑢𝑒 |Δ 𝑜𝑏𝑠𝑒𝑟𝑣𝑒𝑑) Using Bayes Rule, we can estimate the False Positive Risk (FPR), which is the probability that the statistically significant result is a false positive, or the probability that 𝐻\u0b34 is true (no real effect) when the test was statistically significant [15]. Note that FPR is sometimes named FDR, or False Discovery Rate [28; 29], but given the confusion with FDR from multiple hypothesis testing, we use the term recommended by Colquhoun [15]. We use the following terminology [14]: a) SS is a statistically significant positive2 result. b) 𝜶 is the threshold used to determine statistical significance (SS), commonly 0.05 for a two-tailed t-test, and 0.025 for the positive tail. c) 𝜷 is the type-II error (usually 0.2 for 80% power). d) 𝝅 is the prior probability of the null hypothesis, that is 𝑃(𝐻\u0b34). We can apply Bayes Rules as follows: 𝐹𝑃𝑅 = 𝑃(𝐻\u0b34|𝑆𝑆)= α∗గ α∗ గ ା (ଵିఉ)∗(ଵିగ) . An alternative derivation of FPR, resulting in the same formula, was made in the Supplement to Equation 2 and Figure 2 in Benjamin et. al. [30]. The key parameter required for the above is 𝝅, or 𝑃(𝐻\u0b34). Kohavi, Deng, and Vermeer [14] provided a table with seven success rate estimates (1- 𝝅) that were reported in the software industry, which ranged from 8% to 33% with a median and mode of 10%. Plugging these into the above formula results in an FPR of 22% for the median and mode success rate of 10%, industry standard two- tailed alpha of 0.05 equivalent to one-tailed 0.025, and 80% power (𝜋= 0.9,𝛼= 0.025,𝛽= 0.2). This is a much higher rate than people intuitively think of when they hear statistically significant 2 We refer to a positive result as an improvement in the desired direction, which is usually larger (e.g., conversion, revenue), but may be smaller (e.g., faster time). False Positives in A/B Tests KDD ’24, August 25-29, 2024, Barcelona, Spain improvement. For companies that use 𝛼=0.10 as their threshold for statistical significance, or equivalently use 𝛼=0.05 with a one- tailed test for the improvement tail (e.g. Optimizely [31], Analytics Toolkit [32], Booking.com [33], Expedia), the FPR for 10% success rate is a 36%. Over one third of the statistically significant results showing improvement, which we want to celebrate, are likely to be false positives! To provide intuition about why the FPR is so high when the success rate is low, we will use the data reported by Optimizely [34] of 12% win rate across 127,000 experiments. As we will show later in the paper in Section 4.4, the estimated true success rate is 9.3%, in line with the 10% median and mode of Table 2 in Kohavi, Deng, and Vermeer [14]. Looking at Figure 1, the dot-pattern (also green if viewed in color) in the first row represents the 9.3% success rate, that is, true effects that should be statistically significant given our sample size with 80% power. Of these, 80% will be identified as statistically significant, so 80%*9.3%=7.4% are denoted by a plus in the first row. Of the remaining 90.7% null effects, 5% will be statistically significant and positive, so 4.5% of the A/B tests will show a statistically significant result: a false positive. These are denoted by a plus in the second row. Of the ~12% wins (7.4%+4.5% depicted by pluses), 4.5% are false positives, so 4.5%/(4.5% + 7.4%) = 37.8%. This surprisingly high false positive is often referred to as the base rate fallacy [35].',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5083
cosine_accuracy@3	0.7333
cosine_accuracy@5	0.8333
cosine_accuracy@10	0.9
cosine_precision@1	0.5083
cosine_precision@3	0.325
cosine_precision@5	0.225
cosine_precision@10	0.1292
cosine_recall@1	0.3471
cosine_recall@3	0.6194
cosine_recall@5	0.7114
cosine_recall@10	0.8056
cosine_ndcg@10	0.6457
cosine_mrr@10	0.6401
cosine_map@100	0.5788

Training Details

Training Dataset

Unnamed Dataset

Size: 428 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 428 samples:
sentence_0 sentence_1
type string string
details
min: 10 tokens
mean: 37.9 tokens
max: 78 tokens
min: 75 tokens
mean: 502.82 tokens
max: 512 tokens

Samples:

sentence_0	sentence_1
`How do the pitfalls identified in online A/B testing, such as Simpson’s paradox and misuse of standard statistical formulas, relate to the ongoing debate between Bayesian methods and Frequentist approaches in interpreting A/B test results?`	<7-hop>[object Object][object Object]in control, successes in treatment) to probabilities using non-informative priors, then I find the Bayesian exercise losing much of the promise. Worse, the online Bayesian A/B calculators not only require fewer parameters than FPR does, but the “Chance to beat Control” seems highly exaggerated. Appendix Some additional references to the A/B Bayesian vs. A/B Frequentists. 1. Economic Nobel prize winner Guido Imbens (2021) wrote: In the end, I do not see the advantages of Bayes factors over p-values as sufficient to convince researchers to adopt this technology more widely. 2. Bayes and Frequentist by Matt Gershoff (Oct 2022), part of the Build vs. Buy series (see intro deck and last deck with pointers). 3. Philosophy and the practice of Bayesian Statistics (2013) - great point about the need to check models, not just average 4. Nonsensical Bayesian Statistics in A/B Testing by Georgi Georgiev, author of Statistical Methods in Online A/B Testing 5. My post Multi-Armed bandits, T...
`how multiVariable testing (MVT) help speed up testing many factors at once and what experimentation infrastructure requirements make server-side assignment best for running complex MVTs on large sites?`	<2-hop>[object Object][object Object]4 MultiVariable Testing1 An experiment that includes more than one factor is often called a MultiVariable test (MVT) (Alt and Usborne 2005). For example, consider testing ﬁve factors on the MSN homepage in a single experiment. A screenshot of the MSN homepage showing the control for each of these factors is given in Fig.8. 1 This is also known as Multivariate testing. We use the term MultiVariable Testing for two reasons. These tests were ﬁrst called MultiVariable Tests in 1996 in an article in Forbes (Koselka 1996) referring to designed experiments in areas including sales and marketing. In addition, these tests are part of the statistical literature in the Design of Experiments ﬁeld. There is a separate ﬁeld of statistics known as multivariate statistics that does not deal with this topic so using the term multivariate could be a source of confusion. 123 Controlled experiments on the web 159 Factor Control Treatment F1 Shopping module as above Add Offers module below F2 Shop...
`How Figure 4.2 help manage variant assignment and system parameters in experiment platform?`	and its attributes (e.g., country, language, OS, platform), which experiment and variant combinations is that request assigned to? This assignment is based on the experiment specification and a pseudo-random hash of an ID, that is, f(ID). In most cases, to ensure the assignment is consistent for a user, a user ID is used. Variant assignment must also be independent, in that knowing the variant assignment of one user should not tell us anything about variant assignment for a different user. We discuss this in more depth in Chapter 14 . In this chapter, we assume user is the randomization unit. Production code, system parameters and values : Now that you have variant assignment and definitions, how do you ensure that the user receives the appropriate experience: how do you manage different production code and which system parameters should change to what values? This interface (or interfaces) is represented as the Variant Assignment Service in Figure 4.2 , and can return either just the ...

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 100
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 100
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
tp_size: 0
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss	cosine_ndcg@10
1.0	27	-	0.4217
1.8519	50	-	0.5487
2.0	54	-	0.5525
3.0	81	-	0.5851
3.7037	100	-	0.6000
4.0	108	-	0.6019
5.0	135	-	0.6160
5.5556	150	-	0.6255
6.0	162	-	0.6513
7.0	189	-	0.6403
7.4074	200	-	0.6306
8.0	216	-	0.6450
9.0	243	-	0.6455
9.2593	250	-	0.6489
10.0	270	-	0.6355
11.0	297	-	0.6619
11.1111	300	-	0.6650
12.0	324	-	0.6636
12.9630	350	-	0.6906
13.0	351	-	0.6869
14.0	378	-	0.6771
14.8148	400	-	0.6541
15.0	405	-	0.6537
16.0	432	-	0.6485
16.6667	450	-	0.6619
17.0	459	-	0.6334
18.0	486	-	0.6698
18.5185	500	2.6848	0.6645
19.0	513	-	0.6580
20.0	540	-	0.6888
20.3704	550	-	0.6676
21.0	567	-	0.6591
22.0	594	-	0.6558
22.2222	600	-	0.6554
23.0	621	-	0.6476
24.0	648	-	0.6580
24.0741	650	-	0.6560
25.0	675	-	0.6488
25.9259	700	-	0.6206
26.0	702	-	0.6033
27.0	729	-	0.6471
27.7778	750	-	0.6293
28.0	756	-	0.6346
29.0	783	-	0.6406
29.6296	800	-	0.6424
30.0	810	-	0.6234
31.0	837	-	0.6765
31.4815	850	-	0.6561
32.0	864	-	0.6562
33.0	891	-	0.6539
33.3333	900	-	0.6569
34.0	918	-	0.6462
35.0	945	-	0.6724
35.1852	950	-	0.6626
36.0	972	-	0.6280
37.0	999	-	0.6561
37.0370	1000	1.0045	0.6534
38.0	1026	-	0.6570
38.8889	1050	-	0.6650
39.0	1053	-	0.6516
40.0	1080	-	0.6562
40.7407	1100	-	0.6778
41.0	1107	-	0.6798
42.0	1134	-	0.6922
42.5926	1150	-	0.6902
43.0	1161	-	0.6775
44.0	1188	-	0.6663
44.4444	1200	-	0.6730
45.0	1215	-	0.6807
46.0	1242	-	0.6674
46.2963	1250	-	0.6657
47.0	1269	-	0.6648
48.0	1296	-	0.6716
48.1481	1300	-	0.6817
49.0	1323	-	0.6594
50.0	1350	-	0.6611
51.0	1377	-	0.6797
51.8519	1400	-	0.6858
52.0	1404	-	0.6828
53.0	1431	-	0.6836
53.7037	1450	-	0.6710
54.0	1458	-	0.6674
55.0	1485	-	0.6598
55.5556	1500	0.8341	0.6619
56.0	1512	-	0.6625
57.0	1539	-	0.6686
57.4074	1550	-	0.6650
58.0	1566	-	0.6214
59.0	1593	-	0.6366
59.2593	1600	-	0.6399
60.0	1620	-	0.6493
61.0	1647	-	0.6358
61.1111	1650	-	0.6326
62.0	1674	-	0.6171
62.9630	1700	-	0.6229
63.0	1701	-	0.6242
64.0	1728	-	0.6658
64.8148	1750	-	0.6622
65.0	1755	-	0.6555
66.0	1782	-	0.6286
66.6667	1800	-	0.6524
67.0	1809	-	0.6421
68.0	1836	-	0.6324
68.5185	1850	-	0.6479
69.0	1863	-	0.6443
70.0	1890	-	0.6260
70.3704	1900	-	0.6440
71.0	1917	-	0.6390
72.0	1944	-	0.6558
72.2222	1950	-	0.6563
73.0	1971	-	0.6455
74.0	1998	-	0.6422
74.0741	2000	0.6258	0.6507
75.0	2025	-	0.6504
75.9259	2050	-	0.6493
76.0	2052	-	0.6493
77.0	2079	-	0.6546
77.7778	2100	-	0.6430
78.0	2106	-	0.6443
79.0	2133	-	0.6432
79.6296	2150	-	0.6427
80.0	2160	-	0.6467
81.0	2187	-	0.6567
81.4815	2200	-	0.6529
82.0	2214	-	0.6522
83.0	2241	-	0.6487
83.3333	2250	-	0.6444
84.0	2268	-	0.6374
85.0	2295	-	0.6441
85.1852	2300	-	0.6439
86.0	2322	-	0.6378
87.0	2349	-	0.6441
87.0370	2350	-	0.6439
88.0	2376	-	0.6470
88.8889	2400	-	0.6519
89.0	2403	-	0.6451
90.0	2430	-	0.6461
90.7407	2450	-	0.6464
91.0	2457	-	0.6451
92.0	2484	-	0.6396
92.5926	2500	0.5699	0.6425
93.0	2511	-	0.6481
94.0	2538	-	0.6449
94.4444	2550	-	0.6450
95.0	2565	-	0.6452
96.0	2592	-	0.6457
96.2963	2600	-	0.6457
97.0	2619	-	0.6457
98.0	2646	-	0.6457
98.1481	2650	-	0.6457
99.0	2673	-	0.6457
100.0	2700	-	0.6457

Framework Versions

Python: 3.11.12
Sentence Transformers: 4.1.0
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

bibtex

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

bibtex

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

bibtex

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

	sentence_0	sentence_1
type	string	string
details	min: 10 tokens mean: 37.9 tokens max: 78 tokens	min: 75 tokens mean: 502.82 tokens max: 512 tokens