Downloads · 30 days
0
Trongnhat191/Vietnamese_embeddings
Vietnamese_embeddings is a sentence similarity model from Trongnhat191. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model finetuned from AITeamVN/VietnameseEmbedding on the datasetfullfixed dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic t…
Downloads · 30 days
0
Access
Public
Updated Sep 4, 2025
Repo size
47.4 MB
Likes
0
Public
Click a slice to open those files.
.safetensors25.2 MB · 53%
From the Hugging Face model README
This is a sentence-transformers model finetuned from AITeamVN/Vietnamese_Embedding on the dataset_full_fixed dataset. 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.
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
(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()
)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("Vietnamese_embeddings")
# Run inference
queries = [
"B\u1ea1n\r\nB\u00e1 \u0110\u1ea1o th\u00e2n m\u1ebfn! \u0102n\r\nd\u01b0a chu\u1ed9t c\u00f3 m\u1ed9t s\u1ed1 t\u00e1c d\u1ee5ng nh\u01b0 ch\u1eefa ph\u00f9, gi\u00fap l\u1ee3i ti\u1ec3u, c\u00f3 t\u00e1c d\u1ee5ng thanh\r\nnhi\u1ec7t, gi\u1ea3i kh\u00e1t. Tuy nhi\u00ean, theo \u0110\u00f4ng y, d\u01b0a chu\u1ed9t c\u00f3 t\u00ednh l\u1ea1nh, n\u1ebfu \u0103n nhi\u1ec1u\r\ns\u1ebd sinh \u0111i ti\u1ec3u nhi\u1ec1u, th\u1eadm ch\u00ed ng\u01b0\u1eddi th\u1eadn y\u1ebfu c\u00f3 th\u1ec3 hay b\u1ecb v\u00e3i ti\u1ec3u v\u00e0 d\u1eabn\r\n\u0111\u1ebfn . Do v\u1eady, ng\u01b0\u1eddi b\u1ecb l\u1ea1nh b\u1ee5ng, \u1ea3nh h\u01b0\u1edfng ch\u1ee9c n\u0103ng th\u1eadn th\u00ec kh\u00f4ng\r\nn\u00ean \u0103n d\u01b0a chu\u1ed9t. C\u00f2n\r\nng\u01b0\u1eddi b\u00ecnh th\u01b0\u1eddng c\u0169ng kh\u00f4ng n\u00ean s\u1eed d\u1ee5ng qu\u00e1 nhi\u1ec1u d\u01b0a chu\u1ed9t trong th\u1eddi gian\r\nd\u00e0i, l\u00e0m ch\u1ee9c n\u0103ng th\u1eadn suy gi\u1ea3m. M\u1ed7i ng\u00e0y ch\u1ec9 n\u00ean \u0103n 1 - 2 qu\u1ea3 d\u01b0a chu\u1ed9t,\r\nkh\u00f4ng n\u00ean \u0103n v\u1edbi l\u1ea1c s\u1ebd sinh \u0111\u1ea7y h\u01a1i, kh\u00f3 ti\u00eau. Alobacsi.n Theo Ki\u1ebfn th\u1ee9c",
]
documents = [
'Thưa bác sĩ,\r\n\r\nTôi rất thích ăn dưa chuột, ngày nào tôi cũng ăn. Nhưng có người nói ăn nhiều dưa chuột có thể bị liệt dương, xin hỏi có đúng không? Tôi tưởng ăn dưa chuột thì tốt cho chuyện sinh lý. (Nguyễn Bá Đạo - Bắc Giang)',
'Hỗn dịch uống A.T Ibuprofen Syrup 100mg An Thiên giảm đau, kháng viêm (60ml)',
'Viên nén Natidof 8 SPM điều trị thoái hóa đốt sống, vẹo cổ, đau lưng (3 vỉ x 10 viên)',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.6852, -0.0705, -0.0483]])
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
dim_768{
"truncate_dim": 768
}
| Metric | Value |
|---|---|
| cosine_accuracy@1 | 0.7126 |
| cosine_accuracy@3 | 0.8298 |
| cosine_accuracy@5 | 0.8678 |
| cosine_accuracy@10 | 0.906 |
| cosine_precision@1 | 0.7126 |
| cosine_precision@3 | 0.2766 |
| cosine_precision@5 | 0.1736 |
| cosine_precision@10 | 0.0906 |
| cosine_recall@1 | 0.7126 |
| cosine_recall@3 | 0.8298 |
| cosine_recall@5 | 0.8678 |
| cosine_recall@10 | 0.906 |
| cosine_ndcg@10 | 0.8096 |
| cosine_mrr@10 | 0.7787 |
| cosine_map@100 | 0.7824 |
| positive | query | |
|---|---|---|
| type | string | string |
| details | <ul><li>min: 25 tokens</li><li>mean: 249.72 tokens</li><li>max: 1968 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 77.99 tokens</li><li>max: 576 tokens</li></ul> |
| positive | query |
|---|---|
| <code>Chào bạn, Có 2 nhóm nguyên nhân chính làm tăng Ferritin máu , có hoặc không có ứ đọng sắt ở các mô. Bệnh có ứ đọng sắt tiên phát phổ biến nhất là bệnh ứ sắt mô di truyền (hemochromatosis) do đột biến gen HFE, gen tham gia vào điều hòa hấp thu sắt ở ruột non. Bệnh hay gặp ở người da trắng và rất hiếm gặp ở người châu Á. Ở Việt Nam, bệnh tăng Ferritin có ứ sắt mô thứ phát hay gặp nhất là bệnh beta Thalassemia. Nguyên nhân tăng Ferritin không có ứ đọng sắt ở các mô, hay gặp ở người châu Á gồm viêm gan virus mạn tính, rượu hoặc bệnh gan do rượu và không do rượu, bệnh đái tháo đường hoặc hội chứng biến dưỡng. Ngoài ra tăng Ferritin máu hay gặp ở người mắc các bệnh mạn tính như viêm đa khớp dạng thấp, bệnh tự miễn, ungthư và suy thận mạn. Như vậy, trường hợp này có thể tăng Ferritine di truyền hoặc thứ phát gây ra tăng men gan, nhưng cũng có thể viêm gan mạn là nguyên nhân làm cho Ferritine tăng cao. Bạn nên đưa chồng đến tái khám chuyên khoa Viêm Gan để bác sĩ xem xét làm thêm xét nghiệm là...</code> | <code>Bác sĩ cho em hỏi, |
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
eval_strategy: epochper_device_train_batch_size: 2per_device_eval_batch_size: 1learning_rate: 1e-06num_train_epochs: 1lr_scheduler_type: constant_with_warmupwarmup_ratio: 0.1fp16: Truetf32: Falseload_best_model_at_end: Truebatch_sampler: no_duplicatesoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: epochprediction_loss_only: Trueper_device_train_batch_size: 2per_device_eval_batch_size: 1per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 1e-06weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 1max_steps: -1lr_scheduler_type: constant_with_warmuplr_scheduler_kwargs: {}warmup_ratio: 0.1warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Falselocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Trueignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torch_fusedoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 |
|---|---|---|---|
| 0.0046 | 100 | 0.0471 | - |
| 0.0091 | 200 | 0.0258 | - |
| 0.0137 | 300 | 0.0347 | - |
| 0.0183 | 400 | 0.0301 | - |
| 0.0228 | 500 | 0.0301 | - |
| 0.0274 | 600 | 0.0308 | - |
| 0.0320 | 700 | 0.0199 | - |
| 0.0365 | 800 | 0.037 | - |
| 0.0411 | 900 | 0.0286 | - |
| 0.0457 | 1000 | 0.0383 | - |
| 0.0502 | 1100 | 0.0222 | - |
| 0.0548 | 1200 | 0.0193 | - |
| 0.0594 | 1300 | 0.0165 | - |
| 0.0639 | 1400 | 0.0281 | - |
| 0.0685 | 1500 | 0.0301 | - |
| 0.0731 | 1600 | 0.0207 | - |
| 0.0776 | 1700 | 0.0235 | - |
| 0.0822 | 1800 | 0.0159 | - |
| 0.0868 | 1900 | 0.0213 | - |
| 0.0913 | 2000 | 0.0141 | - |
| 0.0959 | 2100 | 0.0126 | - |
| 0.1004 | 2200 | 0.0195 | - |
| 0.1050 | 2300 | 0.0104 | - |
| 0.1096 | 2400 | 0.0138 | - |
| 0.1141 | 2500 | 0.0176 | - |
| 0.1187 | 2600 | 0.0148 | - |
| 0.1233 | 2700 | 0.0188 | - |
| 0.1278 | 2800 | 0.0131 | - |
| 0.1324 | 2900 | 0.0303 | - |
| 0.1370 | 3000 | 0.0151 | - |
| 0.1415 | 3100 | 0.0237 | - |
| 0.1461 | 3200 | 0.015 | - |
| 0.1507 | 3300 | 0.0058 | - |
| 0.1552 | 3400 | 0.0213 | - |
| 0.1598 | 3500 | 0.0075 | - |
| 0.1644 | 3600 | 0.0034 | - |
| 0.1689 | 3700 | 0.0131 | - |
| 0.1735 | 3800 | 0.0094 | - |
| 0.1781 | 3900 | 0.0072 | - |
| 0.1826 | 4000 | 0.0165 | - |
| 0.1872 | 4100 | 0.0106 | - |
| 0.1918 | 4200 | 0.0179 | - |
| 0.1963 | 4300 | 0.0105 | - |
| 0.2009 | 4400 | 0.006 | - |
| 0.2055 | 4500 | 0.009 | - |
| 0.2100 | 4600 | 0.0173 | - |
| 0.2146 | 4700 | 0.0103 | - |
| 0.2192 | 4800 | 0.0095 | - |
| 0.2237 | 4900 | 0.0111 | - |
| 0.2283 | 5000 | 0.0123 | - |
| 0.2329 | 5100 | 0.0034 | - |
| 0.2374 | 5200 | 0.0051 | - |
| 0.2420 | 5300 | 0.0083 | - |
| 0.2466 | 5400 | 0.009 | - |
| 0.2511 | 5500 | 0.0094 | - |
| 0.2557 | 5600 | 0.0092 | - |
| 0.2603 | 5700 | 0.0056 | - |
| 0.2648 | 5800 | 0.019 | - |
| 0.2694 | 5900 | 0.0029 | - |
| 0.2739 | 6000 | 0.0045 | - |
| 0.2785 | 6100 | 0.0087 | - |
| 0.2831 | 6200 | 0.015 | - |
| 0.2876 | 6300 | 0.0042 | - |
| 0.2922 | 6400 | 0.0019 | - |
| 0.2968 | 6500 | 0.0032 | - |
| 0.3013 | 6600 | 0.0071 | - |
| 0.3059 | 6700 | 0.0051 | - |
| 0.3105 | 6800 | 0.0079 | - |
| 0.3150 | 6900 | 0.0065 | - |
| 0.3196 | 7000 | 0.0032 | - |
| 0.3242 | 7100 | 0.0058 | - |
| 0.3287 | 7200 | 0.0031 | - |
| 0.3333 | 7300 | 0.0054 | - |
| 0.3379 | 7400 | 0.0025 | - |
| 0.3424 | 7500 | 0.0013 | - |
| 0.3470 | 7600 | 0.0145 | - |
| 0.3516 | 7700 | 0.0031 | - |
| 0.3561 | 7800 | 0.0062 | - |
| 0.3607 | 7900 | 0.0144 | - |
| 0.3653 | 8000 | 0.0117 | - |
| 0.3698 | 8100 | 0.0024 | - |
| 0.3744 | 8200 | 0.0105 | - |
| 0.3790 | 8300 | 0.0055 | - |
| 0.3835 | 8400 | 0.0078 | - |
| 0.3881 | 8500 | 0.0056 | - |
| 0.3927 | 8600 | 0.0019 | - |
| 0.3972 | 8700 | 0.0024 | - |
| 0.4018 | 8800 | 0.0044 | - |
| 0.4064 | 8900 | 0.0061 | - |
| 0.4109 | 9000 | 0.0081 | - |
| 0.4155 | 9100 | 0.0053 | - |
| 0.4201 | 9200 | 0.0059 | - |
| 0.4246 | 9300 | 0.0053 | - |
| 0.4292 | 9400 | 0.0021 | - |
| 0.4338 | 9500 | 0.0122 | - |
| 0.4383 | 9600 | 0.0038 | - |
| 0.4429 | 9700 | 0.0012 | - |
| 0.4474 | 9800 | 0.0024 | - |
| 0.4520 | 9900 | 0.0027 | - |
| 0.4566 | 10000 | 0.0257 | - |
| 0.4611 | 10100 | 0.0061 | - |
| 0.4657 | 10200 | 0.01 | - |
| 0.4703 | 10300 | 0.0025 | - |
| 0.4748 | 10400 | 0.0019 | - |
| 0.4794 | 10500 | 0.0046 | - |
| 0.4840 | 10600 | 0.0065 | - |
| 0.4885 | 10700 | 0.02 | - |
| 0.4931 | 10800 | 0.0026 | - |
| 0.4977 | 10900 | 0.0032 | - |
| 0.5022 | 11000 | 0.0043 | - |
| 0.5068 | 11100 | 0.0128 | - |
| 0.5114 | 11200 | 0.0021 | - |
| 0.5159 | 11300 | 0.0016 | - |
| 0.5205 | 11400 | 0.0131 | - |
| 0.5251 | 11500 | 0.0182 | - |
| 0.5296 | 11600 | 0.0114 | - |
| 0.5342 | 11700 | 0.0008 | - |
| 0.5388 | 11800 | 0.0044 | - |
| 0.5433 | 11900 | 0.0043 | - |
| 0.5479 | 12000 | 0.0068 | - |
| 0.5525 | 12100 | 0.0077 | - |
| 0.5570 | 12200 | 0.0036 | - |
| 0.5616 | 12300 | 0.0068 | - |
| 0.5662 | 12400 | 0.0094 | - |
| 0.5707 | 12500 | 0.0021 | - |
| 0.5753 | 12600 | 0.0011 | - |
| 0.5799 | 12700 | 0.0013 | - |
| 0.5844 | 12800 | 0.0026 | - |
| 0.5890 | 12900 | 0.0094 | - |
| 0.5936 | 13000 | 0.0026 | - |
| 0.5981 | 13100 | 0.0184 | - |
| 0.6027 | 13200 | 0.0218 | - |
| 0.6073 | 13300 | 0.0052 | - |
| 0.6118 | 13400 | 0.0184 | - |
| 0.6164 | 13500 | 0.0179 | - |
| 0.6209 | 13600 | 0.0027 | - |
| 0.6255 | 13700 | 0.0026 | - |
| 0.6301 | 13800 | 0.0016 | - |
| 0.6346 | 13900 | 0.0011 | - |
| 0.6392 | 14000 | 0.004 | - |
| 0.6438 | 14100 | 0.0019 | - |
| 0.6483 | 14200 | 0.0083 | - |
| 0.6529 | 14300 | 0.0063 | - |
| 0.6575 | 14400 | 0.0181 | - |
| 0.6620 | 14500 | 0.0026 | - |
| 0.6666 | 14600 | 0.0097 | - |
| 0.6712 | 14700 | 0.0094 | - |
| 0.6757 | 14800 | 0.0136 | - |
| 0.6803 | 14900 | 0.0011 | - |
| 0.6849 | 15000 | 0.0059 | - |
| 0.6894 | 15100 | 0.0062 | - |
| 0.6940 | 15200 | 0.0029 | - |
| 0.6986 | 15300 | 0.0054 | - |
| 0.7031 | 15400 | 0.0037 | - |
| 0.7077 | 15500 | 0.003 | - |
| 0.7123 | 15600 | 0.0019 | - |
| 0.7168 | 15700 | 0.0017 | - |
| 0.7214 | 15800 | 0.0063 | - |
| 0.7260 | 15900 | 0.0214 | - |
| 0.7305 | 16000 | 0.0007 | - |
| 0.7351 | 16100 | 0.0055 | - |
| 0.7397 | 16200 | 0.002 | - |
| 0.7442 | 16300 | 0.0014 | - |
| 0.7488 | 16400 | 0.0052 | - |
| 0.7534 | 16500 | 0.0037 | - |
| 0.7579 | 16600 | 0.0134 | - |
| 0.7625 | 16700 | 0.0106 | - |
| 0.7671 | 16800 | 0.0019 | - |
| 0.7716 | 16900 | 0.0048 | - |
| 0.7762 | 17000 | 0.0015 | - |
| 0.7808 | 17100 | 0.0064 | - |
| 0.7853 | 17200 | 0.0028 | - |
| 0.7899 | 17300 | 0.0042 | - |
| 0.7944 | 17400 | 0.0007 | - |
| 0.7990 | 17500 | 0.0033 | - |
| 0.8036 | 17600 | 0.0013 | - |
| 0.8081 | 17700 | 0.0062 | - |
| 0.8127 | 17800 | 0.0167 | - |
| 0.8173 | 17900 | 0.004 | - |
| 0.8218 | 18000 | 0.002 | - |
| 0.8264 | 18100 | 0.0042 | - |
| 0.8310 | 18200 | 0.0095 | - |
| 0.8355 | 18300 | 0.0016 | - |
| 0.8401 | 18400 | 0.0083 | - |
| 0.8447 | 18500 | 0.0011 | - |
| 0.8492 | 18600 | 0.0102 | - |
| 0.8538 | 18700 | 0.001 | - |
| 0.8584 | 18800 | 0.0028 | - |
| 0.8629 | 18900 | 0.0012 | - |
| 0.8675 | 19000 | 0.0119 | - |
| 0.8721 | 19100 | 0.0015 | - |
| 0.8766 | 19200 | 0.0023 | - |
| 0.8812 | 19300 | 0.0009 | - |
| 0.8858 | 19400 | 0.0022 | - |
| 0.8903 | 19500 | 0.0116 | - |
| 0.8949 | 19600 | 0.0119 | - |
| 0.8995 | 19700 | 0.0038 | - |
| 0.9040 | 19800 | 0.0026 | - |
| 0.9086 | 19900 | 0.0125 | - |
| 0.9132 | 20000 | 0.0008 | - |
| 0.9177 | 20100 | 0.0023 | - |
| 0.9223 | 20200 | 0.0101 | - |
| 0.9269 | 20300 | 0.0016 | - |
| 0.9314 | 20400 | 0.0075 | - |
| 0.9360 | 20500 | 0.0062 | - |
| 0.9406 | 20600 | 0.0226 | - |
| 0.9451 | 20700 | 0.0052 | - |
| 0.9497 | 20800 | 0.0034 | - |
| 0.9543 | 20900 | 0.0037 | - |
| 0.9588 | 21000 | 0.0012 | - |
| 0.9634 | 21100 | 0.0038 | - |
| 0.9679 | 21200 | 0.0013 | - |
| 0.9725 | 21300 | 0.0028 | - |
| 0.9771 | 21400 | 0.0063 | - |
| 0.9816 | 21500 | 0.0019 | - |
| 0.9862 | 21600 | 0.0173 | - |
| 0.9908 | 21700 | 0.0018 | - |
| 0.9953 | 21800 | 0.0081 | - |
| 0.9999 | 21900 | 0.0023 | - |
| 1.0 | 21902 | - | 0.8096 |
@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",
}
@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}
}
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->