praphul555/ohai_gte_qwen_1.5b_instruct

SentenceTransformer based on Alibaba-NLP/gte-Qwen2-1.5B-instruct

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-Qwen2-1.5B-instruct. It maps sentences & paragraphs to a 1536-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: Alibaba-NLP/gte-Qwen2-1.5B-instruct
• Maximum Sequence Length: 32768 tokens
• Output Dimensionality: 1536 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': 32768, 'do_lower_case': False, 'architecture': 'PeftModelForFeatureExtraction'})
  (1): Pooling({'word_embedding_dimension': 1536, 'pooling_mode_cls_token': False, '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': True, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("praphul555/ohai_gte_qwen_1.5b_instruct")
# Run inference
queries = [
    "\u003cuser\u003e Hi, I need to cancel a test.\n\u003cassistant\u003e Of course, which test needs cancellation?\n\u003cuser\u003e The reflex lactic acid that we ordered.\n\u003cassistant\u003e Got it, I\u0027ll cancel it.\n\u003cuser\u003e Perfect, cancel it now.",
]
documents = [
    'Reflex Lactic Acid w/ Reflex, Plasma',
    'pt may return to room in 30 min if vital signs stable',
    'BH Social Services Assessment',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1536] [3, 1536]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.7656,  0.0259, -0.0052]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

• Dataset: ir-val
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7729
cosine_accuracy@3	0.9492
cosine_accuracy@5	0.9671
cosine_accuracy@10	0.9777
cosine_precision@1	0.7729
cosine_precision@3	0.3164
cosine_precision@5	0.1934
cosine_precision@10	0.0978
cosine_recall@1	0.7729
cosine_recall@3	0.9492
cosine_recall@5	0.9671
cosine_recall@10	0.9777
cosine_ndcg@10	0.8903
cosine_mrr@10	0.8606
cosine_map@100	0.861

Training Details

Training Dataset

Unnamed Dataset

• Size: 204,376 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 2 tokens mean: 20.11 tokens max: 71 tokens	min: 2 tokens mean: 13.66 tokens max: 59 tokens

• Samples:

  sentence_0	sentence_1
  Please renew the calcium gluconate tabs.	calcium gluconate (calcium gluconate 500 mg oral tablet)
  r	Measured Weight
  Order celiac antibodies tTG IgA and total IgA w/ reflex test.	Celiac Antibodies tTG IgA + Total IgA w/Rflx to tTG IgG and DGP IgG

• Loss: main.LoggingMNR with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• fp16: True
• 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: 64
• per_device_eval_batch_size: 64
• 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: 3
• 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: True
• 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}
• 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
• hub_revision: None
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	ir-val_cosine_ndcg@10
0.0063	10	-	0.7871
0.0125	20	-	0.7863
0.0188	30	-	0.7846
0.0250	40	-	0.7848
0.0313	50	-	0.7875
0.0376	60	-	0.7887
0.0438	70	-	0.7912
0.0501	80	-	0.7922
0.0564	90	-	0.7989
0.0626	100	-	0.8035
0.0689	110	-	0.8112
0.0751	120	-	0.8138
0.0814	130	-	0.8232
0.0877	140	-	0.8265
0.0939	150	-	0.8310
0.1002	160	-	0.8340
0.1064	170	-	0.8402
0.1127	180	-	0.8442
0.1190	190	-	0.8453
0.1252	200	-	0.8469
0.1315	210	-	0.8498
0.1378	220	-	0.8500
0.1440	230	-	0.8502
0.1503	240	-	0.8537
0.1565	250	-	0.8544
0.1628	260	-	0.8544
0.1691	270	-	0.8562
0.1753	280	-	0.8560
0.1816	290	-	0.8572
0.1879	300	-	0.8597
0.1941	310	-	0.8617
0.2004	320	-	0.8621
0.2066	330	-	0.8624
0.2129	340	-	0.8638
0.2192	350	-	0.8631
0.2254	360	-	0.8628
0.2317	370	-	0.8632
0.2379	380	-	0.8678
0.2442	390	-	0.8653
0.2505	400	-	0.8655
0.2567	410	-	0.8671
0.2630	420	-	0.8668
0.2693	430	-	0.8674
0.2755	440	-	0.8675
0.2818	450	-	0.8678
0.2880	460	-	0.8675
0.2943	470	-	0.8679
0.3006	480	-	0.8685
0.3068	490	-	0.8674
0.3131	500	0.3129	0.8686
0.3193	510	-	0.8698
0.3256	520	-	0.8695
0.3319	530	-	0.8693
0.3381	540	-	0.8713
0.3444	550	-	0.8707
0.3507	560	-	0.8713
0.3569	570	-	0.8692
0.3632	580	-	0.8716
0.3694	590	-	0.8728
0.3757	600	-	0.8716
0.3820	610	-	0.8747
0.3882	620	-	0.8730
0.3945	630	-	0.8736
0.4008	640	-	0.8744
0.4070	650	-	0.8746
0.4133	660	-	0.8751
0.4195	670	-	0.8746
0.4258	680	-	0.8727
0.4321	690	-	0.8735
0.4383	700	-	0.8737
0.4446	710	-	0.8726
0.4508	720	-	0.8714
0.4571	730	-	0.8735
0.4634	740	-	0.8735
0.4696	750	-	0.8719
0.4759	760	-	0.8721
0.4822	770	-	0.8734
0.4884	780	-	0.8729
0.4947	790	-	0.8732
0.5009	800	-	0.8739
0.5072	810	-	0.8731
0.5135	820	-	0.8740
0.5197	830	-	0.8723
0.5260	840	-	0.8715
0.5322	850	-	0.8742
0.5385	860	-	0.8738
0.5448	870	-	0.8742
0.5510	880	-	0.8727
0.5573	890	-	0.8718
0.5636	900	-	0.8735
0.5698	910	-	0.8747
0.5761	920	-	0.8743
0.5823	930	-	0.8725
0.5886	940	-	0.8741
0.5949	950	-	0.8726
0.6011	960	-	0.8724
0.6074	970	-	0.8740
0.6137	980	-	0.8751
0.6199	990	-	0.8751
0.6262	1000	0.1567	0.8760
0.6324	1010	-	0.8745
0.6387	1020	-	0.8729
0.6450	1030	-	0.8737
0.6512	1040	-	0.8778
0.6575	1050	-	0.8771
0.6637	1060	-	0.8765
0.6700	1070	-	0.8787
0.6763	1080	-	0.8780
0.6825	1090	-	0.8775
0.6888	1100	-	0.8761
0.6951	1110	-	0.8762
0.7013	1120	-	0.8770
0.7076	1130	-	0.8768
0.7138	1140	-	0.8778
0.7201	1150	-	0.8770
0.7264	1160	-	0.8777
0.7326	1170	-	0.8792
0.7389	1180	-	0.8796
0.7451	1190	-	0.8793
0.7514	1200	-	0.8795
0.7577	1210	-	0.8794
0.7639	1220	-	0.8770
0.7702	1230	-	0.8771
0.7765	1240	-	0.8770
0.7827	1250	-	0.8766
0.7890	1260	-	0.8772
0.7952	1270	-	0.8780
0.8015	1280	-	0.8796
0.8078	1290	-	0.8787
0.8140	1300	-	0.8793
0.8203	1310	-	0.8784
0.8265	1320	-	0.8794
0.8328	1330	-	0.8774
0.8391	1340	-	0.8805
0.8453	1350	-	0.8807
0.8516	1360	-	0.8793
0.8579	1370	-	0.8805
0.8641	1380	-	0.8792
0.8704	1390	-	0.8799
0.8766	1400	-	0.8789
0.8829	1410	-	0.8789
0.8892	1420	-	0.8805
0.8954	1430	-	0.8792
0.9017	1440	-	0.8822
0.9080	1450	-	0.8797
0.9142	1460	-	0.8793
0.9205	1470	-	0.8796
0.9267	1480	-	0.8791
0.9330	1490	-	0.8802
0.9393	1500	0.147	0.8804
0.9455	1510	-	0.8806
0.9518	1520	-	0.8786
0.9580	1530	-	0.8794
0.9643	1540	-	0.8799
0.9706	1550	-	0.8812
0.9768	1560	-	0.8802
0.9831	1570	-	0.8808
0.9894	1580	-	0.8808
0.9956	1590	-	0.8805
1.0	1597	-	0.8805
1.0019	1600	-	0.8806
1.0081	1610	-	0.8806
1.0144	1620	-	0.8804
1.0207	1630	-	0.8791
1.0269	1640	-	0.8804
1.0332	1650	-	0.8802
1.0394	1660	-	0.8823
1.0457	1670	-	0.8805
1.0520	1680	-	0.8808
1.0582	1690	-	0.8824
1.0645	1700	-	0.8801
1.0708	1710	-	0.8810
1.0770	1720	-	0.8812
1.0833	1730	-	0.8817
1.0895	1740	-	0.8812
1.0958	1750	-	0.8806
1.1021	1760	-	0.8820
1.1083	1770	-	0.8826
1.1146	1780	-	0.8825
1.1209	1790	-	0.8800
1.1271	1800	-	0.8805
1.1334	1810	-	0.8801
1.1396	1820	-	0.8819
1.1459	1830	-	0.8810
1.1522	1840	-	0.8800
1.1584	1850	-	0.8813
1.1647	1860	-	0.8817
1.1709	1870	-	0.8801
1.1772	1880	-	0.8809
1.1835	1890	-	0.8821
1.1897	1900	-	0.8838
1.1960	1910	-	0.8819
1.2023	1920	-	0.8821
1.2085	1930	-	0.8826
1.2148	1940	-	0.8841
1.2210	1950	-	0.8845
1.2273	1960	-	0.8829
1.2336	1970	-	0.8817
1.2398	1980	-	0.8833
1.2461	1990	-	0.8861
1.2523	2000	0.1343	0.8825
1.2586	2010	-	0.8821
1.2649	2020	-	0.8840
1.2711	2030	-	0.8836
1.2774	2040	-	0.8832
1.2837	2050	-	0.8806
1.2899	2060	-	0.8820
1.2962	2070	-	0.8805
1.3024	2080	-	0.8818
1.3087	2090	-	0.8834
1.3150	2100	-	0.8819
1.3212	2110	-	0.8854
1.3275	2120	-	0.8824
1.3338	2130	-	0.8811
1.3400	2140	-	0.8823
1.3463	2150	-	0.8810
1.3525	2160	-	0.8819
1.3588	2170	-	0.8816
1.3651	2180	-	0.8828
1.3713	2190	-	0.8828
1.3776	2200	-	0.8850
1.3838	2210	-	0.8833
1.3901	2220	-	0.8849
1.3964	2230	-	0.8834
1.4026	2240	-	0.8815
1.4089	2250	-	0.8821
1.4152	2260	-	0.8830
1.4214	2270	-	0.8822
1.4277	2280	-	0.8809
1.4339	2290	-	0.8831
1.4402	2300	-	0.8838
1.4465	2310	-	0.8840
1.4527	2320	-	0.8836
1.4590	2330	-	0.8827
1.4652	2340	-	0.8833
1.4715	2350	-	0.8836
1.4778	2360	-	0.8823
1.4840	2370	-	0.8823
1.4903	2380	-	0.8829
1.4966	2390	-	0.8823
1.5028	2400	-	0.8826
1.5091	2410	-	0.8839
1.5153	2420	-	0.8833
1.5216	2430	-	0.8830
1.5279	2440	-	0.8829
1.5341	2450	-	0.8828
1.5404	2460	-	0.8849
1.5466	2470	-	0.8827
1.5529	2480	-	0.8833
1.5592	2490	-	0.8832
1.5654	2500	0.1315	0.8841
1.5717	2510	-	0.8835
1.5780	2520	-	0.8839
1.5842	2530	-	0.8834
1.5905	2540	-	0.8847
1.5967	2550	-	0.8829
1.6030	2560	-	0.8815
1.6093	2570	-	0.8815
1.6155	2580	-	0.8815
1.6218	2590	-	0.8828
1.6281	2600	-	0.8839
1.6343	2610	-	0.8831
1.6406	2620	-	0.8848
1.6468	2630	-	0.8840
1.6531	2640	-	0.8821
1.6594	2650	-	0.8849
1.6656	2660	-	0.8833
1.6719	2670	-	0.8824
1.6781	2680	-	0.8826
1.6844	2690	-	0.8819
1.6907	2700	-	0.8831
1.6969	2710	-	0.8831
1.7032	2720	-	0.8845
1.7095	2730	-	0.8820
1.7157	2740	-	0.8814
1.7220	2750	-	0.8813
1.7282	2760	-	0.8830
1.7345	2770	-	0.8838
1.7408	2780	-	0.8833
1.7470	2790	-	0.8825
1.7533	2800	-	0.8814
1.7595	2810	-	0.8821
1.7658	2820	-	0.8817
1.7721	2830	-	0.8829
1.7783	2840	-	0.8837
1.7846	2850	-	0.8840
1.7909	2860	-	0.8838
1.7971	2870	-	0.8842
1.8034	2880	-	0.8867
1.8096	2890	-	0.8865
1.8159	2900	-	0.8863
1.8222	2910	-	0.8857
1.8284	2920	-	0.8846
1.8347	2930	-	0.8842
1.8410	2940	-	0.8860
1.8472	2950	-	0.8857
1.8535	2960	-	0.8851
1.8597	2970	-	0.8852
1.8660	2980	-	0.8852
1.8723	2990	-	0.8862
1.8785	3000	0.1249	0.8850
1.8848	3010	-	0.8843
1.8910	3020	-	0.8845
1.8973	3030	-	0.8862
1.9036	3040	-	0.8862
1.9098	3050	-	0.8848
1.9161	3060	-	0.8847
1.9224	3070	-	0.8865
1.9286	3080	-	0.8857
1.9349	3090	-	0.8874
1.9411	3100	-	0.8855
1.9474	3110	-	0.8873
1.9537	3120	-	0.8872
1.9599	3130	-	0.8856
1.9662	3140	-	0.8857
1.9724	3150	-	0.8862
1.9787	3160	-	0.8861
1.9850	3170	-	0.8861
1.9912	3180	-	0.8872
1.9975	3190	-	0.8869
2.0	3194	-	0.8850
2.0038	3200	-	0.8865
2.0100	3210	-	0.8854
2.0163	3220	-	0.8865
2.0225	3230	-	0.8847
2.0288	3240	-	0.8860
2.0351	3250	-	0.8883
2.0413	3260	-	0.8868
2.0476	3270	-	0.8842
2.0539	3280	-	0.8829
2.0601	3290	-	0.8830
2.0664	3300	-	0.8847
2.0726	3310	-	0.8840
2.0789	3320	-	0.8866
2.0852	3330	-	0.8845
2.0914	3340	-	0.8852
2.0977	3350	-	0.8864
2.1039	3360	-	0.8873
2.1102	3370	-	0.8877
2.1165	3380	-	0.8861
2.1227	3390	-	0.8865
2.1290	3400	-	0.8857
2.1353	3410	-	0.8857
2.1415	3420	-	0.8873
2.1478	3430	-	0.8866
2.1540	3440	-	0.8851
2.1603	3450	-	0.8865
2.1666	3460	-	0.8850
2.1728	3470	-	0.8837
2.1791	3480	-	0.8869
2.1853	3490	-	0.8861
2.1916	3500	0.1171	0.8861
2.1979	3510	-	0.8862
2.2041	3520	-	0.8889
2.2104	3530	-	0.8851
2.2167	3540	-	0.8878
2.2229	3550	-	0.8868
2.2292	3560	-	0.8858
2.2354	3570	-	0.8859
2.2417	3580	-	0.8844
2.2480	3590	-	0.8876
2.2542	3600	-	0.8881
2.2605	3610	-	0.8872
2.2668	3620	-	0.8846
2.2730	3630	-	0.8848
2.2793	3640	-	0.8846
2.2855	3650	-	0.8860
2.2918	3660	-	0.8864
2.2981	3670	-	0.8867
2.3043	3680	-	0.8860
2.3106	3690	-	0.8884
2.3168	3700	-	0.8881
2.3231	3710	-	0.8869
2.3294	3720	-	0.8869
2.3356	3730	-	0.8857
2.3419	3740	-	0.8866
2.3482	3750	-	0.8860
2.3544	3760	-	0.8872
2.3607	3770	-	0.8877
2.3669	3780	-	0.8887
2.3732	3790	-	0.8875
2.3795	3800	-	0.8883
2.3857	3810	-	0.8875
2.3920	3820	-	0.8879
2.3982	3830	-	0.8853
2.4045	3840	-	0.8877
2.4108	3850	-	0.8867
2.4170	3860	-	0.8879
2.4233	3870	-	0.8883
2.4296	3880	-	0.8897
2.4358	3890	-	0.8898
2.4421	3900	-	0.8865
2.4483	3910	-	0.8867
2.4546	3920	-	0.8866
2.4609	3930	-	0.8868
2.4671	3940	-	0.8866
2.4734	3950	-	0.8854
2.4796	3960	-	0.8884
2.4859	3970	-	0.8855
2.4922	3980	-	0.8858
2.4984	3990	-	0.8854
2.5047	4000	0.117	0.8861
2.5110	4010	-	0.8865
2.5172	4020	-	0.8855
2.5235	4030	-	0.8863
2.5297	4040	-	0.8864
2.5360	4050	-	0.8898
2.5423	4060	-	0.8890
2.5485	4070	-	0.8893
2.5548	4080	-	0.8902
2.5611	4090	-	0.8886
2.5673	4100	-	0.8882
2.5736	4110	-	0.8884
2.5798	4120	-	0.8876
2.5861	4130	-	0.8877
2.5924	4140	-	0.8879
2.5986	4150	-	0.8871
2.6049	4160	-	0.8881
2.6111	4170	-	0.8870
2.6174	4180	-	0.8883
2.6237	4190	-	0.8878
2.6299	4200	-	0.8890
2.6362	4210	-	0.8878
2.6425	4220	-	0.8897
2.6487	4230	-	0.8864
2.6550	4240	-	0.8871
2.6612	4250	-	0.8876
2.6675	4260	-	0.8856
2.6738	4270	-	0.8878
2.6800	4280	-	0.8884
2.6863	4290	-	0.8891
2.6925	4300	-	0.8891
2.6988	4310	-	0.8880
2.7051	4320	-	0.8865
2.7113	4330	-	0.8877
2.7176	4340	-	0.8859
2.7239	4350	-	0.8861
2.7301	4360	-	0.8853
2.7364	4370	-	0.8851
2.7426	4380	-	0.8868
2.7489	4390	-	0.8875
2.7552	4400	-	0.8869
2.7614	4410	-	0.8903

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.0.0
• Transformers: 4.53.1
• PyTorch: 2.6.0+cu124
• Accelerate: 1.8.1
• Datasets: 4.0.0
• Tokenizers: 0.21.2

Citation

BibTeX

Sentence Transformers

@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",
}

LoggingMNR

@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}
}