PSanni/gte-modernbert-reranker-custom-max1

CrossEncoder based on Alibaba-NLP/gte-reranker-modernbert-base

This is a Cross Encoder model finetuned from Alibaba-NLP/gte-reranker-modernbert-base using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: Alibaba-NLP/gte-reranker-modernbert-base
• Maximum Sequence Length: 8192 tokens
• Number of Output Labels: 1 label

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("cross_encoder_model_id")
# Get scores for pairs of texts
pairs = [
    ['particleboard bookcase white', 'the trådfri led bulb e12 450 lumen is a white, opal globe-shaped light bulb made of polycarbonate plastic. it provides a default luminous flux of 450 lumens and has a color temperature of 2700 k, with a power consumption of 4.1 watts. this bulb is compatible with ikea smarthome products and offers adjustable white tones and wireless dimming, ideal for small lampshades. its item number is 70518179 and price is 9.99.'],
    ['particleboard bookcase white', 'the bestå tv storage combination with glass doors is a furniture piece in beige, brown, and black colors, designed to organize and display tvs and related gadgets. it measures 94 1/2x16 1/2x91 inches (240x42x231 cm) and features a blend of particleboard, fibreboard, honeycomb paper filling, paper foil, plastic edging, and tempered glass. the tv bench and frame incorporate recycled materials, while the shelves include both tempered glass and particleboard. drawer runners are made from galvanized steel with a push-open mechanism, enhanced by soft closing hinges crafted from steel and nickel-plated metal. the glass doors are composed of tempered glass with a fibreboard frame. the product supports loads up to 22 pounds (10 kg) on its drawer, 44 pounds (20 kg) on shelves, 22 pounds (10 kg) on glass shelves, and a maximum of 110 pounds (50 kg) on the top panel. it includes features for easy cleaning, requiring a wipe with a damp cloth followed by a dry cloth. its item number is 19421393 and price is 462.49.'],
    ['particleboard bookcase white', 'the metod base cabinet for sink with 2 doors in green features a solid color appearance and is constructed from wood materials. its overall dimensions are 31 inches in width, 24 inches in depth, and 31 1/2 inches in height (80 cm x 60 cm x 80 cm). the detailed measurements include a system depth of 24 inches (60 cm) and a depth of 24 1/4 inches (61.6 cm). the product includes doors made of fibreboard with acrylic paint, and the frame consists of particleboard, melamine foil, and plastic edging. the back panel is made of fibreboard with paper foil, while the front rail is made of steel with an epoxy/polyester powder coating. hinges are crafted from steel with nickel plating and feature a built-in damper for smooth operation. the cabinet is designed as part of the metod kitchen system, providing versatile design possibilities. its item number is 89557444 and price is 245.45.'],
    ['particleboard bookcase white', 'the metod corner wall cabinet with shelves is a grey, solid-colored kitchen storage unit featuring a traditional style with its bodbyn fronts and bevelled edges. constructed from wood, including fibreboard and particleboard materials, it is finished with polyurethane and acrylic paints. the cabinet measures 27x14 5/8x31 inches (68x37x80 cm) with a system depth of 14 5/8 inches (37 cm). the door is made of fibreboard with a painted finish, while the frame consists of particleboard and melamine foil, with shelving that includes plastic edging for durability. the cabinet offers functional shelving designed for neat storage. maintenance is simple with cleaning using a cloth and non-abrasive detergent. its item number is 99918695 and price is 259.09.'],
    ['particleboard bookcase white', 'the blåvingad duvet cover and pillowcase set features an ocean animals pattern in multiple colors. made from a blend of 50% cotton and 50% lyocell, it offers a soft and comfortable feel. the set is designed for a twin size, with the duvet cover measuring 218 cm by 162 cm (85 7/8 inches by 63 3/4 inches) and the pillowcase measuring 51 cm by 76 cm (20 inches by 30 inches). it has a thread count of 164 per inch². the product is machine washable and can be tumbled dry at a medium temperature, but should not be bleached or dry cleaned. maximum shrinkage is 4%. its item number is 00521076 and price is 34.99.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'particleboard bookcase white',
    [
        'the trådfri led bulb e12 450 lumen is a white, opal globe-shaped light bulb made of polycarbonate plastic. it provides a default luminous flux of 450 lumens and has a color temperature of 2700 k, with a power consumption of 4.1 watts. this bulb is compatible with ikea smarthome products and offers adjustable white tones and wireless dimming, ideal for small lampshades. its item number is 70518179 and price is 9.99.',
        'the bestå tv storage combination with glass doors is a furniture piece in beige, brown, and black colors, designed to organize and display tvs and related gadgets. it measures 94 1/2x16 1/2x91 inches (240x42x231 cm) and features a blend of particleboard, fibreboard, honeycomb paper filling, paper foil, plastic edging, and tempered glass. the tv bench and frame incorporate recycled materials, while the shelves include both tempered glass and particleboard. drawer runners are made from galvanized steel with a push-open mechanism, enhanced by soft closing hinges crafted from steel and nickel-plated metal. the glass doors are composed of tempered glass with a fibreboard frame. the product supports loads up to 22 pounds (10 kg) on its drawer, 44 pounds (20 kg) on shelves, 22 pounds (10 kg) on glass shelves, and a maximum of 110 pounds (50 kg) on the top panel. it includes features for easy cleaning, requiring a wipe with a damp cloth followed by a dry cloth. its item number is 19421393 and price is 462.49.',
        'the metod base cabinet for sink with 2 doors in green features a solid color appearance and is constructed from wood materials. its overall dimensions are 31 inches in width, 24 inches in depth, and 31 1/2 inches in height (80 cm x 60 cm x 80 cm). the detailed measurements include a system depth of 24 inches (60 cm) and a depth of 24 1/4 inches (61.6 cm). the product includes doors made of fibreboard with acrylic paint, and the frame consists of particleboard, melamine foil, and plastic edging. the back panel is made of fibreboard with paper foil, while the front rail is made of steel with an epoxy/polyester powder coating. hinges are crafted from steel with nickel plating and feature a built-in damper for smooth operation. the cabinet is designed as part of the metod kitchen system, providing versatile design possibilities. its item number is 89557444 and price is 245.45.',
        'the metod corner wall cabinet with shelves is a grey, solid-colored kitchen storage unit featuring a traditional style with its bodbyn fronts and bevelled edges. constructed from wood, including fibreboard and particleboard materials, it is finished with polyurethane and acrylic paints. the cabinet measures 27x14 5/8x31 inches (68x37x80 cm) with a system depth of 14 5/8 inches (37 cm). the door is made of fibreboard with a painted finish, while the frame consists of particleboard and melamine foil, with shelving that includes plastic edging for durability. the cabinet offers functional shelving designed for neat storage. maintenance is simple with cleaning using a cloth and non-abrasive detergent. its item number is 99918695 and price is 259.09.',
        'the blåvingad duvet cover and pillowcase set features an ocean animals pattern in multiple colors. made from a blend of 50% cotton and 50% lyocell, it offers a soft and comfortable feel. the set is designed for a twin size, with the duvet cover measuring 218 cm by 162 cm (85 7/8 inches by 63 3/4 inches) and the pillowcase measuring 51 cm by 76 cm (20 inches by 30 inches). it has a thread count of 164 per inch². the product is machine washable and can be tumbled dry at a medium temperature, but should not be bleached or dry cleaned. maximum shrinkage is 4%. its item number is 00521076 and price is 34.99.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

Unnamed Dataset

• Size: 804,721 training samples
• Columns: query, docs, and labels
• Approximate statistics based on the first 1000 samples:

  	query	docs	labels
  type	string	list	list
  details	min: 4 characters mean: 20.55 characters max: 68 characters	min: 1 elements mean: 8.50 elements max: 16 elements	min: 1 elements mean: 8.50 elements max: 16 elements

• Samples:

  query	docs	labels
  particleboard bookcase white	['the trådfri led bulb e12 450 lumen is a white, opal globe-shaped light bulb made of polycarbonate plastic. it provides a default luminous flux of 450 lumens and has a color temperature of 2700 k, with a power consumption of 4.1 watts. this bulb is compatible with ikea smarthome products and offers adjustable white tones and wireless dimming, ideal for small lampshades. its item number is 70518179 and price is 9.99.', 'the bestå tv storage combination with glass doors is a furniture piece in beige, brown, and black colors, designed to organize and display tvs and related gadgets. it measures 94 1/2x16 1/2x91 inches (240x42x231 cm) and features a blend of particleboard, fibreboard, honeycomb paper filling, paper foil, plastic edging, and tempered glass. the tv bench and frame incorporate recycled materials, while the shelves include both tempered glass and particleboard. drawer runners are made from galvanized steel with a push-open mechanism, enhanced by soft closing hinges crafted fr...	[0, 0, 0, 0, 0, ...]
  small green cabinet with drawer	['the bestå tv bench with doors is a white piece designed to organize and streamline your media area. it features a particle- and fibreboard construction with a honeycomb paper filling made from 100% recycled paper. the surface is finished with paper and melamine foil, with plastic edging for durability. the bench measures 47 1/4 inches wide, 16 1/2 inches deep, and 18 7/8 inches high (120x42x48 cm). it can support a maximum load of 44 pounds per shelf and accommodate tvs weighing up to 35 pounds. functionally, it provides ample storage space and can help keep cables tidy. the tv bench includes features such as soft closing and push-open hinges made from steel and nickel-plated metal, particleboard doors with plastic foil, solid wooden legs with acrylic paint, and a supporting leg made from steel with a powder coating. its item number is 79419448 and price is 231.82.', 'the kungsfors suspension rail with shelf and wall grid is a gray storage solution made from stainless steel. this met...	[0, 0, 0, 0, 0, ...]
  enkoping brown cabinet with shelves	['the maximera drawer, low, is a white storage drawer made from durable metal material. it features measurements of 15 3/4x14 5/8 inches (40x37 cm). the detailed measurements include a width of 14 3/8 inches (36.4 cm) and a frame width of 15 3/4 inches (40.0 cm), a depth of 13 1/4 inches (33.7 cm) and a frame depth of 14 5/8 inches (37.0 cm), and a height of 3 1/8 inches (7.8 cm). the drawer can support a maximum load of 44 lb 1 oz (20 kg). constructed with steel alongside an epoxy/polyester powder coating for the drawer sides and back, it features a particleboard bottom with melamine foil, galvanized steel runners, and abs plastic bumpers. its standout feature is the soft-closing mechanism, ensuring quiet closure, with the capability to pull out fully for easy access and organization. it is maintained by wiping with a cloth dampened in water and mild detergent. its item number is 50285029 and price is 17.5.', 'the nordberget mattress topper is a twin-sized memory foam product in white...	[0, 0, 0, 1, 0, ...]

• Loss: LambdaLoss with these parameters:

  {
      "weighting_scheme": "sentence_transformers.cross_encoder.losses.LambdaLoss.NDCGLoss2PPScheme",
      "k": null,
      "sigma": 1.0,
      "eps": 1e-10,
      "reduction_log": "binary",
      "activation_fn": "torch.nn.modules.linear.Identity",
      "mini_batch_size": 8
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• dataloader_num_workers: 4

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: True
• 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: 4
• 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: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0000	1	0.1305
0.0040	100	0.2531
0.0080	200	0.2407
0.0119	300	0.2348
0.0159	400	0.2214
0.0199	500	0.1899
0.0239	600	0.16
0.0278	700	0.1121
0.0318	800	0.0876
0.0358	900	0.071
0.0398	1000	0.0623
0.0437	1100	0.053
0.0477	1200	0.0562
0.0517	1300	0.0472
0.0557	1400	0.0448
0.0596	1500	0.0441
0.0636	1600	0.0388
0.0676	1700	0.0416
0.0716	1800	0.0431
0.0756	1900	0.038
0.0795	2000	0.0362
0.0835	2100	0.0288
0.0875	2200	0.0303
0.0915	2300	0.0325
0.0954	2400	0.0298
0.0994	2500	0.0276
0.1034	2600	0.0295
0.1074	2700	0.0303
0.1113	2800	0.0282
0.1153	2900	0.0232
0.1193	3000	0.0209
0.1233	3100	0.021
0.1272	3200	0.0175
0.1312	3300	0.0262
0.1352	3400	0.0225
0.1392	3500	0.0273
0.1432	3600	0.0203
0.1471	3700	0.0192
0.1511	3800	0.0215
0.1551	3900	0.0216
0.1591	4000	0.02
0.1630	4100	0.0234
0.1670	4200	0.0215
0.1710	4300	0.0217
0.1750	4400	0.0159
0.1789	4500	0.0219
0.1829	4600	0.0201
0.1869	4700	0.0166
0.1909	4800	0.0202
0.1948	4900	0.0265
0.1988	5000	0.019
0.2028	5100	0.0194
0.2068	5200	0.0164
0.2108	5300	0.0187
0.2147	5400	0.0249
0.2187	5500	0.0159
0.2227	5600	0.0195
0.2267	5700	0.0167
0.2306	5800	0.0195
0.2346	5900	0.0233
0.2386	6000	0.0187
0.2426	6100	0.0197
0.2465	6200	0.0156
0.2505	6300	0.0193
0.2545	6400	0.0211
0.2585	6500	0.0194
0.2624	6600	0.0177
0.2664	6700	0.0157
0.2704	6800	0.0157
0.2744	6900	0.0157
0.2784	7000	0.0137
0.2823	7100	0.017
0.2863	7200	0.0189
0.2903	7300	0.0236
0.2943	7400	0.0119
0.2982	7500	0.0194
0.3022	7600	0.0156
0.3062	7700	0.0171
0.3102	7800	0.0202
0.3141	7900	0.0172
0.3181	8000	0.0148
0.3221	8100	0.0159
0.3261	8200	0.0184
0.3300	8300	0.0127
0.3340	8400	0.013
0.3380	8500	0.0149
0.3420	8600	0.0159
0.3460	8700	0.0201
0.3499	8800	0.0163
0.3539	8900	0.018
0.3579	9000	0.0166
0.3619	9100	0.0165
0.3658	9200	0.0154
0.3698	9300	0.0116
0.3738	9400	0.015
0.3778	9500	0.0144
0.3817	9600	0.0208
0.3857	9700	0.0128
0.3897	9800	0.0205
0.3937	9900	0.0208
0.3976	10000	0.0167
0.4016	10100	0.0119
0.4056	10200	0.0144
0.4096	10300	0.0147
0.4136	10400	0.0189
0.4175	10500	0.0142
0.4215	10600	0.015
0.4255	10700	0.0195
0.4295	10800	0.0172
0.4334	10900	0.0203
0.4374	11000	0.017
0.4414	11100	0.0215
0.4454	11200	0.0221
0.4493	11300	0.0164
0.4533	11400	0.0148
0.4573	11500	0.0176
0.4613	11600	0.0191
0.4652	11700	0.0138
0.4692	11800	0.0177
0.4732	11900	0.0135
0.4772	12000	0.0158
0.4812	12100	0.017
0.4851	12200	0.0128
0.4891	12300	0.0156
0.4931	12400	0.0139
0.4971	12500	0.0229
0.5010	12600	0.0161
0.5050	12700	0.017
0.5090	12800	0.0126
0.5130	12900	0.0163
0.5169	13000	0.0181
0.5209	13100	0.018
0.5249	13200	0.016
0.5289	13300	0.0142
0.5328	13400	0.0186
0.5368	13500	0.0113
0.5408	13600	0.0136
0.5448	13700	0.0155
0.5488	13800	0.0172
0.5527	13900	0.0173
0.5567	14000	0.0167
0.5607	14100	0.017
0.5647	14200	0.0137
0.5686	14300	0.0138
0.5726	14400	0.0147
0.5766	14500	0.0148
0.5806	14600	0.0171
0.5845	14700	0.0202
0.5885	14800	0.0189
0.5925	14900	0.0153
0.5965	15000	0.0145
0.6004	15100	0.017
0.6044	15200	0.0192
0.6084	15300	0.0165
0.6124	15400	0.016
0.6164	15500	0.0179
0.6203	15600	0.0171
0.6243	15700	0.0182
0.6283	15800	0.0188
0.6323	15900	0.0162
0.6362	16000	0.0167
0.6402	16100	0.0145
0.6442	16200	0.0176
0.6482	16300	0.017
0.6521	16400	0.0129
0.6561	16500	0.0158
0.6601	16600	0.0131
0.6641	16700	0.0203
0.6680	16800	0.0178
0.6720	16900	0.0111
0.6760	17000	0.0204
0.6800	17100	0.0138
0.6840	17200	0.0228
0.6879	17300	0.0146
0.6919	17400	0.0169
0.6959	17500	0.017
0.6999	17600	0.0162
0.7038	17700	0.0196
0.7078	17800	0.0157
0.7118	17900	0.0144
0.7158	18000	0.0184
0.7197	18100	0.0147
0.7237	18200	0.019
0.7277	18300	0.0144
0.7317	18400	0.0142
0.7356	18500	0.0185
0.7396	18600	0.0136
0.7436	18700	0.0151
0.7476	18800	0.0154
0.7516	18900	0.0163
0.7555	19000	0.0162
0.7595	19100	0.0175
0.7635	19200	0.0155
0.7675	19300	0.0187
0.7714	19400	0.0142
0.7754	19500	0.0182
0.7794	19600	0.015
0.7834	19700	0.02
0.7873	19800	0.0163
0.7913	19900	0.018
0.7953	20000	0.0155
0.7993	20100	0.0129
0.8032	20200	0.0142
0.8072	20300	0.0113
0.8112	20400	0.0175
0.8152	20500	0.018
0.8192	20600	0.0172
0.8231	20700	0.0158
0.8271	20800	0.0154
0.8311	20900	0.0146
0.8351	21000	0.0126
0.8390	21100	0.0178
0.8430	21200	0.0139
0.8470	21300	0.0193
0.8510	21400	0.0134
0.8549	21500	0.0175
0.8589	21600	0.0174
0.8629	21700	0.0145
0.8669	21800	0.0154
0.8708	21900	0.016
0.8748	22000	0.0142
0.8788	22100	0.0177
0.8828	22200	0.0167
0.8868	22300	0.0145
0.8907	22400	0.0168
0.8947	22500	0.0152
0.8987	22600	0.0156
0.9027	22700	0.0147
0.9066	22800	0.0162
0.9106	22900	0.0181
0.9146	23000	0.0204
0.9186	23100	0.017
0.9225	23200	0.0163
0.9265	23300	0.0173
0.9305	23400	0.0193
0.9345	23500	0.0184
0.9384	23600	0.017
0.9424	23700	0.0163
0.9464	23800	0.0169
0.9504	23900	0.0167
0.9544	24000	0.0161
0.9583	24100	0.0201
0.9623	24200	0.0188
0.9663	24300	0.015
0.9703	24400	0.0162
0.9742	24500	0.0148
0.9782	24600	0.0168
0.9822	24700	0.0181
0.9862	24800	0.0159
0.9901	24900	0.0195
0.9941	25000	0.0164
0.9981	25100	0.0193

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 5.0.0
• Transformers: 4.51.0
• PyTorch: 2.4.1+cu121
• Accelerate: 1.7.0
• Datasets: 3.2.0
• Tokenizers: 0.21.1

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",
}

LambdaLoss

@inproceedings{wang2018lambdaloss,
  title={The LambdaLoss Framework for Ranking Metric Optimization},
  author={Wang, Xuanhui and Li, Cheng and Golbandi, Nadav and Bendersky, Michael and Najork, Marc},
  booktitle={Proceedings of the 27th ACM international conference on information and knowledge management},
  pages={1313--1322},
  year={2018}
}