--- language: - de - en - es - fr - it - nl - pl - pt - ru - zh license: cc-by-nc-sa-4.0 tags: - generated_from_trainer - ner - named-entity-recognition - span-marker datasets: - Babelscape/multinerd metrics: - precision - recall - f1 pipeline_tag: token-classification widget: - text: amelia earthart flog mit ihrer einmotorigen lockheed vega 5b über den atlantik nach paris. example_title: German - text: amelia earhart flew her single engine lockheed vega 5b across the atlantic to paris. example_title: English - text: amelia earthart voló su lockheed vega 5b monomotor a través del océano atlántico hasta parís. example_title: Spanish - text: amelia earthart a fait voler son monomoteur lockheed vega 5b à travers l'ocean atlantique jusqu'à paris. example_title: French - text: amelia earhart ha volato con il suo monomotore lockheed vega 5b attraverso l'atlantico fino a parigi. example_title: Italian - text: amelia earthart vloog met haar één-motorige lockheed vega 5b over de atlantische oceaan naar parijs. example_title: Dutch - text: amelia earthart przeleciała swoim jednosilnikowym samolotem lockheed vega 5b przez ocean atlantycki do paryża. example_title: Polish - text: amelia earhart voou em seu monomotor lockheed vega 5b através do atlântico para paris. example_title: Portuguese - text: амелия эртхарт перелетела на своем одномоторном самолете lockheed vega 5b через атлантический океан в париж. example_title: Russian - text: amelia earthart flaug eins hreyfils lockheed vega 5b yfir atlantshafið til parísar. example_title: Icelandic - text: η amelia earthart πέταξε το μονοκινητήριο lockheed vega 5b της πέρα ​​από τον ατλαντικό ωκεανό στο παρίσι. example_title: Greek - text: amelia earhartová přeletěla se svým jednomotorovým lockheed vega 5b přes atlantik do paříže. example_title: Czech - text: amelia earhart lensi yksimoottorisella lockheed vega 5b:llä atlantin yli pariisiin. example_title: Finnish - text: amelia earhart fløj med sin enmotoriske lockheed vega 5b over atlanten til paris. example_title: Danish - text: amelia earhart flög sin enmotoriga lockheed vega 5b över atlanten till paris. example_title: Swedish - text: amelia earhart fløy sin enmotoriske lockheed vega 5b over atlanterhavet til paris. example_title: Norwegian - text: amelia earhart și-a zburat cu un singur motor lockheed vega 5b peste atlantic până la paris. example_title: Romanian - text: amelia earhart menerbangkan mesin tunggal lockheed vega 5b melintasi atlantik ke paris. example_title: Indonesian - text: амелія эрхарт пераляцела на сваім аднаматорным lockheed vega 5b праз атлантыку ў парыж. example_title: Belarusian - text: амелія ергарт перелетіла на своєму одномоторному літаку lockheed vega 5b через атлантику до парижа. example_title: Ukrainian - text: amelia earhart preletjela je svojim jednomotornim zrakoplovom lockheed vega 5b preko atlantika do pariza. example_title: Croatian - text: amelia earhart lendas oma ühemootoriga lockheed vega 5b üle atlandi ookeani pariisi. example_title: Estonian base_model: bert-base-multilingual-uncased model-index: - name: span-marker-bert-base-multilingual-uncased-multinerd results: - task: type: token-classification name: Named Entity Recognition dataset: name: MultiNERD type: Babelscape/multinerd split: test revision: 2814b78e7af4b5a1f1886fe7ad49632de4d9dd25 metrics: - type: f1 value: 0.9187 name: F1 - type: precision value: 0.9202 name: Precision - type: recall value: 0.9172 name: Recall --- # span-marker-bert-base-multilingual-uncased-multinerd This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an [Babelscape/multinerd](https://huggingface.co/datasets/Babelscape/multinerd) dataset. Is your data always capitalized correctly? Then consider using the cased variant of this model instead for better performance: [lxyuan/span-marker-bert-base-multilingual-cased-multinerd](https://huggingface.co/lxyuan/span-marker-bert-base-multilingual-cased-multinerd). This model achieves the following results on the evaluation set: - Loss: 0.0054 - Overall Precision: 0.9275 - Overall Recall: 0.9147 - Overall F1: 0.9210 - Overall Accuracy: 0.9842 Test set results: - test_loss: 0.0058621917851269245, - test_overall_accuracy: 0.9831472809849865, - test_overall_f1: 0.9187844693592546, - test_overall_precision: 0.9202802342397876, - test_overall_recall: 0.9172935588307115, - test_runtime: 2716.7472, - test_samples_per_second: 149.141, - test_steps_per_second: 4.661, Note: This is a replication of Tom's work. In this work, we used slightly different hyperparameters: `epochs=3` and `gradient_accumulation_steps=2`. We also switched to the uncased [bert model](https://huggingface.co/bert-base-multilingual-uncased) to see if an uncased encoder model would perform better for commonly lowercased entities like, such as food. Please check the discussion [here](https://huggingface.co/lxyuan/span-marker-bert-base-multilingual-cased-multinerd/discussions/1). Refer to the official [model page](https://huggingface.co/tomaarsen/span-marker-mbert-base-multinerd) to review their results and training script. ## Results: | **Language** | **Precision** | **Recall** | **F1** | |--------------|---------------|------------|-----------| | **all** | 92.03 | 91.73 | **91.88** | | **de** | 94.96 | 94.87 | **94.91** | | **en** | 93.69 | 93.75 | **93.72** | | **es** | 91.19 | 90.69 | **90.94** | | **fr** | 91.36 | 90.74 | **91.05** | | **it** | 90.51 | 92.57 | **91.53** | | **nl** | 93.23 | 92.13 | **92.67** | | **pl** | 92.17 | 91.59 | **91.88** | | **pt** | 92.70 | 91.59 | **92.14** | | **ru** | 92.31 | 92.36 | **92.34** | | **zh** | 88.91 | 87.53 | **88.22** | Below is a combined table that compares the results of the cased and uncased models for each language: | **Language** | **Metric** | **Cased** | **Uncased** | |--------------|--------------|-----------|-------------| | **all** | Precision | 92.42 | 92.03 | | | Recall | 92.81 | 91.73 | | | F1 | **92.61** | 91.88 | | **de** | Precision | 95.03 | 94.96 | | | Recall | 95.07 | 94.87 | | | F1 | **95.05** | 94.91 | | **en** | Precision | 95.00 | 93.69 | | | Recall | 95.40 | 93.75 | | | F1 | **95.20** | 93.72 | | **es** | Precision | 92.05 | 91.19 | | | Recall | 91.37 | 90.69 | | | F1 | **91.71** | 90.94 | | **fr** | Precision | 92.37 | 91.36 | | | Recall | 91.41 | 90.74 | | | F1 | **91.89** | 91.05 | | **it** | Precision | 91.45 | 90.51 | | | Recall | 93.15 | 92.57 | | | F1 | **92.29** | 91.53 | | **nl** | Precision | 93.85 | 93.23 | | | Recall | 92.98 | 92.13 | | | F1 | **93.41** | 92.67 | | **pl** | Precision | 93.13 | 92.17 | | | Recall | 92.66 | 91.59 | | | F1 | **92.89** | 91.88 | | **pt** | Precision | 93.60 | 92.70 | | | Recall | 92.50 | 91.59 | | | F1 | **93.05** | 92.14 | | **ru** | Precision | 93.25 | 92.31 | | | Recall | 93.32 | 92.36 | | | F1 | **93.29** | 92.34 | | **zh** | Precision | 89.47 | 88.91 | | | Recall | 88.40 | 87.53 | | | F1 | **88.93** | 88.22 | Short discussion: Upon examining the results, one might conclude that the cased version of the model is better than the uncased version, as it outperforms the latter across all languages. However, I recommend that users test both models on their specific datasets (or domains) to determine which one actually delivers better performance. My reasoning for this suggestion stems from a brief comparison I conducted on the FOOD (food) entities. I found that both cased and uncased models are sensitive to the full stop punctuation mark. We direct readers to the section: Quick Comparison on FOOD Entities. ## Label set | Class | Description | Examples | |-------|-------------|----------| | **PER (person)** | People | Ray Charles, Jessica Alba, Leonardo DiCaprio, Roger Federer, Anna Massey. | | **ORG (organization)** | Associations, companies, agencies, institutions, nationalities and religious or political groups | University of Edinburgh, San Francisco Giants, Google, Democratic Party. | | **LOC (location)** | Physical locations (e.g. mountains, bodies of water), geopolitical entities (e.g. cities, states), and facilities (e.g. bridges, buildings, airports). | Rome, Lake Paiku, Chrysler Building, Mount Rushmore, Mississippi River. | | **ANIM (animal)** | Breeds of dogs, cats and other animals, including their scientific names. | Maine Coon, African Wild Dog, Great White Shark, New Zealand Bellbird. | | **BIO (biological)** | Genus of fungus, bacteria and protoctists, families of viruses, and other biological entities. | Herpes Simplex Virus, Escherichia Coli, Salmonella, Bacillus Anthracis. | | **CEL (celestial)** | Planets, stars, asteroids, comets, nebulae, galaxies and other astronomical objects. | Sun, Neptune, Asteroid 187 Lamberta, Proxima Centauri, V838 Monocerotis. | | **DIS (disease)** | Physical, mental, infectious, non-infectious, deficiency, inherited, degenerative, social and self-inflicted diseases. | Alzheimer’s Disease, Cystic Fibrosis, Dilated Cardiomyopathy, Arthritis. | | **EVE (event)** | Sport events, battles, wars and other events. | American Civil War, 2003 Wimbledon Championships, Cannes Film Festival. | | **FOOD (food)** | Foods and drinks. | Carbonara, Sangiovese, Cheddar Beer Fondue, Pizza Margherita. | | **INST (instrument)** | Technological instruments, mechanical instruments, musical instruments, and other tools. | Spitzer Space Telescope, Commodore 64, Skype, Apple Watch, Fender Stratocaster. | | **MEDIA (media)** | Titles of films, books, magazines, songs and albums, fictional characters and languages. | Forbes, American Psycho, Kiss Me Once, Twin Peaks, Disney Adventures. | | **PLANT (plant)** | Types of trees, flowers, and other plants, including their scientific names. | Salix, Quercus Petraea, Douglas Fir, Forsythia, Artemisia Maritima. | | **MYTH (mythological)** | Mythological and religious entities. | Apollo, Persephone, Aphrodite, Saint Peter, Pope Gregory I, Hercules. | | **TIME (time)** | Specific and well-defined time intervals, such as eras, historical periods, centuries, years and important days. No months and days of the week. | Renaissance, Middle Ages, Christmas, Great Depression, 17th Century, 2012. | | **VEHI (vehicle)** | Cars, motorcycles and other vehicles. | Ferrari Testarossa, Suzuki Jimny, Honda CR-X, Boeing 747, Fairey Fulmar. | ## Inference Example ```python # install span_marker (env)$ pip install span_marker from span_marker import SpanMarkerModel model = SpanMarkerModel.from_pretrained("lxyuan/span-marker-bert-base-multilingual-uncased-multinerd") description = "Singapore is renowned for its hawker centers offering dishes \ like Hainanese chicken rice and laksa, while Malaysia boasts dishes such as \ nasi lemak and rendang, reflecting its rich culinary heritage." entities = model.predict(description) entities >>> [ {'span': 'Singapore', 'label': 'LOC', 'score': 0.9999247789382935, 'char_start_index': 0, 'char_end_index': 9}, {'span': 'laksa', 'label': 'FOOD', 'score': 0.794235348701477, 'char_start_index': 93, 'char_end_index': 98}, {'span': 'Malaysia', 'label': 'LOC', 'score': 0.9999157190322876, 'char_start_index': 106, 'char_end_index': 114} ] # missed: Hainanese chicken rice as FOOD # missed: nasi lemak as FOOD # missed: rendang as FOOD # note: Unfortunately, this uncased version still fails to pick up those commonly lowercased food entities and even misses out on the capitalized `Hainanese chicken rice` entity. ``` #### Quick test on Chinese ```python from span_marker import SpanMarkerModel model = SpanMarkerModel.from_pretrained("lxyuan/span-marker-bert-base-multilingual-uncased-multinerd") # translate to chinese description = "Singapore is renowned for its hawker centers offering dishes \ like Hainanese chicken rice and laksa, while Malaysia boasts dishes such as \ nasi lemak and rendang, reflecting its rich culinary heritage." zh_description = "新加坡因其小贩中心提供海南鸡饭和叻沙等菜肴而闻名, 而马来西亚则拥有椰浆饭和仁当等菜肴，反映了其丰富的烹饪传统." entities = model.predict(zh_description) entities >>> [ {'span': '新加坡', 'label': 'LOC', 'score': 0.8477746248245239, 'char_start_index': 0, 'char_end_index': 3}, {'span': '马来西亚', 'label': 'LOC', 'score': 0.7525337934494019, 'char_start_index': 27, 'char_end_index': 31} ] # It only managed to capture two countries: Singapore and Malaysia. # All other entities were missed out. # Same prediction as the [uncased model](https://huggingface.co/lxyuan/span-marker-bert-base-multilingual-cased-multinerd) ``` ### Quick Comparison on FOOD Entities In this quick comparison, we found that a full stop punctuation mark seems to help the uncased model identify food entities, regardless of whether they are capitalized or in uppercase. In contrast, the cased model doesn't respond well to full stops, and adding them would lower the prediction score. ```python from span_marker import SpanMarkerModel cased_model = SpanMarkerModel.from_pretrained("lxyuan/span-marker-bert-base-multilingual-cased-multinerd") uncased_model = SpanMarkerModel.from_pretrained("lxyuan/span-marker-bert-base-multilingual-uncased-multinerd") # no full stop mark uncased_model.predict("i love fried chicken and korea bbq") >>> [] uncased_model.predict("i love fried chicken and korea BBQ") # Uppercase BBQ only >>> [] uncased_model.predict("i love fried chicken and Korea BBQ") # Capitalize korea and uppercase BBQ >>> [] # add full stop to get better result uncased_model.predict("i love fried chicken and korea bbq.") >>> [ {'span': 'fried chicken', 'label': 'FOOD', 'score': 0.6531468629837036, 'char_start_index': 7, 'char_end_index': 20}, {'span': 'korea bbq', 'label': 'FOOD', 'score': 0.9738698601722717, 'char_start_index': 25,'char_end_index': 34} ] uncased_model.predict("i love fried chicken and korea BBQ.") >>> [ {'span': 'fried chicken', 'label': 'FOOD', 'score': 0.6531468629837036, 'char_start_index': 7, 'char_end_index': 20}, {'span': 'korea BBQ', 'label': 'FOOD', 'score': 0.9738698601722717, 'char_start_index': 25, 'char_end_index': 34} ] uncased_model.predict("i love fried chicken and Korea BBQ.") >>> [ {'span': 'fried chicken', 'label': 'FOOD', 'score': 0.6531468629837036, 'char_start_index': 7, 'char_end_index': 20}, {'span': 'Korea BBQ', 'label': 'FOOD', 'score': 0.9738698601722717, 'char_start_index': 25, 'char_end_index': 34} ] # no full stop mark cased_model.predict("i love fried chicken and korea bbq") >>> [ {'span': 'korea bbq', 'label': 'FOOD', 'score': 0.5054221749305725, 'char_start_index': 25, 'char_end_index': 34} ] cased_model.predict("i love fried chicken and korea BBQ") >>> [ {'span': 'korea BBQ', 'label': 'FOOD', 'score': 0.6987857222557068, 'char_start_index': 25, 'char_end_index': 34} ] cased_model.predict("i love fried chicken and Korea BBQ") >>> [ {'span': 'Korea BBQ', 'label': 'FOOD', 'score': 0.9755308032035828, 'char_start_index': 25, 'char_end_index': 34} ] # add a fullstop mark hurt the cased model prediction score a little bit cased_model.predict("i love fried chicken and korea bbq.") >>> [] cased_model.predict("i love fried chicken and korea BBQ.") >>> [ {'span': 'korea BBQ', 'label': 'FOOD', 'score': 0.5078140497207642, 'char_start_index': 25, 'char_end_index': 34} ] cased_model.predict("i love fried chicken and Korea BBQ.") >>> [ {'span': 'Korea BBQ', 'label': 'FOOD', 'score': 0.895089328289032, 'char_start_index': 25, 'char_end_index': 34} ] ``` ## Training procedure One can reproduce the result running this [script](https://huggingface.co/tomaarsen/span-marker-mbert-base-multinerd/blob/main/train.py) ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:-----:|:------:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.0157 | 1.0 | 50369 | 0.0048 | 0.9143 | 0.8986 | 0.9064 | 0.9807 | | 0.003 | 2.0 | 100738 | 0.0047 | 0.9237 | 0.9126 | 0.9181 | 0.9835 | | 0.0017 | 3.0 | 151107 | 0.0054 | 0.9275 | 0.9147 | 0.9210 | 0.9842 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu117 - Datasets 2.14.3 - Tokenizers 0.13.3