--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:3358 - loss:CosineSimilarityLoss base_model: KiruruP/anime-recommendation-multilingual-mpnet-base-v2 widget: - source_sentence: What is a manga series about a boy-king with a diamond mine in the South Seas, surrounded by beautiful teenage boys and facing threats from an international diamond syndicate? sentences: - After the defeat of Myouri Unzen at the hands of Medaka Kurokami and her Student Council, peace has returned to Hakoniwa Academy—at least, for a short while. Soon, Medaka, Zenkichi Hitoyoshi, Kouki Akune, and Mogana Kikaijima find themselves wrapped up in another sinister scheme, known as the "Flask Plan," led by the school's principal himself. However, the council's first problem is to deal with a whole new group of superhuman students calling themselves the "Thirteen Party," led by the egotistical but powerful Oudo Miyakonojou. With the mysterious Flask Plan, Oudo's tyranny, and the resurfacing of an old enemy, the state of Hakoniwa Academy is far from tranquil, and Medaka and her companions have their hands full as things only get a lot more abnormal. - Patarillo! is set in a society much like ours in most ways, with one decided twist. The manga on which it is based is one of the much-read works produced for adolescent Japanese girls that features a healthy proportion of gay men and beautiful teenagers aka bishounen (beautiful boys). Most of the action takes place in Marinera, the land of eternal spring, located somewhere in the South Seas. The country is a major producer of diamonds; they provide much of the basis of conflict in the anime series. They come from one of the most prolific mines in the world, owned by the king of Marinera, the vertically challenged but horizontally endowed boy-king Patarillo himself. The International Diamond Syndicate - a huge semi- criminal organization/ secret society dedicated to taking over the world's entire diamond supply- wants that mine and will stop at nothing to get it. In the early episodes they send off a number of bishounen assassins to do in Patarillo, which necessitates his having a bodyguard, the English MI6 agent, Major Jack ('Bishounen-Killer') Bancoran. Bancoran's nickname doesn't mean he shoots bishounen in cold blood. The soubriquet comes from the fact that no male under the age of 17 can resist his sexual fascination. This, to Bancoran's eternal disgust, includes Patarillo himself. The action switches often from Marinera to MI6 headquarters in London (London seems to be an easy two hour's flight from the South Seas) or Bancoran's palatial condo in the suburbs of same. (MI6, be it noted, looks a lot like Fritz Lang's Metropolis, while Jack's 'apartment' bears a passing resemblance to Randolph Hearst's spread.) The action also goes into the past and future and out into space. Patarillo evidently gets around. - 'The world''s greatest assassin had sworn lifelong allegiance to the organization that raised him. However, despite his loyalty, that very same organization takes action to silence him, ultimately leading to his demise. Drowning in frustration and regrets he can no longer suppress, he finds himself in an audience with a goddess attracted by his exceptional skills. The goddess offers him reincarnation into a magnificent world of swords and magic so he can perform a crucial mission: prevent that world''s destruction by slaying its hero. Accepting the goddess'' request, he is reborn as Lugh Tuatha Dé, the son of a noble family of assassins serving the Alvan Kingdom. Under the guidance of his father, Lugh learns new assassination techniques that significantly differ from the cold-blooded and unsympathetic killing style of his previous life. Furthermore, his other talents bloom, allowing him to meet new allies and acquaintances. Even so, Lugh knows that his efforts are far from adequate, because a monumental adversary such as the hero can only be defeated with perfection.' - source_sentence: What is the story of a World War I pilot turned pig who becomes a bounty hunter in the Adriatic Sea, and how does he seek revenge against a young hotshot pilot? sentences: - Shi Miao simply cannot stand her lazy, stupid, and unreliable elder brother Shi Fen, who is one year above her at the same high school. Though the two siblings can only depend on each other, Shi Miao's violent tendencies combined with Shi Fen's knack for causing trouble cause them to fight constantly. And so, Shi Miao can only hope that someone might take her brother away—even though, when push comes to shove, Shi Fen always tries to do what he believes is best for his cute younger sister. - After a curse turned him into a pig, World War I ace Marco Pagot becomes Porco Rosso, a mysterious bounty hunter who takes down sky pirates in the Adriatic Sea. He whiles away his days on a secluded island, rarely leaving other than to collect bounties or to visit the beautiful Gina, a songstress and owner of the Hotel Adriano. One day, while traveling to fix his faulty engine, Porco Rosso is gunned down by a young American hotshot named Donald Curtis. Thrilled at the possibility of fame, Donald boldly declares that the flying pig is dead. Not wanting to disappoint Gina, Porco Rosso flees to the famous Piccolo S.P.A. airplane company and takes out a massive loan in order to repair and improve his fighter plane. There, he is surprised to find that the chief engineer of Piccolo S.P.A. is the 17-year-old Fio Piccolo, who hungers for a chance to prove herself. With Fio's improvements, Porco Rosso prepares to challenge Donald officially and regain his honor. - 'Justy Ueki Tylor is an average 20-year-old man: lazy, greedy, and a passionate womanizer. He plans to land an easy job with the United Planets Space Force that pays decently and is also far away from the rigorous combat raging throughout the galaxy. However, Tylor''s dreams of living a simple life are brought to a sudden halt when he stumbles into a dangerous hostage situation. Through one strange mishap after another, Tylor miraculously manages to save the hostages and is awarded command of the decrepit space-cruiser Soyokaze! Now Tylor finds himself in charge of sending mad mercenaries, proud pilots, skeptical colleagues, and harsh commanders through the infinite expanse of the universe, all the while avoiding the looming threat of the Holy Raalgon Empire. What misadventures await the irresponsible Captain Tylor?' - source_sentence: '"What is the next challenge for Souma Yukihira and Erina Nakiri in the Régiment de Cuisine at Tootsuki Culinary Academy, as they face off against the Elite Ten Council?"' sentences: - Nyaruko still wants Mahiro, as does Hasuta. Kūko wants Nyaruko, but believes both Nyaruko's and Mahiro's "first time" belongs to her. Yoriko puts up with all of it and cheerfully runs the house where they all live. Mahiro just wants some sanity. He doesn't want to be the love toy of a Nyarlathotepan, Cthughan, or a shots-like Hasturan. He may or may not hold out. - On a sunny afternoon in her Paris apartment, assassin-for-hire Mireille Bouquet receives a strange email from Kirika Yuumura, a young student from Japan, inviting her to "make a pilgrimage to the past" together. Initially thinking the email is nonsense, she changes her mind when it begins playing a song that she recognizes from her youth. Upon first meeting each other in person, the two are suddenly ambushed by gun-wielding men. While Mireille is capable of fending off the assault, she discovers that Kirika is quite adept in combat situations after she takes out several gunmen on her own. Despite her proficiency at killing, Kirika laments her inability to feel remorse for her victims. In addition, Kirika apparently has no memory of how she came to acquire the skills she possesses or even of her real identity. Sensing shared history between them, Mireille agrees to team up with Kirika, and together, they embark on a journey to uncover the mysteries of their pasts. Operating under the codename "Noir," the duo's fragile alliance is tested as they begin accepting jobs, each one bringing them closer to the truth of who they really are. - At Tootsuki Culinary Academy, a heated eight-on-eight Shokugeki known as the Régiment de Cuisine rages on between Central and the rebel forces led by Souma Yukihira and Erina Nakiri. Though they won a stunning perfect victory in the first bout, the rebels face an uphill battle ahead, as they must now face off against the rest of the Elite Ten Council. With the future of Tootsuki at stake, Souma and Erina must push far beyond the limits of their abilities, using everything they learned from their mentors and ultimately drawing from their experiences cooking together as friends. - source_sentence: What is the story of a boy without magical abilities living in a magical world, forced to attend a prestigious magic academy to prove himself and protect his family? sentences: - 'In this magical world, one is easily identified as having magical abilities by a distinctive mark on their face. Those unable to practice magic are swiftly exterminated to maintain the magical integrity of society. However, deep within a forest lies an anomaly in Mash Burnedead, who can be found pumping iron with one arm and lifting a cream puff with the other. This aloof boy with superhuman strength—but no magical abilities—leads a quiet life with his father, far removed from society. Mash''s peace is soon disturbed when the authorities discover his lack of magical powers. They issue him an ultimatum: compete to become a Divine Visionary, which would force everyone to accept him, or be persecuted forever. To protect his family, he enrolls in the prestigious Easton Magic Academy, which only the most elite and gifted students are allowed to attend. Now, Mash must overcome his shortcomings as a magic-less being and surpass the other students—relying solely on his muscles.' - Pei Qian, an ordinary migrant worker, was accidentally bound to the wealth conversion system, which gave him a good opportunity to spend money in business and start his life over again. However, the system stipulates that you can only earn one yuan if you make a profit of 100 yuan, but all the money you lose can go into your own pocket. In order to lose money, Pei Qian chose the high-risk, money-burning game industry, and deliberately produced "alternative" games that went against the rules of the market. However, he unexpectedly became popular time and time again, earning a lot of money, and painfully became Pei Qian is the "business wizard" admired by everyone, but only Pei Qian understands that I really just want to lose money... - When "ordinary boy" Kagami Kazuya meets the beautiful tsukumogami Kiriha, his life gets turned upside-down. As a "Taboo Child" who draws the supernatural towards him, he receives orders from the God of the Land, Kukuri, to become an exorcist and defeat these evil forces. And so, he and Kiriha do battle. To find out information on these supernatural beings, Kazuya and his friends set up a counselor's club at school. But behind the typical-seeming troubles he hears about, he uncovers a major plot to target Kukuri... In addition to the sadistic-yet-beautiful tsukumogami Kiriha, the situation draws other girls to Kazuya to join the fray! - source_sentence: '"Who is blackmailing the members of Class F in a school where their avatars are acting strangely?"' sentences: - The blockheads of Class F return with more misadventures! Rather than desperately competing against the elite students in Class A for better facilities, they have other problems at hand. While the girls are constantly vying for the boys' attention, Akihisa Yoshii and Yuuji Sakamoto are being blackmailed by a stalker who threatens to reveal their most embarrassing secrets to the whole school. Moreover, everyone's avatar starts to behave strangely. Filled with more nosebleeds and eye-pokes, the boys of Class F must work together to discover the stalker's identity and deal with the misfortunes that come with love among fools. - 'Amatsuyu "Jouro" Kisaragi is a completely average second-year high school student who has two dates over one weekend⁠—with the student council president Sakura "Cosmos" Akino on Saturday, then with his childhood friend Aoi "Himawari" Hinata on Sunday. Sadly for Jouro, both girls proclaim their love for his best friend Taiyou "Sun-chan" Ooga, the ace of the baseball team. Accepting each of their requests for advice and guidance, he is now responsible for helping the two girls win the heart of the same guy. Unbeknownst to his friends, Jouro''s friendly and obtuse image is all but a ruse designed to cast himself as the clueless protagonist of a textbook romantic comedy. A schemer under his cheery facade, he makes the best of this unexpected turn of events with a new plan: get Sun-chan to fall for either Cosmos or Himawari and take the other as his own prize. But Jouro''s last-ditch effort is threatened by the gloomy, four-eyed Sumireko "Pansy" Sanshokuin, who surprises Jouro with not only her knowledge of his secret personality but also a confession to the true self he hid for all this time. Stuck in this hilariously messy situation, each of the five students must navigate countless lies, traps, and misunderstandings to come out on top.' - 'After witnessing his mother''s death at a young age, Uryuu Kamihate grew up disillusioned with the gods, dismissing faith in them as utter nonsense. Due to his beliefs, he aims to become a doctor, spending most of his time studying to enter the prestigious Kyoto University. To further his studies, Uryuu searches for a new place to take him in and get away from the noisy environment of the orphanage where he grew up. Chidori Amagami, head priest of the Amagami Shrine, allows him to stay at the Amagami residence. However, Uryuu has to live there with Chidori''s three granddaughters—Yae, Yuna, and Asahi—who serve as shrine maidens. Moreover, Chidori has another condition for Uryuu: he has to marry one of the sisters to ensure the shrine''s future and one day inherit it. But with Uryuu''s goals and outlook naturally clashing against the sisters'' beliefs, this already daunting ordeal seems outright impossible.' pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on KiruruP/anime-recommendation-multilingual-mpnet-base-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [KiruruP/anime-recommendation-multilingual-mpnet-base-v2](https://huggingface.co/KiruruP/anime-recommendation-multilingual-mpnet-base-v2). It maps sentences & paragraphs to a 768-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:** [KiruruP/anime-recommendation-multilingual-mpnet-base-v2](https://huggingface.co/KiruruP/anime-recommendation-multilingual-mpnet-base-v2) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'}) (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash 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("KiruruP/anime-recommendation-multilingual-mpnet-base-v2-v3") # Run inference sentences = [ '"Who is blackmailing the members of Class F in a school where their avatars are acting strangely?"', "The blockheads of Class F return with more misadventures! Rather than desperately competing against the elite students in Class A for better facilities, they have other problems at hand. While the girls are constantly vying for the boys' attention, Akihisa Yoshii and Yuuji Sakamoto are being blackmailed by a stalker who threatens to reveal their most embarrassing secrets to the whole school. Moreover, everyone's avatar starts to behave strangely. Filled with more nosebleeds and eye-pokes, the boys of Class F must work together to discover the stalker's identity and deal with the misfortunes that come with love among fools.", 'Amatsuyu "Jouro" Kisaragi is a completely average second-year high school student who has two dates over one weekend\u2060—with the student council president Sakura "Cosmos" Akino on Saturday, then with his childhood friend Aoi "Himawari" Hinata on Sunday. Sadly for Jouro, both girls proclaim their love for his best friend Taiyou "Sun-chan" Ooga, the ace of the baseball team. Accepting each of their requests for advice and guidance, he is now responsible for helping the two girls win the heart of the same guy. Unbeknownst to his friends, Jouro\'s friendly and obtuse image is all but a ruse designed to cast himself as the clueless protagonist of a textbook romantic comedy. A schemer under his cheery facade, he makes the best of this unexpected turn of events with a new plan: get Sun-chan to fall for either Cosmos or Himawari and take the other as his own prize. But Jouro\'s last-ditch effort is threatened by the gloomy, four-eyed Sumireko "Pansy" Sanshokuin, who surprises Jouro with not only her knowledge of his secret personality but also a confession to the true self he hid for all this time. Stuck in this hilariously messy situation, each of the five students must navigate countless lies, traps, and misunderstandings to come out on top.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.9794, 0.6574], # [0.9794, 1.0000, 0.6667], # [0.6574, 0.6667, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 3,358 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | label | |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | What is the story about the kind-hearted guardian in a small church who has a secret crush on the pastor and protects the villagers with her mysterious powers? | In a small church atop a hill, Pastor Lawrence looks after Saint Cecilia. Her presence is a beacon of hope for the villagers, as her mysterious powers protect them from the weakness of their minds and outside evils. While she appears dignified in front of the villagers, Cecilia allows her lazy side to show when alone with the pastor. Although Cecilia is the guardian of the people, Lawrence is determined to shield her from harm. Unbeknownst to Lawrence, Cecilia harbors a huge crush on him. She accompanies him on his shopping trips and provides him with divine protection every day. Despite Lawrence remaining oblivious to her true feelings, Cecilia continues to shower him with obvious displays of affection as the bond between them grows. | 1.0 | | What is a query for a natural language search engine to find a story about a cadet with no space experience, inspired by a passionate woman to join a failing space program and change his country's fate? | Shirotsugh "Shiro" Lhadatt may be a cadet in the Kingdom of Honneamise's Royal Space Force (RSF), but he has never been in space before—in fact, nobody has. The RSF is often regarded as a failure both by the country's citizens and a government more interested in precipitating a war with a neighboring country than scientific achievement. Following the funeral of a fellow cadet, an unmotivated Shiro is walking in the city one night, when he bumps into Riquinni Nonderaiko, a young, pious woman, genuinely enthusiastic about the significance of space exploration. As the two gradually bond, Riquinni's encouragement inspires Shiro to volunteer as a pilot for a prospective rocket ship, potentially becoming Honneamise's first man in space. Shiro and the RSF are soon joined by a team of elderly but eager scientists and engineers, and together, they embark on a mission to mold their nation's space program into a success. However, their efforts soon catch the attention of the government, which see... | 1.0 | | What is the strongest woman on the planet doing to prevent All For One from seizing her quirk and aiding her allies against Tomura Shigaraki and All Might? | Following an all-out battle with the Paranormal Liberation Front, it is difficult for the people of Japan to continue placing faith in their heroes. To combat the combined power of Tomura Shigaraki and All For One, All Might calls for his ally from the West—the strongest woman on the planet, Star and Stripe. However, All For One decides to intercept Star and her fleet to get his hands on her overpowered quirk before she can enter Japanese airspace. Although Endeavor, Hawks, and Best Jeanist are headed to the rendezvous point, Star makes a gamble in the present to save her comrades. | 1.0 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 10 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `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`: 10 - `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} - `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 | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 2.3810 | 500 | 0.0177 | | 4.7619 | 1000 | 0.0038 | | 7.1429 | 1500 | 0.0015 | | 9.5238 | 2000 | 0.001 | ### Framework Versions - Python: 3.11.13 - Sentence Transformers: 5.1.0 - Transformers: 4.55.0 - PyTorch: 2.6.0+cu124 - Accelerate: 1.10.0 - Datasets: 4.0.0 - Tokenizers: 0.21.4 ## 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", } ```