distilroberta-ai-job-embeddings

SentenceTransformer

This is a sentence-transformers model trained on the ai-job-embedding-finetuning dataset. 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:** [Unknown](https://huggingface.co/unknown) -->

• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • ai-job-embedding-finetuning

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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})
  (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("sithot28/distilroberta-ai-job-embeddings")
# Run inference
sentences = [
    'Financial Data Analyst',
    'We are the leading provider of professional services to the middle market globally, our purpose is to instill confidence in a world of change, empowering our clients and people to realize their full potential. Our exceptional people are the key to our unrivaled, inclusive culture and talent experience and our ability to be compelling to our clients. You’ll find an environment that inspires and empowers you to thrive both personally and professionally. There’s no one like you and that’s why there’s nowhere like RSM.\n\nRSM is looking to hire a Data Analyst on our National Finance and Operations team.\n\nThe Data Analyst is responsible for the development, automation, and compilation of data. This position will prepare reports through Excel, Access, SharePoint, and Power BI using compiled data from several internal systems.\n\nEssential Duties\n\nAnalytical duties may include but are not limited to:\n\nDeveloping data and storage requirements, reporting, analytics, and delivery methods in data standards and metadata.Develop, analyze, and evaluate data to create and maintain business intelligence frameworks.Integrate and mine large data sets, connecting data from disparate sources to identify critical insights and pragmatic data solutions.Maintain/update/create technical specifications (ex. data mapping, data flows, and dashboard content).Develop real-time reporting for analyzing KPIs.Design and create analysis and reports that include summaries, graphs, diagrams, and other visual representations in BI or excel.Develop and maintain forecasting databases/tools and provide analysis to leaders on outcomes.Discover and define new processes for improvement and opportunities.\n\nMinimum Qualifications\n\nBachelor’s degree or equivalent experience. Accounting or Finance major preferred.Strong Microsoft Office skills.Ability to communicate effectively both verbally and written.Ability to work autonomously and part of a team.Effective organization and time management skills.Solid understanding of developing data requirements.Knowledge of Excel, Power BI, SQL, and understanding of concepts of database structures and data querying.Advanced Microsoft Office skills with exposure to Visual Basic.Previous experience with SQL preferred.Previous experience with a Business Intelligence (BI) tool preferred.Previous experience analyzing data and predicting future outcomes preferred.Prepare and review monthly work papers; perform account reconciliations, investigate general ledger balance discrepancies.Assist with month-end closing process.\n\nAt RSM, we offer a competitive benefits and compensation package for all our people. We support and inspire you to prioritize your wellbeing by delivering personalized, holistic programming for your physical, emotional, financial and community wellbeing. RSM has a generous time off policy with at least 14 paid holidays, wellbeing days and associate and above access to self-managed time off. We offer flexibility in your schedule, empowering you to balance life’s demands, while also maintaining your ability to serve clients. Learn more about our total rewards at https://rsmus.com/careers/working-at-rsm/benefits.\n\nRSM is proud to be an Affirmative Action and Equal Employment Opportunity employer.\u202f We are proud to provide our employees with tools to assist them in being successful in achieving both personal and professional goals. We welcome and support all our employees to thrive in an environment free of discrimination and harassment. As an Affirmative Action and Equal Opportunity Employer all applicants will receive consideration for employment as RSM does not tolerate discrimination and/or harassment based on race; color; creed; sincerely held religious beliefs, practices or observances; sex (including pregnancy or disabilities related to nursing); gender (including gender identity and/or gender expression); sexual orientation; HIV Status; national origin; ancestry; familial or marital status; age; physical or mental disability; citizenship; political affiliation; medical condition (including family and medical leave); domestic violence victim status; past, current or prospective service in the US uniformed service; pre-disposing genetic characteristics or any other characteristic protected under applicable federal, state or local law.\n\nAccommodation for applicants with disabilities is available upon request in connection with the recruitment process and/or employment/partnership. RSM is committed to providing equal opportunity and reasonable accommodation for people with disabilities. If you require a reasonable accommodation to complete an application, interview, or otherwise participate in the recruiting process, please call us at 800-274-3978 or send us an email at [email protected].\n\nRSM does not intend to hire entry level candidates who will require sponsorship now OR in the future (i.e. F-1 visa holders). If you are a recent U.S. college / university graduate possessing 1-2 years of progressive and relevant work experience in a same or similar role to the one for which you are applying, excluding internships, you may be eligible for hire as an experienced associate.\n\nCompensation Range: $61,200 - $109,900',
    "Machine Learning Engineer - Remote - Competitive Salary + Bonus + Benefits\nDescriptionAre you passionate about machine learning and interested in working in the fast-paced information technology and services industry? We are seeking a talented Machine Learning Engineer to join our team. As a Machine Learning Engineer, you will play a key role in driving innovation and creating solutions that leverage machine learning algorithms. You will collaborate with our team of talented software developers to enhance our existing products and develop new cutting-edge solutions. If you have a strong technical background, a knack for problem-solving, and a passion for transforming data into actionable insights, we would love to hear from you.\nResponsibilitiesDevelop and implement machine learning models and algorithms for various applicationsAnalyze and process large, complex datasets to extract valuable insightsCollaborate with cross-functional teams to understand business requirements and deliver innovative solutionsPerform data cleaning, preprocessing, and feature engineering to improve model performanceOptimize and fine-tune machine learning models for scalability and efficiencyEvaluate and improve existing ML algorithms, frameworks, and toolkitsStay up-to-date with the latest trends and advancements in the field of machine learning\nRequirementsBachelor's degree in Computer Science, Engineering, or a related fieldStrong knowledge of machine learning algorithms and data modeling techniquesProficiency in Python and its associated libraries such as TensorFlow, PyTorch, or scikit-learnExperience with big data technologies such as Hadoop, Spark, or Apache KafkaFamiliarity with cloud computing platforms such as AWS or Google CloudExcellent problem-solving and analytical skillsStrong communication and collaboration abilitiesAbility to work effectively in a fast-paced and dynamic environment",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!-- ### 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.* -->

Evaluation

Metrics

Triplet

• Datasets: ai-job-validation and ai-job-test
• Evaluated with <code>TripletEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

ai-job-embedding-finetuning

• Dataset: ai-job-embedding-finetuning
• Size: 943 training samples
• Columns: <code>title</code>, <code>description</code>, and <code>description_neg</code>
• Approximate statistics based on the first 943 samples:

  	title	description	description_neg
  type	string	string	string
  details	<ul><li>min: 4 tokens</li><li>mean: 7.16 tokens</li><li>max: 37 tokens</li></ul>	<ul><li>min: 14 tokens</li><li>mean: 419.14 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 29 tokens</li><li>mean: 419.76 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  title	description	description_neg
  <code>Data Engineering Architect- AWS Cloud</code>	<code>Publicis Sapient is a digital transformation partner helping established organizations get to their future, digitally-enabled state, both in the way they work and the way they serve their customers. We help unlock value through a start-up mindset and modern methods, fusing strategy, consulting and customer experience with agile engineering and problem-solving creativity. United by our core values and our purpose of helping people thrive in the brave pursuit of next, our 20,000+ people in 53 offices around the world combine experience across technology, data sciences, consulting and customer obsession to accelerate our clients’ businesses through designing the products and services their customers truly value.<br><br>Job Description<br><br>Publicis Sapient is looking for a Data Architect -AWS Cloud to join our team of bright thinkers and doers. You will team with top-notch technologists to enable real business outcomes for our enterprise clients by translating their needs into transformative soluti...</code>	<code>Exemption Status<br><br>United States of America (Exempt)<br><br>$92,036 - $127,700 - $163,364<br><br>“Pay scale information is not necessarily reflective of actual compensation that may be earned, nor a promise of any specific pay for any selected candidate or employee, which is always dependent on actual experience, education, qualifications, and other factors. A full review of our comprehensive pay and benefits will be discussed at the offer stage with the selected candidate.”<br><br>This position is not eligible for Sponsorship.<br><br>MedImpact Healthcare Systems, Inc. is looking for extraordinary people to join our team!<br><br>Why join MedImpact? Because our success is dependent on you; innovative professionals with top notch skills who thrive on opportunity, high performance, and teamwork. We look for individuals who want to work on a team that cares about making a difference in the value of healthcare.<br><br>At MedImpact, we deliver leading edge pharmaceutical and technology related solutions that dramatically improv...</code>
  <code>Data Analyst II</code>	<code>About FedEx Supply Chain<br><br>FedEx Supply Chain, a subsidiary of FedEx Corp. (NYSE: FDX), is a leader in the third-party logistics industry offering a diverse service portfolio that enables commerce for businesses. With a proven track record of innovation and operational excellence, FedEx Supply Chain takes a consultative approach to optimize logistics processes, implement innovative technology and drive continuous improvement. By leveraging best practices and the world-renowned FedEx network, FedEx Supply Chain delivers leading solutions that provide flexibility, enable scalability and improve cost-effectiveness for customers. Through more than 11,000 employees, 130 operations and 35 million square feet of warehouse space, FedEx Supply Chain manages nearly 150 million packages and processes 358 million returns each year. For more information, go to supplychain.fedex.com.<br><br>We Have….<br><br>A strong FedEx brand consistently ranked among the world’s most admired and trusted employers.A top notch ...</code>	<code>We are a Generative AI Video start-up that is dedicated to making video animation accessible and affordable for music labels, artists, and creatives. Our team consists of creative, open minded, caring, and entrepreneurial individuals from all walks of life. On our iOS app we feature several templates and environments for you to transform to your liking by submitting a text-to-video prompt of what you want to be visualized. Additionally, users can upload their own pictures and videos to use as environments for our AI generated text-to-video prompt.<br><br>Our team is hiring for a Senior Applied AI Engineer with 4-6 yrs. of experience working in AI/ML, primarily with a recent emphasis on Gen AI and LLM integrated projects. You will help in the development of innovative generative techniques and advancing our research agenda. Additionally, by leveraging your knowledge of ML architecture you will contribute to end-to-end ML pipeline development, ML infrastructure, and the integration of diffusio...</code>
  <code>Senior Data Engineer</code>	<code>Job Type<br><br>Full-time<br><br>Description<br><br>At CeriFi, we empower professionals to supercharge their careers through technology-driven education. We provide financial and legal experts with cutting-edge training, certification, and continuing education opportunities. Our approach is laser-focused on student and customer success enabled by our innovative learning technologies and we're revolutionizing career development.<br><br>Join our dynamic team at CeriFi where EdTech innovation meets a vibrant remote work culture. As a tech-savvy company backed by Leeds Equity Partners, we are at the forefront of industry trends. Be part of a fun and collaborative environment that values creativity and embraces cutting-edge technologies.<br><br>Position Overview:<br><br>As a Senior Data Engineer, you will spearhead the development of a cutting-edge data platform for a next-generation learning experience platform. Leveraging proprietary data and advanced learning science techniques, you will focus on creating robust data pipel...</code>	<code>TITLE: Data Analyst LOCATION: Plainsboro, hybrid (2-3 days in-office per week)DURATION: 6 months with potential to extendSCHEDULE: 9 to 5 pm EST TIMEPay Range: <br>TOP MUST HAVES:1. Experience with Tableau2. Ability to present data with meaningful insight.3. Ability to function effectively in a fast-paced environment.<br>QUALIFICATIONSBachelor’s degree required; advanced degree preferred2+ years of analytics and reporting experience required, preferably in a pharmaceutical industry, - consumer packaged goods, or marketing organization consideredAble to create effective reports that present data in meaningful and cohesive story telling presentation for commercial team consumption – not just data dumpExperience manipulating and analyzing complex datasets including specialty pharmacy, Komodo, IQVIA (Xponent, DDD), Patient Level Claims Data, and other proprietary sourcesProficiency working with Tableau, Excel and other data manipulation and analysis platformsStrong PowerPoint and Excel skillsDem...</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Evaluation Dataset

ai-job-embedding-finetuning

• Dataset: ai-job-embedding-finetuning
• Size: 117 evaluation samples
• Columns: <code>title</code>, <code>description</code>, and <code>description_neg</code>
• Approximate statistics based on the first 117 samples:

  	title	description	description_neg
  type	string	string	string
  details	<ul><li>min: 4 tokens</li><li>mean: 7.07 tokens</li><li>max: 24 tokens</li></ul>	<ul><li>min: 39 tokens</li><li>mean: 420.56 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 14 tokens</li><li>mean: 416.93 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  title	description	description_neg
  <code>Senior Data Scientist, Google Cloud Support</code>	<code>Note: By applying to this position you will have an opportunity to share your preferred working location from the following: San Francisco, CA, USA; New York, NY, USA; Waterloo, ON, Canada.Minimum qualifications:<br><br>Bachelor's degree in Computer Science, Information Systems, related technical field, or equivalent practical experience.3 years of experience developing/deploying machine learning and time series forecasting models using statistical software (e.g., Python, R).3 years of experience applying statistical modeling, hypothesis testing, and experimentation.3 years of experience analyzing data, and working with SQL and databases.<br><br>Preferred qualifications:<br><br>Master's degree or PhD in Computer Science, Data Science, Mathematics, Economics, Physics, Engineering, Management Information Systems, Statistics, Accounting, or a similar field.Experience in product analytics, customer support, business intelligence, data science, or data warehousing.Ability to collaborate with internal stakeho...</code>	<code>We are seeking a professional who is looking to start a professional journey as a Loans Transformation Data Analyst with one of the largest Banking Corporation headquartered in NYC, NY.<br> <br>Industry: Banking<br> <br>Work Location: NYC, NY<br> <br>Job Title: Loans Transformation Data Analyst<br> <br>Duration: 12 months<br> <br>Function background / context:<br><br>ICM Lending Transformation is looking for an experienced Data Analyst, who is proactive, independent, and comfortable with identifying and resolving blockers.<br>Role includes creating and maintaining centralized SharePoint site and associated content for the overall Data Remediation Transformation Program.<br>Develop and maintain automated workflow tools to facilitate regulatory remediation efforts.<br>Support BAU and analytics processes.<br><br> <br>Responsibilities:<br><br>Create and maintain centralized SharePoint site and associated content for overall Data Remediation Transformation Program<br>Develop and maintain automated workflow tools to facilitate regulatory remediation eff...</code>
  <code>Office/Administration - Data Analyst Lv3 #: 24-02340</code>	<code>Job Title: Office/Administration - Data Analyst Lv3<br><br>Location: Wayzata, MN (Hybrid)<br><br>Duration: 6 Months on W2<br><br> Monday through Friday - 8:00-5:00 PM CST - Hybrid Schedule 2-3 days in the office.<br><br>Job Description<br><br>Client's Data Function is transforming their data platform and analytics foundation through the implementation of new data architecture, process, and standards. We are looking for a Data Platform Governance Analyst to play a significant role in the implementation and operations of the client's implementation of the data governance and compliance frameworks.<br><br>The role will focus on data as an asset (with a focus on ownership and compliance) while helping to identify & prioritize use cases for data which will contribute towards the longer-term governance roadmap for the data platform. Key areas of focus, responsibility, and contribution will be: Compliance Framework Design and Implementation, Data Platform Onboarding and Portfolio Governance, and Assurance of Auditability and Ob...</code>	<code>Company<br><br>Qualcomm Technologies, Inc.<br><br>Job Area<br><br>Engineering Group, Engineering Group > Machine Learning Engineering<br><br>General Summary<br><br>Create state-of-the-art machine learning development tools and software libraries. Design software libraries to assist in building and executing machine learning models. Develop computer algorithms to complete specific software tasks for cutting edge computer vision, speech, and machine learning experiences for the end users of our software stack. Build compiler toolchain to translate, convert and optimize machine learning models. Define and build user-facing application programming interfaces and software packages to enable users to interact with software. Interact with customers as needed and provide engineering roadmap to assist in prioritization of deliverables.<br><br>Minimum Qualifications<br><br> Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 4+ years of Hardware Engineering, Software Engineering, Systems Enginee...</code>
  <code>Data Analyst/Data Science/NLP (Intern apr 30) DIN01</code>	<code>The ideal candidate will use their passion for big data and analytics to provide insights to the business covering a range of topics. They will be responsible for conducting both recurring and ad hoc analysis for business users. ResponsibilitiesUnderstand the day-to-day issues that our business faces, which can be better understood with data Compile and analyze data related to business' issues Develop clear visualizations to convey complicated data in a straightforward fashion<br>QualificationsBachelor's or Master's degree in Statistics or Applied Mathematics or equivalent experience 1 - 2 years' Data Analysis experience Proficient in SQL</code>	<code>About Subaru Research and Development:Do you care about making social impacts through your job, like eliminating fatal accidents by improving safety driving systems, or reducing carbon emissions by developing new BEVs?Do your personal interests relate to road trips, going outdoors, off-road driving, hands-on work on cars, or rally and racing? If your answer is yes, then this job is right for you!<br>Subaru R&D is an innovation partner of SUBARU Corporation in Japan, and our mission is to serve as a R&D hub of the SUBARU Group. We strive to create products that ignite the hearts of our customers in North America market. We lead and support Subaru's next generation vehicle development by researching, prototyping, testing, and analyzing.<br>General Position Summary:Develops and directs software system tests, programming, and documentation. Analyzes North American customer data and technical trends to determine user demands and set target performance goals for future products, and coordinates te...</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• 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: 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: 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
• 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
• dispatch_batches: None
• split_batches: 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: no_duplicates
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.48.2
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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",
}

MultipleNegativesRankingLoss

@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.* -->