Rasa: Open Source Language Understanding and Dialogue Management

By Tom Bocklisch, Joe Faulkner, Nick Pawlowski, Alan Nichol. 2017

487 citations recorded by the source corpus.

We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software. Their purpose is to make machine-learning based dialogue management and language understanding accessible to non-specialist software developers. In terms of design philosophy, we aim for ease of use, and bootstrapping from minimal (or no) initial training data. Both packages are extensively documented and ship with a comprehensive suite of tests. The code is available at this https URL

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “RASA: Open source language understanding and dialogue management.”
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize (2018, methodology): “JS, Python, and Java SDKs of the Alexa Skills Kit or ASK (Kumar et al., 2017), as well as general dialog toolkits like Rasa (Bocklisch et al., 2017) and DeepPavlov (Burtsev et al., 2017).”
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces (2018, background): “AI now Google’s Dialogflow), and the open-source platform Rasa NLU [7].”
NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails (2023, methodology): “Building task-oriented dialogue agents generally requires two components: a Natural Language Understanding (NLU) and a Dialogue Management (DM) engine (Bocklisch et al., 2017; Liu et al., 2021).”
SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model (2020, methodology): “For example, recent attempts such as RASA (Bocklisch et al., 2017), ConvLab (Lee et al., 2019; Zhu et al., 2020), and Conversation Learner (Shukla et al., 2020) have been made to allow the use of data-driven approaches based on machine learning or machine teaching for the development of dialog modul”
A Survey on Intent-Based Networking (2023, methodology): “In IBN, NLP is often applied to IBNSs that provide a chatbot-like conversational interface (e.g., DialogFlow [58], Slack [59], Rasa [60], etc.) enabling the user to express her intent in a natural language.”
Further Advances in Open Domain Dialog Systems in the Third Alexa Prize Socialbot Grand Challenge (2020, methodology): “, 2017), as well as general dialog toolkits like Rasa (Bocklisch et al., 2017) and DeepPavlov (Burtsev et al.”
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020, background): “…toolkits focus on either end-to-end models (Miller et al., 2017) or one specific component such as dialogue policy (POL) (Ultes et al., 2017), while the others toolkits that are designed for developers (Bocklisch et al., 2017; Papangelis et al., 2020) do not have state-of-the-art models integrated.”
Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management (2020, background): “Data augmentation for dialogue management is relatively unexplored and limited to increasing training data volume with (random) data duplication/recombination (Bocklisch et al., 2017) or general machine learning data transformations such as oversampling and downsampling of existing samples (Chawla e”
Dialogue Transformers (2019, methodology): “All experiments are performed using the Rasa framework [19] and all code, hyperparameters, and data required to reproduce these experiments are available online at https://github.com/ RasaHQ/TED-paper .”