Programming bots by synthesizing natural language expressions into API invocations

Zamanirad, Shayan; Benatallah, Boualem; Barukh, Moshe Chai; Casati, Fabio; Rodríguez, Carlos

doi:10.1109/ase.2017.8115694

Cited by 24 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…", the intent is to know the commits that modified the Utilities file. One of the approaches (e.g., [53]) to extract the intents is to use Word Embeddings more preciously Word2Vec model [33]. The model takes a text corpus as input and outputs a vector space where each word in the corpus is represented by a vector.…”

Section: Intent Extractormentioning

confidence: 99%

MSRBot: Using bots to answer questions from software repositories

Abdellatif¹,

Badran²,

Shihab³

2020

Empir Software Eng

View full text Add to dashboard Cite

Software repositories contain a plethora of useful information that can be used to enhance software projects. Prior work has leveraged repository data to improve many aspects of the software development process, such as, help extract requirement decisions, identify potentially defective code and improve maintenance and evolution. However, in many cases, practitioners are not able to fully benefit from software repositories due to the fact that they need special expertise and dedicated effort to mine their repositories.Therefore, in this paper, we use bots to automate and ease the process of extracting useful information from software repositories. Particularly, we lay out an approach of how bots, layered on top of software repositories, can be used to answer some of the most common software development/maintenance questions facing developers. We perform a preliminary study with 12 participants to validate the effectiveness of the bot. Our findings indicate that using bots achieves very promising results in terms of answer accuracy, speed and usefulness. Our work has the potential to transform the MSR field by significantly lowering the barrier to entry, making the extraction of useful information from software repositories as easy as chatting with a bot.

show abstract

Section: Intent Extractormentioning

confidence: 99%

MSRBot: Using bots to answer questions from software repositories

Abdellatif¹,

Badran²,

Shihab³

2020

Empir Software Eng

View full text Add to dashboard Cite

show abstract

“…The assumption here is that user provides all the required information (e.g. slots 4 /values) at once, in one single utterance [30]. Thus, each utterance from user (e.g.…”

Section: Human-chatbot Conversationsmentioning

confidence: 99%

State Machine Based Human-Bot Conversation Model and Services

Zamanirad

Benatallah

Rodríguez

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Task-oriented virtual assistants (or simply chatbots) are in very high demand these days. They employ third-party APIs to serve end-users via natural language interactions. Chatbots are famed for their easy-to-use interface and gentle learning curve (it only requires one of humans' most innate ability, the use of natural language). Studies on human conversation patterns show, however, that day-today dialogues are of multi-turn and multi-intent nature, which pushes the need for chatbots that are more resilient and flexible to this style of conversations. In this paper, we propose the idea of leveraging Conversational State Machine to make it a core part of chatbots' conversation engine by formulating conversations as a sequence of states. Here, each state covers an intent and contains a nested state machine to help manage tasks associated to the conversation intent. Such enhanced conversation engine, together with a novel technique to spot implicit information from dialogues (by exploiting Dialog Acts), allows chatbots to manage tangled conversation situations where most existing chatbot technologies fail.

show abstract

“…Little and Miller [11] generate Java code from a set of brief keywords. Some synthesis approaches are focused on particular domains or technologies: e.g., SQL query generation [12], smartphone automation script synthesis [13], bot API invocations [14]. All of the mentioned approaches perceive APIs as black boxes, which are already designed.…”

Section: Related Workmentioning

confidence: 99%

Designing Voice-Controllable APIs

Sulír

Porubãn

2019

2019 IEEE 15th International Scientific Conference on Informatics

View full text Add to dashboard Cite

The main purpose of a voice command system is to process a sentence in natural language and perform the corresponding action. Although there exist many approaches to map sentences to API (application programming interface) calls, this mapping is usually performed after the API is already implemented, possibly by other programmers. In this paper, we describe how the API developer can use patterns to map sentences to API calls by utilizing the similarities between names and types in the sentences and the API. In the cases when the mapping is not straightforward, we suggest the usage of suitable annotations (attribute-oriented programming).

show abstract

Programming bots by synthesizing natural language expressions into API invocations

Cited by 24 publications

References 14 publications

MSRBot: Using bots to answer questions from software repositories

MSRBot: Using bots to answer questions from software repositories

State Machine Based Human-Bot Conversation Model and Services

Designing Voice-Controllable APIs

Contact Info

Product

Resources

About