Dialogue Management for Interactive API Search
This addresses the challenge for programmers who struggle to find API components by developing interactive tools that emulate human-like conversational assistance, though it is incremental as it builds on existing interactive search concepts.
The paper tackles the problem of dialogue management for interactive API search by presenting a dialogue manager that uses search results and dialogue history to select efficient actions, implementing both hand-crafted and reinforcement learning policies, and evaluating them against a baseline single-turn policy in synthetic and human evaluations.
API search involves finding components in an API that are relevant to a programming task. For example, a programmer may need a function in a C library that opens a new network connection, then another function that sends data across that connection. Unfortunately, programmers often have trouble finding the API components that they need. A strong scientific consensus is emerging towards developing interactive tool support that responds to conversational feedback, emulating the experience of asking a fellow human programmer for help. A major barrier to creating these interactive tools is implementing dialogue management for API search. Dialogue management involves determining how a system should respond to user input, such as whether to ask a clarification question or to display potential results. In this paper, we present a dialogue manager for interactive API search that considers search results and dialogue history to select efficient actions. We implement two dialogue policies: a hand-crafted policy and a policy optimized via reinforcement learning. We perform a synthetics evaluation and a human evaluation comparing the policies to a generic single-turn, top-N policy used by source code search engines.