Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keywordbased queries. We propose a reinforcementlearning-driven translation model framework able to 1) learn the translation from NL expressions to queries in a supervised way, and, 2) to overcome the lack of large-scale dataset by framing the translation model as a word selection approach and injecting relevance feedback in the learning process. Experiments are carried out on two TREC datasets and outline the effectiveness of our approach.