Users expect their queries to be answered by search systems, regardless of the query's surface form, which include keyword queries and natural questions.Natural Language Understanding (NLU) components of Search and QA systems may fail to correctly interpret semantically equivalent inputs if this deviates from how the system was trained, leading to suboptimal understanding capabilities.We propose the keyword-question rewriting task to improve query understanding capabilities of NLU systems for all surface forms.To achieve this, we present CycleKQR, an unsupervised approach, enabling effective rewriting between keyword and question queries using non-parallel data.Empirically we show the impact on QA performance of unfamiliar query forms for open domain and Knowledge Base QA systems (trained on either keywords or natural language questions).We demonstrate how CycleKQR significantly improves QA performance by rewriting queries into the appropriate form, while at the same time retaining the original semantic meaning of input queries, allowing CycleKQR to improve performance by up to 3% over supervised baselines.Finally, we release a dataset of 66k keyword-question pairs. 1 1 https://github.com/amzn/kqrHow much is iPhone 13?What is the price of iPhone 13? How much does iPhone 13 cost?iPhone 13 cost, cost of iPhone 13 iPhone 13 price, price of iPhone 13 iPhone 13 offer, iPhone 13dealQuestions

Named Entity Recognition (NER) is a crucial natural language understanding task for many down-stream tasks such as question answering and retrieval. Despite significant progress in developing NER models for multiple languages and domains, scaling to emerging and/or low-resource domains still remains challenging, due to the costly nature of acquiring training data. We propose CycleNER, an unsupervised approach based on cycle-consistency training that uses two functions: (i) sentence-to-entity – S2E and (ii) entity-to-sentence – E2S, to carry out the NER task. CycleNER does not require annotations but a set of sentences with no entity labels and another independent set of entity examples. Through cycle-consistency training, the output from one function is used as input for the other (e.g. S2E → E2S) to align the representation spaces of both functions and therefore enable unsupervised training. Evaluation on several domains comparing CycleNER against supervised and unsupervised competitors shows that CycleNER achieves highly competitive performance with only a few thousand input sentences. We demonstrate competitive performance against supervised models, achieving 73% of supervised performance without any annotations on CoNLL03, while significantly outperforming unsupervised approaches.

In my Ph.D. work, my objective is to improve the state of the art in Conversational Recommender Systems, by proposing a model that closely follows the process that people enact when searching for products and services. Rich user profiles are elicited using natural language dialogue. Item descriptions will be extracted from a combination of structured and unstructured data such as user reviews. Natural language explanations will ensure that users can quickly understand the reasoning behind the recommendations. Interactive explanation will then allow them to further compare several alternatives. This extended abstract presents the motivations of my work, it details the research plan, and the research questions. Finally, it shows some preliminary results, and outlines the next steps for my Ph.D. program.