Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are usually trained and tested on benchmarks of gold QA pairs. This implies that training is limited to surface forms seen in the respective datasets, and evaluation is on a small set of held-out questions. Through our proposed framework REIGN, we take several steps to remedy this restricted learning setup. First, we systematically generate reformulations of training questions to increase robustness of models to surface form variations. This is a particularly challenging problem, given the incomplete nature of such questions. Second, we guide ConvQA models towards higher performance by feeding it only those reformulations that help improve their answering quality, using deep reinforcement learning. Third, we demonstrate the viability of training major model components on one benchmark and applying them zero-shot to another. Finally, for a rigorous evaluation of robustness for trained models, we use and release large numbers of diverse reformulations generated by prompting ChatGPT for benchmark test sets (resulting in 20x increase in sizes). Our findings show that ConvQA models with robust training via reformulations significantly outperform those with standard training from gold QA pairs only.

The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp question-answer pairs found in popular benchmarks. In reality, however, such training data is hard to come by: users would rarely mark answers explicitly as correct or wrong. In this work, we take a step towards a more natural learning paradigm - from noisy and implicit feedback via question reformulations. A reformulation is likely to be triggered by an incorrect system response, whereas a new follow-up question could be a positive signal on the previous turn's answer. We present a reinforcement learning model, termed CONQUER, that can learn from a conversational stream of questions and reformulations. CONQUER models the answering process as multiple agents walking in parallel on the KG, where the walks are determined by actions sampled using a policy network. This policy network takes the question along with the conversational context as inputs and is trained via noisy rewards obtained from the reformulation likelihood. To evaluate CONQUER, we create and release ConvRef, a benchmark with about 11k natural conversations containing around 205k reformulations. Experiments show that CONQUER successfully learns from noisy reward signals, significantly improving over a state-of-the-art baseline.

This PhD thesis will explore conversational question answering with a special emphasis on incorporating user feedback. As preliminary work, we developed a conversational passage retrieval system in the scope of the TREC Conversational Assistance Track 2019. Our current focus is to develop methods based on reinforcement learning to incorporate implicit user feedback in form of question reformulations for conversational QA over knowledge graphs. Finally, we plan to design a conversational QA system operating on heterogeneous sources.

Question answering (QA) over text passages is a problem of longstanding interest in information retrieval. Recently, the conversational setting has attracted attention, where a user asks a sequence of questions to satisfy her information needs around a topic. While this setup is a natural one and similar to humans conversing with each other, it introduces a key research challenge: understanding the context left implicit by the user in follow-up questions. In this work, we demonstrate CROWN (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns. To this end, CROWN first builds a word proximity network (WPN) from large corpora to store statistically significant term co-occurrences. At answering time, passages are ranked by a combination of their similarity to the question, and coherence of query terms within: these factors are measured by reading off node and edge weights from the WPN. CROWN provides an interface that is both intuitive for end-users, and insightful for experts for reconfiguration to individual setups. CROWN was evaluated on TREC CAsT data, where it achieved above-median performance in a pool of neural methods.

Research on multimodal systems for human-robot interaction mostly focuses on the processing of inputs. Yet, the output is equally important: A robot that is able to use different modalities in an interaction appears more natural and can be understood more easily. In this paper, we present our multimodal fission framework, called MMF framework, which is a framework for incorporating planning criteria to select the most suitable set of modalities based on information about the interaction context. We describe our input and output layer, present an algorithm for an automated selection of suitable attributes for referencing objects verbally as well as a simple assessment of the suitability of pointing gestures in the given context. Furthermore, we describe a new approach for the modality and device selection as formulation of constraint optimization problems. In the end, we will report the results of a user study, which has been conducted to evaluate the generated multimodal output.