Zhenduo Wang

Zhenduo Wang, Yuancheng Tu, Corby Rosset et al. · tsinghua

A long-standing challenge for search and conversational assistants is query intention detection in ambiguous queries. Asking clarifying questions in conversational search has been widely studied and considered an effective solution to resolve query ambiguity. Existing work have explored various approaches for clarifying question ranking and generation. However, due to the lack of real conversational search data, they have to use artificial datasets for training, which limits their generalizability to real-world search scenarios. As a result, the industry has shown reluctance to implement them in reality, further suspending the availability of real conversational search interaction data. The above dilemma can be formulated as a cold start problem of clarifying question generation and conversational search in general. Furthermore, even if we do have large-scale conversational logs, it is not realistic to gather training data that can comprehensively cover all possible queries and topics in open-domain search scenarios. The risk of fitting bias when training a clarifying question retrieval/generation model on incomprehensive dataset is thus another important challenge. In this work, we innovatively explore generating clarifying questions in a zero-shot setting to overcome the cold start problem and we propose a constrained clarifying question generation system which uses both question templates and query facets to guide the effective and precise question generation. The experiment results show that our method outperforms existing state-of-the-art zero-shot baselines by a large margin. Human annotations to our model outputs also indicate our method generates 25.2\% more natural questions, 18.1\% more useful questions, 6.1\% less unnatural and 4\% less useless questions.

Zhenduo Wang, Yasser Abduallah, Jason T. L. Wang et al.

The F10.7 and F30 solar indices are the solar radio fluxes measured at wavelengths of 10.7 cm and 30 cm, respectively, which are key indicators of solar activity. F10.7 is valuable for explaining the impact of solar ultraviolet (UV) radiation on the upper atmosphere of Earth, while F30 is more sensitive and could improve the reaction of thermospheric density to solar stimulation. In this study, we present a new deep learning model, named the Solar Index Network, or SINet for short, to predict daily values of the F10.7 and F30 solar indices. The SINet model is designed to make medium-term predictions of the index values (1-60 days in advance). The observed data used for SINet training were taken from the National Oceanic and Atmospheric Administration (NOAA) as well as Toyokawa and Nobeyama facilities. Our experimental results show that SINet performs better than five closely related statistical and deep learning methods for the prediction of F10.7. Furthermore, to our knowledge, this is the first time deep learning has been used to predict the F30 solar index.

Khalid A. Alobaid, Jason T. L. Wang, Haimin Wang et al.

The application of machine learning to the study of coronal mass ejections (CMEs) and their impacts on Earth has seen significant growth recently. Understanding and forecasting CME geoeffectiveness is crucial for protecting infrastructure in space and ensuring the resilience of technological systems on Earth. Here we present GeoCME, a deep-learning framework designed to predict, deterministically or probabilistically, whether a CME event that arrives at Earth will cause a geomagnetic storm. A geomagnetic storm is defined as a disturbance of the Earth's magnetosphere during which the minimum Dst index value is less than -50 nT. GeoCME is trained on observations from the instruments including LASCO C2, EIT and MDI on board the Solar and Heliospheric Observatory (SOHO), focusing on a dataset that includes 136 halo/partial halo CMEs in Solar Cycle 23. Using ensemble and transfer learning techniques, GeoCME is capable of extracting features hidden in the SOHO observations and making predictions based on the learned features. Our experimental results demonstrate the good performance of GeoCME, achieving a Matthew's correlation coefficient of 0.807 and a true skill statistics score of 0.714 when the tool is used as a deterministic prediction model. When the tool is used as a probabilistic forecasting model, it achieves a Brier score of 0.094 and a Brier skill score of 0.493. These results are promising, showing that the proposed GeoCME can help enhance our understanding of CME-triggered solar-terrestrial interactions.

Zhenduo Wang, Qingyao Ai

In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on identifying the need of asking clarifying questions and methodologies of generating them. These works assume asking clarifying questions is a safe alternative to retrieving results. As existing conversational search models are far from perfect, it's possible and common that they could retrieve or generate bad clarifying questions. Asking too many clarifying questions can also drain user's patience when the user prefers searching efficiency over correctness. Hence, these models can get backfired and harm user's search experience because of these risks by asking clarifying questions. In this work, we propose a simulation framework to simulate the risk of asking questions in conversational search and further revise a risk-aware conversational search model to control the risk. We show the model's robustness and effectiveness through extensive experiments on three conversations datasets, including MSDialog, Ubuntu Dialog Corpus, and Opendialkg in which we compare it with multiple baselines. We show that the risk-control module can work with two different re-ranker models and outperform all the baselines in most of our experiments.

Zhenduo Wang, Qingyao Ai

Users often formulate their search queries with immature language without well-developed keywords and complete structures. Such queries fail to express their true information needs and raise ambiguity as fragmental language often yield various interpretations and aspects. This gives search engines a hard time processing and understanding the query, and eventually leads to unsatisfactory retrieval results. An alternative approach to direct answer while facing an ambiguous query is to proactively ask clarifying questions to the user. Recent years have seen many works and shared tasks from both NLP and IR community about identifying the need for asking clarifying question and methodology to generate them. An often neglected fact by these works is that although sometimes the need for clarifying questions is correctly recognized, the clarifying questions these system generate are still off-topic and dissatisfaction provoking to users and may just cause users to leave the conversation. In this work, we propose a risk-aware conversational search agent model to balance the risk of answering user's query and asking clarifying questions. The agent is fully aware that asking clarifying questions can potentially collect more information from user, but it will compare all the choices it has and evaluate the risks. Only after then, it will make decision between answering or asking. To demonstrate that our system is able to retrieve better answers, we conduct experiments on the MSDialog dataset which contains real-world customer service conversations from Microsoft products community. We also purpose a reinforcement learning strategy which allows us to train our model on the original dataset directly and saves us from any further data annotation efforts. Our experiment results show that our risk-aware conversational search agent is able to significantly outperform strong non-risk-aware baselines.

Zhenduo Wang, Ted Pedersen

This paper describes the UMDSub system that participated in Task 2 of SemEval-2018. We developed a system that predicts an emoji given the raw text in a English tweet. The system is a Multi-channel Convolutional Neural Network based on subword embeddings for the representation of tweets. This model improves on character or word based methods by about 2\%. Our system placed 21st of 48 participating systems in the official evaluation.