Xinyan Zhao


2023

pdf bib
Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users
Yohan Jo | Xinyan Zhao | Arijit Biswas | Nikoletta Basiou | Vincent Auvray | Nikolaos Malandrakis | Angeliki Metallinou | Alexandros Potamianos
Findings of the Association for Computational Linguistics: EMNLP 2023

While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate development of such systems, we release the Multi-User MultiWOZ dataset: task-oriented dialogues among two users and one agent. To collect this dataset, each user utterance from MultiWOZ 2.2 was replaced with a small chat between two users that is semantically and pragmatically consistent with the original user utterance, thus resulting in the same dialogue state and system response. These dialogues reflect interesting dynamics of collaborative decision-making in task-oriented scenarios, e.g., social chatter and deliberation. Supported by this data, we propose the novel task of multi-user contextual query rewriting: to rewrite a task-oriented chat between two users as a concise task-oriented query that retains only task-relevant information and that is directly consumable by the dialogue system. We demonstrate that in multi-user dialogues, using predicted rewrites substantially improves dialogue state tracking without modifying existing dialogue systems that are trained for single-user dialogues. Further, this method surpasses training a medium-sized model directly on multi-user dialogues and generalizes to unseen domains.

pdf bib
Narrative Style and the Spread of Health Misinformation on Twitter
Achyutarama Ganti | Eslam Ali Hassan Hussein | Steven Wilson | Zexin Ma | Xinyan Zhao
Findings of the Association for Computational Linguistics: EMNLP 2023

Using a narrative style is an effective way to communicate health information both on and off social media. Given the amount of misinformation being spread online and its potential negative effects, it is crucial to investigate the interplay between narrative communication style and misinformative health content on user engagement on social media platforms. To explore this in the context of Twitter, we start with previously annotated health misinformation tweets (n 15,000) and annotate a subset of the data (n=3,000) for the presence of narrative style. We then use these manually assigned labels to train text classifiers, experimenting with supervised fine-tuning and in-context learning for automatic narrative detection. We use our best model to label remaining portion of the dataset, then statistically analyze the relationship between narrative style, misinformation, and user-level features on engagement, finding that narrative use is connected to increased tweet engagement and can, in some cases, lead to increased engagement with misinformation. Finally, we analyze the general categories of language used in narratives and health misinformation in our dataset.

2022

pdf bib
UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues
Xinyan Zhao | Bin He | Yasheng Wang | Yitong Li | Fei Mi | Yajiao Liu | Xin Jiang | Qun Liu | Huanhuan Chen
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering

With the advances in deep learning, tremendous progress has been made with chit-chat dialogue systems and task-oriented dialogue systems. However, these two systems are often tackled separately in current methods. To achieve more natural interaction with humans, dialogue systems need to be capable of both chatting and accomplishing tasks. To this end, we propose a unified dialogue system (UniDS) with the two aforementioned skills. In particular, we design a unified dialogue data schema, compatible for both chit-chat and task-oriented dialogues. Besides, we propose a two-stage training method to train UniDS based on the unified dialogue data schema. UniDS does not need to adding extra parameters to existing chit-chat dialogue systems. Experimental results demonstrate that the proposed UniDS works comparably well as the state-of-the-art chit-chat dialogue systems and task-oriented dialogue systems. More importantly, UniDS achieves better robustness than pure dialogue systems and satisfactory switch ability between two types of dialogues.

pdf bib
Narrative Detection and Feature Analysis in Online Health Communities
Achyutarama Ganti | Steven Wilson | Zexin Ma | Xinyan Zhao | Rong Ma
Proceedings of the 4th Workshop of Narrative Understanding (WNU2022)

Narratives have been shown to be an effective way to communicate health risks and promote health behavior change, and given the growing amount of health information being shared on social media, it is crucial to study health-related narratives in social media. However, expert identification of a large number of narrative texts is a time consuming process, and larger scale studies on the use of narratives may be enabled through automatic text classification approaches. Prior work has demonstrated that automatic narrative detection is possible, but modern deep learning approaches have not been used for this task in the domain of online health communities. Therefore, in this paper, we explore the use of deep learning methods to automatically classify the presence of narratives in social media posts, finding that they outperform previously proposed approaches. We also find that in many cases, these models generalize well across posts from different health organizations. Finally, in order to better understand the increase in performance achieved by deep learning models, we use feature analysis techniques to explore the features that most contribute to narrative detection for posts in online health communities.

2021

pdf bib
GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
Xinyan Zhao | Haibo Ding | Zhe Feng
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often requires a considerable amount of manual effort and domain expertise. To alleviate this problem, we propose GLARA, a graph-based labeling rule augmentation framework, to learn new labeling rules from unlabeled data. We first create a graph with nodes representing candidate rules extracted from unlabeled data. Then, we design a new graph neural network to augment labeling rules by exploring the semantic relations between rules. We finally apply the augmented rules on unlabeled data to generate weak labels and train a NER model using the weakly labeled data. We evaluate our method on three NER datasets and find that we can achieve an average improvement of +20% F1 score over the best baseline when given a small set of seed rules.

2020

pdf bib
Identifying Medication Abuse and Adverse Effects from Tweets: University of Michigan at #SMM4H 2020
V.G.Vinod Vydiswaran | Deahan Yu | Xinyan Zhao | Ermioni Carr | Jonathan Martindale | Jingcheng Xiao | Noha Ghannam | Matteo Althoen | Alexis Castellanos | Neel Patel | Daniel Vasquez
Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task

The team from the University of Michigan participated in three tasks in the Social Media Mining for Health Applications (#SMM4H) 2020 shared tasks – on detecting mentions of adverse effects (Task 2), extracting and normalizing them (Task 3), and detecting mentions of medication abuse (Task 4). Our approaches relied on a combination of traditional machine learning and deep learning models. On Tasks 2 and 4, our submitted runs performed at or above the task average.

pdf bib
PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
Jiazhao Li | Corey Lester | Xinyan Zhao | Yuting Ding | Yun Jiang | V.G.Vinod Vydiswaran
Findings of the Association for Computational Linguistics: EMNLP 2020

The language used by physicians and health professionals in prescription directions includes medical jargon and implicit directives and causes much confusion among patients. Human intervention to simplify the language at the pharmacies may introduce additional errors that can lead to potentially severe health outcomes. We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload. We evaluate the proposed approach over a dataset consisting of over 530K prescriptions obtained from a large mail-order pharmacy. The end-to-end system achieves a BLEU score of 60.27 against the reference directions generated by pharmacists, a 39.6% relative improvement over the rule-based normalization. Pharmacists judged 94.3% of the simplified directions as usable as-is or with minimal changes. This work demonstrates the feasibility of a machine translation-based tool for simplifying prescription directions in real-life.

2019

pdf bib
Identifying Adverse Drug Events Mentions in Tweets Using Attentive, Collocated, and Aggregated Medical Representation
Xinyan Zhao | Deahan Yu | V.G.Vinod Vydiswaran
Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task

Identifying mentions of medical concepts in social media is challenging because of high variability in free text. In this paper, we propose a novel neural network architecture, the Collocated LSTM with Attentive Pooling and Aggregated representation (CLAPA), that integrates a bidirectional LSTM model with attention and pooling strategy and utilizes the collocation information from training data to improve the representation of medical concepts. The collocation and aggregation layers improve the model performance on the task of identifying mentions of adverse drug events (ADE) in tweets. Using the dataset made available as part of the workshop shared task, we show that careful selection of neighborhood contexts can help uncover useful local information and improve the overall medical concept representation.