arXiv subjects

Yifei Yuan

Publications and source records attributed to Yifei Yuan.

53 records · Page 3Linked to original sources

arXiv2024

Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search

In mixed-initiative conversational search systems, clarifying questions are used to help users who struggle to express their intentions in a single query. These questions aim to uncover user's information needs and resolve query ambiguities. We hypothesize that in scenarios where multimodal information is pertinent, the clarification process can be improved by using non-textual information. Therefore, we propose to add images to clarifying questions and formulate the novel task of asking multimodal clarifying questions in open-domain, mixed-initiative conversational search systems. To facilitate research into this task, we collect a dataset named Melon that contains over 4k multimodal clarifying questions, enriched with over 14k images. We also propose a multimodal query clarification model named Marto and adopt a prompt-based, generative fine-tuning strategy to perform the training of different stages with different prompts. Several analyses are conducted to understand the importance of multimodal contents during the query clarification phase. Experimental results indicate that the addition of images leads to significant improvements of up to 90% in retrieval performance when selecting the relevant images. Extensive analyses are also performed to show the superiority of Marto compared with discriminative baselines in terms of effectiveness and efficiency.

cs.CL↗

arXiv2023

Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions

Conversational question-answering (CQA) systems aim to create interactive search systems that effectively retrieve information by interacting with users. To replicate human-to-human conversations, existing work uses human annotators to play the roles of the questioner (student) and the answerer (teacher). Despite its effectiveness, challenges exist as human annotation is time-consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of large language models (LLMs) in CQA simulation, we propose a simulation framework that employs zero-shot learner LLMs for simulating teacher-student interactions. Our framework involves two LLMs interacting on a specific topic, with the first LLM acting as a student, generating questions to explore a given search topic. The second LLM plays the role of a teacher by answering questions and is equipped with additional information, including a text on the given topic. We implement both the student and teacher by zero-shot prompting the GPT-4 model. To assess the effectiveness of LLMs in simulating CQA interactions and understand the disparities between LLM- and human-generated conversations, we evaluate the simulated data from various perspectives. We begin by evaluating the teacher's performance through both automatic and human assessment. Next, we evaluate the performance of the student, analyzing and comparing the disparities between questions generated by the LLM and those generated by humans. Furthermore, we conduct extensive analyses to thoroughly examine the LLM performance by benchmarking state-of-the-art reading comprehension models on both datasets. Our results reveal that the teacher LLM generates lengthier answers that tend to be more accurate and complete. The student LLM generates more diverse questions, covering more aspects of a given topic.

cs.CL↗

arXiv2023

Social Media Fashion Knowledge Extraction as Captioning

Social media plays a significant role in boosting the fashion industry, where a massive amount of fashion-related posts are generated every day. In order to obtain the rich fashion information from the posts, we study the task of social media fashion knowledge extraction. Fashion knowledge, which typically consists of the occasion, person attributes, and fashion item information, can be effectively represented as a set of tuples. Most previous studies on fashion knowledge extraction are based on the fashion product images without considering the rich text information in social media posts. Existing work on fashion knowledge extraction in social media is classification-based and requires to manually determine a set of fashion knowledge categories in advance. In our work, we propose to cast the task as a captioning problem to capture the interplay of the multimodal post information. Specifically, we transform the fashion knowledge tuples into a natural language caption with a sentence transformation method. Our framework then aims to generate the sentence-based fashion knowledge directly from the social media post. Inspired by the big success of pre-trained models, we build our model based on a multimodal pre-trained generative model and design several auxiliary tasks for enhancing the knowledge extraction. Since there is no existing dataset which can be directly borrowed to our task, we introduce a dataset consisting of social media posts with manual fashion knowledge annotation. Extensive experiments are conducted to demonstrate the effectiveness of our model.

cs.CL↗

arXiv2023

VoxelMap++: Mergeable Voxel Mapping Method for Online LiDAR(-inertial) Odometry

This paper presents VoxelMap++: a voxel mapping method with plane merging which can effectively improve the accuracy and efficiency of LiDAR(-inertial) based simultaneous localization and mapping (SLAM). This map is a collection of voxels that contains one plane feature with 3DOF representation and corresponding covariance estimation. Considering total map will contain a large number of coplanar features (kid planes), these kid planes' 3DOF estimation can be regarded as the measurements with covariance of a larger plane (father plane). Thus, we design a plane merging module based on union-find which can save resources and further improve the accuracy of plane fitting. This module can distinguish the kid planes in different voxels and merge these kid planes to estimate the father plane. After merging, the father plane 3DOF representation will be more accurate than the kids plane and the uncertainty will decrease significantly which can further improve the performance of LiDAR(-inertial) odometry. Experiments on challenging environments such as corridors and forests demonstrate the high accuracy and efficiency of our method compared to other state-of-the-art methods (see our attached video). By the way, our implementation VoxelMap++ is open-sourced on GitHub which is applicable for both non-repetitive scanning LiDARs and traditional scanning LiDAR.

cs.RO↗

arXiv2023

Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations

Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiative ESC where the user and system can both take the initiative in leading the conversation. Specifically, we conduct a novel analysis on mixed-initiative ESC systems with a tailor-designed schema that divides utterances into different types with speaker roles and initiative types. Four emotional support metrics are proposed to evaluate the mixed-initiative interactions. The analysis reveals the necessity and challenges of building mixed-initiative ESC systems. In the light of this, we propose a knowledge-enhanced mixed-initiative framework (KEMI) for ESC, which retrieves actual case knowledge from a large-scale mental health knowledge graph for generating mixed-initiative responses. Experimental results on two ESC datasets show the superiority of KEMI in both content-preserving evaluation and mixed initiative related analyses.

cs.CL↗

arXiv2022

McQueen: a Benchmark for Multimodal Conversational Query Rewrite

The task of query rewrite aims to convert an in-context query to its fully-specified version where ellipsis and coreference are completed and referred-back according to the history context. Although much progress has been made, less efforts have been paid to real scenario conversations that involve drawing information from more than one modalities. In this paper, we propose the task of multimodal conversational query rewrite (McQR), which performs query rewrite under the multimodal visual conversation setting. We collect a large-scale dataset named McQueen based on manual annotation, which contains 15k visual conversations and over 80k queries where each one is associated with a fully-specified rewrite version. In addition, for entities appearing in the rewrite, we provide the corresponding image box annotation. We then use the McQueen dataset to benchmark a state-of-the-art method for effectively tackling the McQR task, which is based on a multimodal pre-trained model with pointer generator. Extensive experiments are performed to demonstrate the effectiveness of our model on this task\footnote{The dataset and code of this paper are both available in \url{https://github.com/yfyuan01/MQR}

cs.CL↗

arXiv2022

System-level Simulation of Reconfigurable Intelligent Surface assisted Wireless Communications System

Reconfigurable intelligent surface (RIS) is an emerging technique employing metasurface to reflect the signal from the source node to the destination node. By smartly reconfiguring the electromagnetic (EM) properties of the metasurface and adjusting the EM parameters of the reflected radio waves, RIS can turn the uncontrollable propagation environment into an artificially reconfigurable space, and thus, can significantly increase the communications capacity and improve the coverage of the system. In this paper, we investigate the far field channel in which the line-of-sight (LOS) propagation is dominant. We propose an antenna model that can characterize the radiation patterns of realistic RIS elements, and consider the signal power received from the two-hop path through RIS. System-level simulations of network performance under various scenarios and parameter.

cs.IT↗

arXiv2022

Generalized Polarization Transform: A Novel Coded Transmission Paradigm

For the upcoming 6G wireless networks, a new wave of applications and services will demand ultra-high data rates and reliability. To this end, future wireless systems are expected to pave the way for entirely new fundamental air interface technologies to attain a breakthrough in spectrum efficiency (SE). This article discusses a new paradigm, named generalized polarization transform (GPT), to achieve an integrated design of coding, modulation, multi-antenna, multiple access, etc., in a real sense. The GPT enabled air interface develops far-reaching insights that the joint optimization of critical air interface ingredients can achieve remarkable gains on SE compared with the state-of-the-art module-stacking design.

cs.IT↗

arXiv2022

Joint Successive Cancellation List Decoding for the Double Polar codes

As a new joint source-channel coding scheme, the double polar (D-Polar) codes have been proposed recently. In this letter, a novel joint source-channel decoder, namely the joint successive cancellation list (J-SCL) decoder, is proposed to improve the decoding performance of the D-Polar codes. We merge the trellis of the source polar code and that of the channel polar code to construct a compound trellis. In this compound trellis, the joint source-channel nodes represent both of the information bits and the high-entropy bits. Based on the compound trellis, the J-SCL decoder is designed to recover the source messages by combining the source SCL decoding and channel SCL decoding. The J-SCL decoder doubles the number of the decoding paths at each decoding level and then reserves the L paths with the smallest joint path-metric (JPM). For the JSC node, the JPM is updated considering both the channel decision log-likelihood ratios (LLRs) and the source decision LLRs. Simulation results show that the J-SCL decoder outperforms the turbo-like BP (TL-BP) decoder with lower complexity.

cs.IT↗

arXiv2021

Sentiment Analysis of Fashion Related Posts in Social Media

The role of social media in fashion industry has been blooming as the years have continued on. In this work, we investigate sentiment analysis for fashion related posts in social media platforms. There are two main challenges of this task. On the first place, information of different modalities must be jointly considered to make the final predictions. On the second place, some unique fashion related attributes should be taken into account. While most existing works focus on traditional multimodal sentiment analysis, they always fail to exploit the fashion related attributes in this task. We propose a novel framework that jointly leverages the image vision, post text, as well as fashion attribute modality to determine the sentiment category. One characteristic of our model is that it extracts fashion attributes and integrates them with the image vision information for effective representation. Furthermore, it exploits the mutual relationship between the fashion attributes and the post texts via a mutual attention mechanism. Since there is no existing dataset suitable for this task, we prepare a large-scale sentiment analysis dataset of over 12k fashion related social media posts. Extensive experiments are conducted to demonstrate the effectiveness of our model.

cs.CL↗

arXiv2021

Aspect Sentiment Quad Prediction as Paraphrase Generation

Aspect-based sentiment analysis (ABSA) has been extensively studied in recent years, which typically involves four fundamental sentiment elements, including the aspect category, aspect term, opinion term, and sentiment polarity. Existing studies usually consider the detection of partial sentiment elements, instead of predicting the four elements in one shot. In this work, we introduce the Aspect Sentiment Quad Prediction (ASQP) task, aiming to jointly detect all sentiment elements in quads for a given opinionated sentence, which can reveal a more comprehensive and complete aspect-level sentiment structure. We further propose a novel \textsc{Paraphrase} modeling paradigm to cast the ASQP task to a paraphrase generation process. On one hand, the generation formulation allows solving ASQP in an end-to-end manner, alleviating the potential error propagation in the pipeline solution. On the other hand, the semantics of the sentiment elements can be fully exploited by learning to generate them in the natural language form. Extensive experiments on benchmark datasets show the superiority of our proposed method and the capacity of cross-task transfer with the proposed unified \textsc{Paraphrase} modeling framework.

cs.CL↗

arXiv2021

A Path to Smart Radio Environments: An Industrial Viewpoint on Reconfigurable Intelligent Surfaces

With both the standardization and commercialization completed in an unforeseen pace for the 5th generation (5G) wireless network, researchers, engineers and executives from the academia and the industry have turned their sights on candidate technologies to support the next generation wireless networks. Reconfigurable intelligent surfaces (RIS), sometimes referred to as intelligent reflecting surfaces (IRS), have been identified to be potential components of the future wireless networks because they can reconfigure the propagation environment for wireless signals with low-cost passive devices. In doing so, the coverage of a cell can be expected to increase significantly as well as the overall throughput of the network. RIS has not only become an attractive research area but also triggered a couple of projects to develop appropriate solutions to enable the set-up of hardware demonstrations and prototypes. In parallel, technical discussions and activities towards standardization already took off in some regions. Promoting RIS to be integrated into future commercial networks and become a commercial success requires significant standardization work taken place both at regional level standards developing organizations (SDO) and international SDOs such as the 3rd Generation Partnership Project (3GPP). While many research papers study how RIS can be used and optimized, few effort is devoted to analyzing the challenges to commercialize RIS and how RIS can be standardized. This paper intends to shed some light on RIS from an industrial viewpoint and provide a clear roadmap to make RIS industrially feasible.

cs.NI↗

arXiv2021

Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback

We study the task of conversational fashion image retrieval via multiturn natural language feedback. Most previous studies are based on single-turn settings. Existing models on multiturn conversational fashion image retrieval have limitations, such as employing traditional models, and leading to ineffective performance. We propose a novel framework that can effectively handle conversational fashion image retrieval with multiturn natural language feedback texts. One characteristic of the framework is that it searches for candidate images based on exploitation of the encoded reference image and feedback text information together with the conversation history. Furthermore, the image fashion attribute information is leveraged via a mutual attention strategy. Since there is no existing fashion dataset suitable for the multiturn setting of our task, we derive a large-scale multiturn fashion dataset via additional manual annotation efforts on an existing single-turn dataset. The experiments show that our proposed model significantly outperforms existing state-of-the-art methods.

cs.CV↗

arXiv2021

NOMA for Next-generation Massive IoT: Performance Potential and Technology Directions

Broader applications of the Internet of Things (IoT) are expected in the forthcoming 6G system, although massive IoT is already a key scenario in 5G, predominantly relying on physical layer solutions inherited from 4G LTE and primarily using orthogonal multiple access (OMA). In 6G IoT, supporting a massive number of connections will be required for diverse services of the vertical sectors, prompting fundamental studies on how to improve the spectral efficiency of the system. One of the key enabling technologies is non-orthogonal multiple access (NOMA). This paper consists of two parts. In the first part, finite block length theory and the diversity order of multi-user systems will be used to show the significant potential of NOMA compared to traditional OMA. The supremacy of NOMA over OMA is particularly pronounced for asynchronous contention-based systems relying on imperfect link adaptation, which are commonly assumed for massive IoT systems. To approach these performance bounds, in the second part of the paper, several promising technology directions are proposed for 6G massive IoT, including linear spreading, joint spreading & modulation, multi-user channel coding in the context of various techniques for practical uncoordinated transmissions, cell-free operations, etc., from the perspective of NOMA.

cs.IT↗

arXiv2021

Performance Comparison between Reconfigurable Intelligent Surface and Relays: Theoretical Methods and a Perspective from Operator

Reconfigurable intelligent surface (RIS) is an emerging technique employing metasurface to reflect the signal from the source node to the destination node without consuming any energy. Not only the spectral efficiency but also the energy efficiency can be improved through RIS. Essentially, RIS can be considered as a passive relay between the source and destination node. On the other hand, a relay node in a traditional relay network has to be active, which indicates that it will consume energy when it is relaying the signal or information between the source and destination nodes. In this paper, we compare the performances between RIS and active relay for a general multiple-input multiple-output (MIMO) system. To make the comparison fair and comprehensive, both the performances of RIS and active relay are optimized with best-effort. In terms of the RIS, transmit beamforming and reflecting coefficient at the RIS are jointly optimized so as to maximize the end-to-end throughput. Although the optimization problem is non-convex, it is transformed equivalently to a weighted mean-square error (MSE) minimization problem and an alternating optimization problem is proposed, which can ensure the convergence to a stationary point. In terms of active relay, both half duplex relay (HDR) and full duplex relay (FDR) are considered. End-to-end throughput is maximized via an alternating optimization method. Numerical results are presented to demonstrate the effectiveness of the proposed algorithm. Finally, comparisons between RIS and relays are investigated from the perspective of system model, performance, deployment and controlling method.

cs.IT↗

arXiv2020

Potential Key Technologies for 6G Mobile Communications

The standard development of 5G wireless communication culminated between 2017 and 2019, followed by the worldwide deployment of 5G networks, which is expected to result in very high data rate for enhanced mobile broadband, support ultra-reliable and low-latency services and accommodate massive number of connections. Research attention is shifting to future generation of wireless communications, for instance, beyond 5G or 6G. Unlike previous papers, which discussed the use cases, deployment scenarios, or new network architectures of 6G in depth, this paper focuses on a few potential technologies for 6G wireless communications, all of which represent certain fundamental breakthrough at the physical layer-technical hardcore of any new generation of wireless communications. Some of them, such as holographic radio, terahertz communication, large intelligent surface, and orbital angular momentum, are of revolutionary nature and many related studies are still at their scientific exploration stage. Several technical areas, such as advanced channel coding and modulation, visible light communication, and advanced duplex, while having been studied, may find more opportunities in 6G.

cs.IT↗

arXiv2012

Regular Functions, Cost Register Automata, and Generalized Min-Cost Problems

Motivated by the successful application of the theory of regular languages to formal verification of finite-state systems, there is a renewed interest in developing a theory of analyzable functions from strings to numerical values that can provide a foundation for analyzing {\em quantitative} properties of finite-state systems. In this paper, we propose a deterministic model for associating costs with strings that is parameterized by operations of interest (such as addition, scaling, and $\min$), a notion of {\em regularity} that provides a yardstick to measure expressiveness, and study decision problems and theoretical properties of resulting classes of cost functions. Our definition of regularity relies on the theory of string-to-tree transducers, and allows associating costs with events that are conditional upon regular properties of future events. Our model of {\em cost register automata} allows computation of regular functions using multiple "write-only" registers whose values can be combined using the allowed set of operations. We show that classical shortest-path algorithms as well as algorithms designed for computing {\em discounted costs}, can be adopted for solving the min-cost problems for the more general classes of functions specified in our model. Cost register automata with $\min$ and increment give a deterministic model that is equivalent to {\em weighted automata}, an extensively studied nondeterministic model, and this connection results in new insights and new open problems.

cs.FL↗