Searcharxiv⌕ Search

arXiv subjects

Siyang Liu

Publications and source records attributed to Siyang Liu.

30 records · Page 2Linked to original sources
arXiv2023

EASE: An Easily-Customized Annotation System Powered by Efficiency Enhancement Mechanisms

The performance of current supervised AI systems is tightly connected to the availability of annotated datasets. Annotations are usually collected through annotation tools, which are often designed for specific tasks and are difficult to customize. Moreover, existing annotation tools with an active learning mechanism often only support limited use cases. To address these limitations, we present EASE, an Easily-Customized Annotation System Powered by Efficiency Enhancement Mechanisms. \sysname provides modular annotation units for building customized annotation interfaces and also provides multiple back-end options that suggest annotations using (1) multi-task active learning; (2) demographic feature based active learning; (3) a prompt system that can query the API of large language models. We conduct multiple experiments and user studies to evaluate our system's flexibility and effectiveness. Our results show that our system can meet the diverse needs of NLP researchers and significantly accelerate the annotation process.

cs.HC↗
arXiv2022

Rethinking and Refining the Distinct Metric

Distinct-$n$ score\cite{Li2016} is a widely used automatic metric for evaluating diversity in language generation tasks. However, we observed that the original approach for calculating distinct scores has evident biases that tend to assign higher penalties to longer sequences. We refine the calculation of distinct scores by scaling the number of distinct tokens based on their expectations. We provide both empirical and theoretical evidence to show that our method effectively removes the biases existing in the original distinct score. Our experiments show that our proposed metric, \textit{Expectation-Adjusted Distinct (EAD)}, correlates better with human judgment in evaluating response diversity. To foster future research, we provide an example implementation at \url{https://github.com/lsy641/Expectation-Adjusted-Distinct}.

cs.CL↗
arXiv2021

PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support

Great research interests have been attracted to devise AI services that are able to provide mental health support. However, the lack of corpora is a main obstacle to this research, particularly in Chinese language. In this paper, we propose PsyQA, a Chinese dataset of psychological health support in the form of question and answer pair. PsyQA is crawled from a Chinese mental health service platform, and contains 22K questions and 56K long and well-structured answers. Based on the psychological counseling theories, we annotate a portion of answer texts with typical strategies for providing support, and further present in-depth analysis of both lexical features and strategy patterns in the counseling answers. We also evaluate the performance of generating counseling answers with the generative pretrained models. Results show that utilizing strategies enhances the fluency and helpfulness of generated answers, but there is still a large space for future research.

cs.CL↗
arXiv2021

Towards Emotional Support Dialog Systems

Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. Following reasonable procedures and using various support skills can help to effectively provide support. However, due to the lack of a well-designed task and corpora of effective emotional support conversations, research on building emotional support into dialog systems remains untouched. In this paper, we define the Emotional Support Conversation (ESC) task and propose an ESC Framework, which is grounded on the Helping Skills Theory. We construct an Emotion Support Conversation dataset (ESConv) with rich annotation (especially support strategy) in a help-seeker and supporter mode. To ensure a corpus of high-quality conversations that provide examples of effective emotional support, we take extensive effort to design training tutorials for supporters and several mechanisms for quality control during data collection. Finally, we evaluate state-of-the-art dialog models with respect to the ability to provide emotional support. Our results show the importance of support strategies in providing effective emotional support and the utility of ESConv in training more emotional support systems.

cs.CL↗
arXiv2020

SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge

Most of the existing pre-trained language representation models neglect to consider the linguistic knowledge of texts, which can promote language understanding in NLP tasks. To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and sentiment polarity (inferred from SentiWordNet) into pre-trained models. We first propose a context-aware sentiment attention mechanism to acquire the sentiment polarity of each word with its part-of-speech tag by querying SentiWordNet. Then, we devise a new pre-training task called label-aware masked language model to construct knowledge-aware language representation. Experiments show that SentiLARE obtains new state-of-the-art performance on a variety of sentiment analysis tasks.

cs.CL↗
arXiv2020

Periodicities in cluster algebras and cluster automorphism groups

In this paper, we study the relations between groups related to cluster automorphism groups which are defined by Assem, Schiffler and Shamchenko in \cite{ASS}. We establish the relationship among (strict) direct cluster automorphism groups and those groups consisting of periodicities of respectively labeled seeds and exchange matrices in the language of short exact sequences. As an application, we characterize automorphism-finite cluster algebras in the cases with bipartite seeds or finite mutation type. Finally, we study the relation between the groups $\mathrm{Aut}\mathcal{A}$ and $\mathrm{Aut}_{M_n}S$ and give the negative answer via counter-examples to King and Pressland's a problem in \cite{KP}.

math.RT↗
arXiv2020

On maximal green sequences in abelian length categories

In this article, we study the relationship among maximal green sequences, complete forward hom-orthogonal sequences and stability functions in abelian length categories. Mainly, we firstly give a one-to-one correspondence between maximal green sequences and complete forward hom-orthogonal sequences via mutual constructions, and then prove that a maximal green sequence can be induced by a central charge if and only if it satisfies crossing inequalities. As applications, we show that crossing inequalities can be computed by $c$-vectors for finite dimensional algebras; finally, we give the Rotation Lemma for finite dimensional Jacobian algebras.

math.RT↗
arXiv2020

An Immunology-Inspired Network Security Architecture

The coming 5G networks have been enabling the creation of a wide variety of new services and applications which demand a new network security architecture. Immunology is the study of the immune system in vertebrates (including humans) which protects us from infection through various lines of defence. By studying the resemblance between the immune system and network security system, we acquire some inspirations from immunology and distill some guidelines for the design of network security architecture. We present a philosophical design principle, that is maintaining the balance between security and availability. Then, we derive two methodological principles: 1) achieving situation-awareness and fast response through community cooperation among heterogeneous nodes, and 2) Enhancing defense capability through consistently contesting with invaders in a real environment and actively mutating/evolving attack strategies. We also present a reference architecture designed based on the principles.

cs.CR↗
arXiv2019

CubeNet: Multi-Facet Hierarchical Heterogeneous Network Construction, Analysis, and Mining

Due to the ever-increasing size of data, construction, analysis and mining of universal massive networks are becoming forbidden and meaningless. In this work, we outline a novel framework called CubeNet, which systematically constructs and organizes real-world networks into different but correlated semantic cells, to support various downstream network analysis and mining tasks with better flexibility, deeper insights and higher efficiency. Particular, we promote our recent research on text and network mining with novel concepts and techniques to (1) construct four real-world large-scale multi-facet hierarchical heterogeneous networks; (2) enable insightful OLAP-style network analysis; (3) facilitate localized and contextual network mining. Although some functions have been covered individually in our previous work, a systematic and efficient realization of an organic system has not been studied, while some functions are still our on-going research tasks. By integrating them, CubeNet may not only showcase the utility of our recent research, but also inspire and stimulate future research on effective, insightful and scalable knowledge discovery under this novel framework.

cs.SI↗
arXiv2019

A conjecture on cluster automorphisms of cluster algebras

A cluster automorphism is a $\mathbb{Z}$-algebra automorphism of a cluster algebra $\mathcal A$ satisfying that it sends a cluster to another and commutes with mutations. Chang and Schiffler conjectured that a cluster automorphism of $\mathcal A$ is just a $\mathbb{Z}$-algebra homomorphism of a cluster algebra sending a cluster to another. The aim of this article is to prove this conjecture.

math.RT↗
arXiv2017

On Exchange Spectra of Valued Cluster Quivers and Cluster Algebras

Inspirited by the importance of the spectral theory of graphs, we introduce the spectral theory of valued cluster quiver of a cluster algebra. Our aim is to characterize a cluster algebra via its spectrum so as to use the spectral theory as a tool. First, we give the relations between exchange spectrum of a valued cluster quiver and adjacency spectrum of its underlying valued graph, and between exchange spectra of a valued cluster quiver and its full valued subquivers. The key point is to find some invariants from the spectrum theory under mutations of cluster algebras, which is the second part we discuss. We give a sufficient and necessary condition for a cluster quiver and its mutation to be cospectral. Following this discussion, the so-called cospectral subalgebra of a cluster algebra is introduced. We study bounds of exchange spectrum radii of cluster quivers and give a characterization of $2$-maximal cluster quivers via the classification of oriented graphs of its mutation equivalence. Finally, as an application of this result, we obtain that the preprojective algebra of a cluster quiver of Dynkin type is representation-finite if and only if the cluster quiver is $2$-maximal.

math.RT↗