arXiv subjects

Ming Zhong

Publications and source records attributed to Ming Zhong.

At least 91 records · Page 5Linked to original sources

arXiv2023

PINNs-Based Uncertainty Quantification for Transient Stability Analysis

This paper addresses the challenge of transient stability in power systems with missing parameters and uncertainty propagation in swing equations. We introduce a novel application of Physics-Informed Neural Networks (PINNs), specifically an Ensemble of PINNs (E-PINNs), to estimate critical parameters like rotor angle and inertia coefficient with enhanced accuracy and reduced computational load. E-PINNs capitalize on the underlying physical principles of swing equations to provide a robust solution. Our approach not only facilitates efficient parameter estimation but also quantifies uncertainties, delivering probabilistic insights into the system behavior. The efficacy of E-PINNs is demonstrated through the analysis of $1$-bus and $2$-bus systems, highlighting the model's ability to handle parameter variability and data scarcity. The study advances the application of machine learning in power system stability, paving the way for reliable and computationally efficient transient stability analysis.

cs.AI↗

arXiv2023

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation

Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses. Existing methods either manually annotate or employ LLM (e.g., GPT-series) to generate data for instruction tuning. However, they often overlook associating instructions with existing annotated datasets. In this paper, we propose Dynosaur, a dynamic growth paradigm for the automatic curation of instruction-tuning data. Based on the metadata of existing datasets, we use LLMs to automatically construct instruction-tuning data by identifying relevant data fields and generating appropriate instructions. By leveraging the existing annotated datasets, Dynosaur offers several advantages: 1) it reduces the API cost for generating instructions (e.g., it costs less than $12 USD by calling GPT-3.5-turbo for generating 800K instruction tuning samples; 2) it provides high-quality data for instruction tuning (e.g., it performs better than Alpaca and Flan on Super-NI and Longform with comparable data sizes); and 3) it supports the continuous improvement of models by generating instruction-tuning data when a new annotated dataset becomes available. We further investigate a continual learning scheme for learning with the ever-growing instruction-tuning dataset, and demonstrate that replaying tasks with diverse instruction embeddings not only helps mitigate forgetting issues but generalizes to unseen tasks better. Code and data are available at https://github.com/WadeYin9712/Dynosaur.

cs.CL↗

arXiv2023

Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

Large language models with instruction-following capabilities open the door to a wider group of users. However, when it comes to information extraction - a classic task in natural language processing - most task-specific systems cannot align well with long-tail ad hoc extraction use cases for non-expert users. To address this, we propose a novel paradigm, termed On-Demand Information Extraction, to fulfill the personalized demands of real-world users. Our task aims to follow the instructions to extract the desired content from the associated text and present it in a structured tabular format. The table headers can either be user-specified or inferred contextually by the model. To facilitate research in this emerging area, we present a benchmark named InstructIE, inclusive of both automatically generated training data, as well as the human-annotated test set. Building on InstructIE, we further develop an On-Demand Information Extractor, ODIE. Comprehensive evaluations on our benchmark reveal that ODIE substantially outperforms the existing open-source models of similar size. Our code and dataset are released on https://github.com/yzjiao/On-Demand-IE.

cs.CL↗

arXiv2023

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks. However, it remains unclear whether the existing focus of NLP research accurately captures the genuine requirements of human users. This paper provides a comprehensive analysis of the divergence between current NLP research and the needs of real-world NLP applications via a large-scale collection of user-GPT conversations. We analyze a large-scale collection of real user queries to GPT. We compare these queries against existing NLP benchmark tasks and identify a significant gap between the tasks that users frequently request from LLMs and the tasks that are commonly studied in academic research. For example, we find that tasks such as ``design'' and ``planning'' are prevalent in user interactions but are largely neglected or different from traditional NLP benchmarks. We investigate these overlooked tasks, dissect the practical challenges they pose, and provide insights toward a roadmap to make LLMs better aligned with user needs.

cs.CL↗

arXiv2023

L-Eval: Instituting Standardized Evaluation for Long Context Language Models

Recently, there has been growing interest in extending the context length of large language models (LLMs), aiming to effectively process long inputs of one turn or conversations with more extensive histories. While proprietary models such as GPT-4 and Claude can largely preserve the reasoning ability in an extended context, open-source models are still progressing through the early stages of development. To bridge this gap, we propose L-Eval to institute a more standardized evaluation for long context language models (LCLMs) addressing two key aspects: dataset construction and evaluation metrics. On the one hand, we build a new evaluation suite containing 20 sub-tasks, 508 long documents, and over 2,000 human-labeled query-response pairs encompassing diverse question styles, domains, and input length (3k$\sim$200k tokens). On the other hand, we investigate the effectiveness in evalution metrics for LCLMs. Results show that popular n-gram matching metrics generally can not correlate well with human judgment, and thus we strongly advocate for length-instruction-enhanced (LIE) evaluation and employing LLM judges. We conducted a comprehensive study of 4 popular commercial LLMs and 12 open-source counterparts using the L-Eval benchmark. Our empirical findings offer useful insights into the study of LCLMs and lay the groundwork for the development of more principled evaluation of these models.

cs.CL↗

arXiv2023

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

Most existing cross-lingual summarization (CLS) work constructs CLS corpora by simply and directly translating pre-annotated summaries from one language to another, which can contain errors from both summarization and translation processes. To address this issue, we propose ConvSumX, a cross-lingual conversation summarization benchmark, through a new annotation schema that explicitly considers source input context. ConvSumX consists of 2 sub-tasks under different real-world scenarios, with each covering 3 language directions. We conduct thorough analysis on ConvSumX and 3 widely-used manually annotated CLS corpora and empirically find that ConvSumX is more faithful towards input text. Additionally, based on the same intuition, we propose a 2-Step method, which takes both conversation and summary as input to simulate human annotation process. Experimental results show that 2-Step method surpasses strong baselines on ConvSumX under both automatic and human evaluation. Analysis shows that both source input text and summary are crucial for modeling cross-lingual summaries.

cs.CL↗

arXiv2023

ReactIE: Enhancing Chemical Reaction Extraction with Weak Supervision

Structured chemical reaction information plays a vital role for chemists engaged in laboratory work and advanced endeavors such as computer-aided drug design. Despite the importance of extracting structured reactions from scientific literature, data annotation for this purpose is cost-prohibitive due to the significant labor required from domain experts. Consequently, the scarcity of sufficient training data poses an obstacle to the progress of related models in this domain. In this paper, we propose ReactIE, which combines two weakly supervised approaches for pre-training. Our method utilizes frequent patterns within the text as linguistic cues to identify specific characteristics of chemical reactions. Additionally, we adopt synthetic data from patent records as distant supervision to incorporate domain knowledge into the model. Experiments demonstrate that ReactIE achieves substantial improvements and outperforms all existing baselines.

cs.CL↗

arXiv2023

Mimicking the Thinking Process for Emotion Recognition in Conversation with Prompts and Paraphrasing

Emotion recognition in conversation, which aims to predict the emotion for all utterances, has attracted considerable research attention in recent years. It is a challenging task since the recognition of the emotion in one utterance involves many complex factors, such as the conversational context, the speaker's background, and the subtle difference between emotion labels. In this paper, we propose a novel framework which mimics the thinking process when modeling these factors. Specifically, we first comprehend the conversational context with a history-oriented prompt to selectively gather information from predecessors of the target utterance. We then model the speaker's background with an experience-oriented prompt to retrieve the similar utterances from all conversations. We finally differentiate the subtle label semantics with a paraphrasing mechanism to elicit the intrinsic label related knowledge. We conducted extensive experiments on three benchmarks. The empirical results demonstrate the superiority of our proposed framework over the state-of-the-art baselines.

cs.CL↗

arXiv2023

The Emergence of Lines of Hierarchy in Collective Motion of Biological Systems

The emergence of large scale structures in biological systems, and in particular the formation of lines of hierarchy, is observed in many scales, from collections of cells to groups of insects to herds of animals. Motivated by phenomena in chemotaxis and phototaxis, we present a new class of alignment models which exhibit alignment into lines. The spontaneous formation of such ``fingers" can be interpreted as the emergence of leaders and followers in a system of identically interacting agents. Various numerical examples are provided, which demonstrate emergent behaviors similar to the ``fingering'' phenomenon observed in some phototaxis and chemotaxis experiments; this phenomenon is generally known as a challenging pattern to capture for existing models. The novel pairwise interactions provides a fundamental mechanism by which agents may form social hierarchy across a wide range of biological systems.

nlin.AO↗

arXiv2023

PREME: Preference-based Meeting Exploration through an Interactive Questionnaire

The recent increase in the volume of online meetings necessitates automated tools for managing and organizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it. In this work, we propose a novel end-to-end framework for generating interactive questionnaires for preference-based meeting exploration. As a result, users are supplied with a list of suggested questions reflecting their preferences. Since the task is new, we introduce an automatic evaluation strategy. Namely, it measures how much the generated questions via questionnaire are answerable to ensure factual correctness and covers the source meeting for the depth of possible exploration.

cs.CL↗

arXiv2023

COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization

Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives. However, the output summary is always evaluated from summary-level which leads to the inconsistency in training and evaluation. In this paper, we propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. By modeling a contrastive objective, we show that the summarization model is able to directly generate summaries according to the summary-level score without additional modules and parameters. Extensive experiments demonstrate that COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score while preserving the parameter efficiency and inference efficiency. Compared with state-of-the-art multi-stage systems, we save more than 100 GPU training hours and obtaining 3~8 speed-up ratio during inference while maintaining comparable results.

cs.CL↗

arXiv2023

Scalable Time-Range k-Core Query on Temporal Graphs(Full Version)

Querying cohesive subgraphs on temporal graphs with various time constraints has attracted intensive research interests recently. In this paper, we study a novel Temporal k-Core Query (TCQ) problem: given a time interval, find all distinct k-cores that exist within any subintervals from a temporal graph, which generalizes the previous historical k-core query. This problem is challenging because the number of subintervals increases quadratically to the span of time interval. For that, we propose a novel Temporal Core Decomposition (TCD) algorithm that decrementally induces temporal k-cores from the previously induced ones and thus reduces "intra-core" redundant computation significantly. Then, we introduce an intuitive concept named Tightest Time Interval (TTI) for temporal k-core, and design an optimization technique with theoretical guarantee that leverages TTI as a key to predict which subintervals will induce duplicated k-cores and prunes the subintervals completely in advance, thereby eliminating "inter-core" redundant computation. The complexity of optimized TCD (OTCD) algorithm no longer depends on the span of query time interval but only the scale of final results, which means OTCD algorithm is scalable. Moreover, we propose a compact in-memory data structure named Temporal Edge List (TEL) to implement OTCD algorithm efficiently in physical level with bounded memory requirement. TEL organizes temporal edges in a "timeline" and can be updated instantly when new edges arrive, and thus our approach can also deal with dynamic temporal graphs. We compare OTCD algorithm with the incremental historical k-core query on several real-world temporal graphs, and observe that OTCD algorithm outperforms it by three orders of magnitude, even though OTCD algorithm needs none precomputed index.

cs.DB↗

arXiv2023

Message passing approach to analyze the robustness of hypergraph

Hypergraph networks are closer to real life because they can reflect higher-order interactions, so researchers have begun using them to build models for real-world networks. The mean-field approach is the current tool for studying the percolation problem on hypergraph networks. However, we found that when there is a loop in the hypergraph network, the calculated results using this approach deviate from the real results. Therefore, in this paper, we rephrase the percolation on the hypergraph network as a message passing process, thus obtaining a message passing approach. Our proposed approach has been tested in several hypergraph networks with loops, and the experimental results are more accurate than those under the mean-field approach. This is helpful to analyze and understand the robustness of hypergraph networks with loops. In addition, we also specifically analyzed how four different types of loops affect the accuracy of the experiment. Our proposed message passing approach also provides another way to study percolation on hypergraph networks.

physics.soc-ph↗

arXiv2023

Concurrent Emergence of Clustering, Flocking and Synchronization in Systems of Interacting Agents

We present some recent development in modeling concurrent emergence of collective behaviors, namely, the emergence of clustering, flocking and synchronization at the same time. We derive two new models, namely Swarmalator-Vicsek and Swarmalator- Cucker-Smale, which can produce the synchronization and flocking with interesting spatial patterns. We present extensive numerical insights into how the synchronization of phases can affect both the spatial patterns and the flocking behavior.

math.DS↗

arXiv2022

Unsupervised Multi-Granularity Summarization

Text summarization is a user-preference based task, i.e., for one document, users often have different priorities for summary. As a key aspect of customization in summarization, granularity is used to measure the semantic coverage between the summary and source document. However, developing systems that can generate summaries with customizable semantic coverage is still an under-explored topic. In this paper, we propose the first unsupervised multi-granularity summarization framework, GranuSum. We take events as the basic semantic units of the source documents and propose to rank these events by their salience. We also develop a model to summarize input documents with given events as anchors and hints. By inputting different numbers of events, GranuSum is capable of producing multi-granular summaries in an unsupervised manner. Meanwhile, we annotate a new benchmark GranuDUC that contains multiple summaries at different granularities for each document cluster. Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines. Further, by exploiting the event information, GranuSum also exhibits state-of-the-art performance under the conventional unsupervised abstractive setting. Dataset for this paper can be found at: https://github.com/maszhongming/GranuDUC

cs.CL↗

arXiv2022

Using Physics Informed Neural Networks for Supernova Radiative Transfer Simulation

We use physics informed neural networks (PINNs) to solve the radiative transfer equation and calculate a synthetic spectrum for a Type Ia supernova (SN~Ia) SN 2011fe. The calculation is based on local thermodynamic equilibrium (LTE) and 9 elements are included. Physical processes included are approximate radiative equilibrium, bound-bound transitions, and the Doppler effect. A PINN based gamma-ray scattering approximation is used for radioactive decay energy deposition. The PINN synthetic spectrum is compared to an observed spectrum, a synthetic spectrum calculated by the Monte-Carlo radiative transfer program TARDIS, and the formal solution of the radiative transfer equation. We discuss the challenges and potential of this deep-learning based radiative transfer equation solver. In fact, PINNs offer the prospect of simultaneous solution of the atmosphere problem for both radiation field and thermal state throughout spacetime. We have made modest steps to realizing that prospect with our calculations which required many approximations in order to be feasible at this point in the development of PINN atmosphere solutions.

astro-ph.HE↗

arXiv2022

Open-Vocabulary Argument Role Prediction for Event Extraction

The argument role in event extraction refers to the relation between an event and an argument participating in it. Despite the great progress in event extraction, existing studies still depend on roles pre-defined by domain experts. These studies expose obvious weakness when extending to emerging event types or new domains without available roles. Therefore, more attention and effort needs to be devoted to automatically customizing argument roles. In this paper, we define this essential but under-explored task: open-vocabulary argument role prediction. The goal of this task is to infer a set of argument roles for a given event type. We propose a novel unsupervised framework, RolePred for this task. Specifically, we formulate the role prediction problem as an in-filling task and construct prompts for a pre-trained language model to generate candidate roles. By extracting and analyzing the candidate arguments, the event-specific roles are further merged and selected. To standardize the research of this task, we collect a new event extraction dataset from WikiPpedia including 142 customized argument roles with rich semantics. On this dataset, RolePred outperforms the existing methods by a large margin. Source code and dataset are available on our GitHub repository: https://github.com/yzjiao/RolePred

cs.CL↗

arXiv2022

CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision

Scientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers. Previous efforts on curating scientific TLDR datasets failed to scale up due to the heavy human annotation and domain expertise required. In this paper, we propose a simple yet effective approach to automatically extracting TLDR summaries for scientific papers from their citation texts. Based on the proposed approach, we create a new benchmark CiteSum without human annotation, which is around 30 times larger than the previous human-curated dataset SciTLDR. We conduct a comprehensive analysis of CiteSum, examining its data characteristics and establishing strong baselines. We further demonstrate the usefulness of CiteSum by adapting models pre-trained on CiteSum (named CITES) to new tasks and domains with limited supervision. For scientific extreme summarization, CITES outperforms most fully-supervised methods on SciTLDR without any fine-tuning and obtains state-of-the-art results with only 128 examples. For news extreme summarization, CITES achieves significant gains on XSum over its base model (not pre-trained on CiteSum), e.g., +7.2 ROUGE-1 zero-shot performance and state-of-the-art few-shot performance. For news headline generation, CITES performs the best among unsupervised and zero-shot methods on Gigaword. Our dataset and code can be found at https://github.com/morningmoni/CiteSum.

cs.CL↗