arXiv subjects

Haoran Meng

Publications and source records attributed to Haoran Meng.

6 recordsLinked to original sources

arXiv2025

Video-based Direct Time Series Measurement of Along-Strike Slip on the Coseismic Surface Rupture During the 2025 Mw7.7 Myanmar Earthquake

This study presents a time-resolved analysis of coseismic lateral surface rupture along the Sagaing Fault during the Mw 7.7 Mandalay, Myanmar earthquake on March 28, 2025. Leveraging a publicly available Closed-Circuit Television (CCTV) footage alongside on-site measurements, we show the first in-situ high sampling rate direct measurement of a coseismic slip evolution of a fault during an earthquake. Our work comprises four primary stages: data acquisition, video pre-processing, object tracking, and physical displacement estimation. Video pre-processing includes camera stabilization and distortion correction. We then track pixel-level movements of selected reference points using two complementary computer-vision approaches -- a traditional grayscale template matching algorithm and a state-of-the-art vision transformer multi-object tracking algorithm, and verify both profiles against meticulous manual frame-by-frame measurements, with results that closely match one another. Finally, we translated those pixel displacements into real-world ground movements by calibrating against reference objects whose dimensions were measured on site. Based on the resulting displacement time series, we estimated the critical slip-weakening distance. The resulting high-resolution time series of the along-strike slip, provided in the appendix, offers a critical benchmark for validating dynamic rupture simulations, refining frictional models, and enhancing seismic hazard assessment.

physics.geo-ph↗

arXiv2024

Perpendicular Diffusion Effect of Cosmic Ray Dipole Anisotropy

Anisotropy is very important to understand cosmic ray (CR) source and interstellar environment. The theoretical explanation of cosmic rays anisotropy from experiments remains challenging and even puzzling for a long time. In this paper, by following the ideas of Jokipii 2007, we use a simple analytical model to study the CR dipole anisotropy amplitude, considering that CRs diffuse only in perpendicular direction, with the ratio between the secondary and primary cosmic rays omnidirectional particle distribution function as an input. We make power law fitting of the observed B/C ratio and use it as the input of the anisotropy model. We show that the modeling results can roughly describe the general trend of the observational data in energy range from $6\times 10^1$ to $3\times 10^{11}$ GeV. It is suggested that the perpendicular diffusion may play a significant role in CR anisotropy in the wide energy range.

astro-ph.HE↗

arXiv2023

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade

In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added data, new intents would emerge and might have semantic entanglement with the existing intents, e.g. new intents that are semantically too specific or generic are actually subset or superset of some existing intents in the semantic space, thus impairing the robustness of the NLU model. As the first attempt to solve this problem, we setup a new benchmark consisting of 4 Dialogue Version Control dataSets (DialogVCS). We formulate the intent detection with imperfect data in the system update as a multi-label classification task with positive but unlabeled intents, which asks the models to recognize all the proper intents, including the ones with semantic entanglement, in the inference. We also propose comprehensive baseline models and conduct in-depth analyses for the benchmark, showing that the semantically entangled intents can be effectively recognized with an automatic workflow.

cs.CL↗

arXiv2022

DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog

Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios. Prior work attempts to obtain 1-to-1 QA pairs from growing customer service chatlog, which fails to integrate the incomplete utterances from the dialog context for composite QA retrieval. In this paper, we propose N-to-N QA extraction task in which the derived questions and corresponding answers might be separated across different utterances. We introduce a suite of generative/discriminative tagging based methods with end-to-end and two-stage variants that perform well on 5 customer service datasets and for the first time setup a benchmark for N-to-N DialogQAE with utterance and session level evaluation metrics. With a deep dive into extracted QA pairs, we find that the relations between and inside the QA pairs can be indicators to analyze the dialogue structure, e.g. information seeking, clarification, barge-in and elaboration. We also show that the proposed models can adapt to different domains and languages, and reduce the labor cost of knowledge accumulation in the real-world product dialogue platform.

cs.CL↗

arXiv2022

DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection

While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance. Instead of training a dedicated multi-intent detection model, we propose DialogUSR, a dialogue utterance splitting and reformulation task that first splits multi-intent user query into several single-intent sub-queries and then recovers all the coreferred and omitted information in the sub-queries. DialogUSR can serve as a plug-in and domain-agnostic module that empowers the multi-intent detection for the deployed chatbots with minimal efforts. We collect a high-quality naturally occurring dataset that covers 23 domains with a multi-step crowd-souring procedure. To benchmark the proposed dataset, we propose multiple action-based generative models that involve end-to-end and two-stage training, and conduct in-depth analyses on the pros and cons of the proposed baselines.

cs.CL↗

arXiv2022

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues

It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query. In this work, we take a sober look at such an unconditional formulation in the sense that no prior knowledge is specified with respect to the source image(s). Inspired by the designs of both visual commonsense reasoning and natural language inference tasks, we propose a new task termed Premise-based Multi-modal Reasoning(PMR) where a textual premise is the background presumption on each source image. The PMR dataset contains 15,360 manually annotated samples which are created by a multi-phase crowd-sourcing process. With selected high-quality movie screenshots and human-curated premise templates from 6 pre-defined categories, we ask crowd-source workers to write one true hypothesis and three distractors (4 choices) given the premise and image through a cross-check procedure. Besides, we generate adversarial samples to alleviate the annotation artifacts and double the size of PMR. We benchmark various state-of-the-art (pretrained) multi-modal inference models on PMR and conduct comprehensive experimental analyses to showcase the utility of our dataset.

cs.CL↗