arXiv subjects

Jian Ni

Publications and source records attributed to Jian Ni.

At least 19 recordsLinked to original sources

arXiv2026

Mechanism Design for Decentralized Risk Detection: Strict Propriety, Network Coalitions, and the Backfiring Mandat

Competing firms that share a population of risky customers face a decentralized risk detection problem in which each firm holds fragmentary information whose aggregation would generate social value, but private incentives impede truthful sharing. We develop a dynamic mechanism design framework for this setting and identify three strategic frictions that distinguish it from classical mechanism design with decentralized information: compliance moral hazard, adversarial adaptation, and information destruction through intervention. A temporal value assignment (TVA) mechanism credits firms using a strictly proper scoring rule applied to discounted verified outcomes; under stated assumptions, TVA implements truthful posterior reporting as a Bayes--Nash equilibrium (uniquely optimal at each edge in large federations, with $O(1/m)$ shading in finite systems). A network Shapley characterization shows that under edge-additive coalition value, each firm's marginal contribution is proportional to its weighted cross-firm interaction degree, yielding a sharp prescription for coalition design that prioritizes inter-firm volume over firm size. Embedding TVA in a model of competition among firms, we establish a welfare ordering across four regulatory regimes (autarky, voluntary federation, mandated full sharing, TVA) and identify conditions under which information-sharing mandates without compatible incentive design reduce welfare below autarky: a ``backfiring mandate.'' We illustrate the framework on a 1.4M-transaction synthetic anti-money-laundering benchmark; the same machinery extends to platform fraud, cybersecurity threat intelligence, and supply chain risk detection.

cs.GT↗

arXiv2025

Networked Markets, Fragmented Data: Adaptive Graph Learning for Customer Risk Analytics and Policy Design

Financial institutions face escalating challenges in identifying high-risk customer behaviors within massive transaction networks, where fraudulent activities exploit market fragmentation and institutional boundaries. We address three fundamental problems in customer risk analytics: data silos preventing holistic relationship assessment, extreme behavioral class imbalance, and suboptimal customer intervention strategies that fail to balance compliance costs with relationship value. We develop an integrated customer intelligence framework combining federated learning, relational network analysis, and adaptive targeting policies. Our federated graph neural network enables collaborative behavior modeling across competing institutions without compromising proprietary customer data, using privacy-preserving embeddings to capture cross-market relational patterns. We introduce cross-bank Personalized PageRank to identify coordinated behavioral clusters providing interpretable customer network segmentation for risk managers. A hierarchical reinforcement learning mechanism optimizes dynamic intervention targeting, calibrating escalation policies to maximize prevention value while minimizing customer friction and operational costs. Analyzing 1.4 million customer transactions across seven markets, our approach reduces false positive and false negative rates to 4.64% and 11.07%, substantially outperforming single-institution models. The framework prevents 79.25% of potential losses versus 49.41% under fixed-rule policies, with optimal market-specific targeting thresholds reflecting heterogeneous customer base characteristics. These findings demonstrate that federated customer analytics materially improve both risk management effectiveness and customer relationship outcomes in networked competitive markets.

cs.CE↗

arXiv2025

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

Accurately locating key moments within long videos is crucial for solving long video understanding (LVU) tasks. However, existing benchmarks are either severely limited in terms of video length and task diversity, or they focus solely on the end-to-end LVU performance, making them inappropriate for evaluating whether key moments can be accurately accessed. To address this challenge, we propose MomentSeeker, a novel benchmark for long-video moment retrieval (LMVR), distinguished by the following features. First, it is created based on long and diverse videos, averaging over 1200 seconds in duration and collected from various domains, e.g., movie, anomaly, egocentric, and sports. Second, it covers a variety of real-world scenarios in three levels: global-level, event-level, object-level, covering common tasks like action recognition, object localization, and causal reasoning, etc. Third, it incorporates rich forms of queries, including text-only queries, image-conditioned queries, and video-conditioned queries. On top of MomentSeeker, we conduct comprehensive experiments for both generation-based approaches (directly using MLLMs) and retrieval-based approaches (leveraging video retrievers). Our results reveal the significant challenges in long-video moment retrieval in terms of accuracy and efficiency, despite improvements from the latest long-video MLLMs and task-specific fine-tuning. We have publicly released MomentSeeker(https://yhy-2000.github.io/MomentSeeker/) to facilitate future research in this area.

cs.CV↗

arXiv2024

Practical token pruning for foundation models in few-shot conversational virtual assistant systems

In an enterprise Virtual Assistant (VA) system, intent classification is the crucial component that determines how a user input is handled based on what the user wants. The VA system is expected to be a cost-efficient SaaS service with low training and inference time while achieving high accuracy even with a small number of training samples. We pretrain a transformer-based sentence embedding model with a contrastive learning objective and leverage the embedding of the model as features when training intent classification models. Our approach achieves the state-of-the-art results for few-shot scenarios and performs better than other commercial solutions on popular intent classification benchmarks. However, generating features via a transformer-based model increases the inference time, especially for longer user inputs, due to the quadratic runtime of the transformer's attention mechanism. On top of model distillation, we introduce a practical multi-task adaptation approach that configures dynamic token pruning without the need for task-specific training for intent classification. We demonstrate that this approach improves the inference speed of popular sentence transformer models without affecting model performance.

cs.CL↗

arXiv2024

Distilling Event Sequence Knowledge From Large Language Models

Event sequence models have been found to be highly effective in the analysis and prediction of events. Building such models requires availability of abundant high-quality event sequence data. In certain applications, however, clean structured event sequences are not available, and automated sequence extraction results in data that is too noisy and incomplete. In this work, we explore the use of Large Language Models (LLMs) to generate event sequences that can effectively be used for probabilistic event model construction. This can be viewed as a mechanism of distilling event sequence knowledge from LLMs. Our approach relies on a Knowledge Graph (KG) of event concepts with partial causal relations to guide the generative language model for causal event sequence generation. We show that our approach can generate high-quality event sequences, filling a knowledge gap in the input KG. Furthermore, we explore how the generated sequences can be leveraged to discover useful and more complex structured knowledge from pattern mining and probabilistic event models. We release our sequence generation code and evaluation framework, as well as corpus of event sequence data.

cs.CL↗

arXiv2024

Discovering Quirks through Timing at FASER and Future Forward Experiments at the LHC

Quirks are generic predictions of strongly-coupled dark sectors. For weak-scale masses and a broad range of confining scales in the dark sector, quirks can be discovered only at the energy frontier, but quirk--anti-quirk pairs are produced with unusual signatures at low $p_T$, making them difficult to detect at the large LHC detectors. We determine the prospects for discovering quirks using timing information at FASER, FASER2, and an "ultimate detector" in the far-forward region at the LHC. NLO QCD corrections are incorporated in the simulation of quirk production, which can significantly increase the production rate. To accurately propagate quirk pairs from the ATLAS interaction point to the forward detectors, the ionization energy loss of charged quirks traveling through matter, the radiation of infracolor glueballs and QCD hadrons during quirk pair oscillations, and the annihilation of quirkonium are properly considered. The quirk signal is separated from the large muon background using timing information from scintillator detectors by requiring either two coincident delayed tracks, based on arrival times at the detector, or two coincident slow tracks, based on time differences between hits in the front and back scintillators. We find that simple cuts preserve much of the signal, but reduce the muon background to negligible levels. With the data already collected, FASER can discover quirks in currently unconstrained parameter space. FASER2, running at the Forward Physics Facility during the HL-LHC era, will greatly extend this reach, probing the TeV-scale quirk masses motivated by the gauge hierarchy problem for the broad range of dark-sector confining scales between 100 eV and 100 keV.

hep-ph↗

arXiv2024

Product Design Using Generative Adversarial Network: Incorporating Consumer Preference and External Data

The rise of generative artificial intelligence (AI) has facilitated automated product design but often neglects valuable consumer preference data within companies' internal datasets. Additionally, external sources such as social media and user-generated content (UGC) platforms contain substantial untapped information on product design and consumer preferences, yet remain underutilized. We propose a novel framework that transforms the product design paradigm to be data-driven, automated, and consumer-centric. Our method employs a semi-supervised deep generative architecture that systematically integrates multidimensional consumer preferences and heterogeneous external data. The framework is both generative and preference-aware, enabling companies to produce consumer-aligned designs with enhanced cost efficiency. Our framework trains a specialized predictor model to comprehend consumer preferences and utilizes predicted popularity metrics to guide a continuous conditional generative adversarial network (CcGAN). The trained CcGAN can directionally generate consumer-preferred designs, circumventing the expenditure associated with testing suboptimal candidates. Using external data, our framework offers particular advantages for start-ups or other resource-constrained companies confronting the ``cold-start" problem. We demonstrate the framework's efficacy through an empirical application with a self-operated photography chain, where our model successfully generated superior photo template designs. We also conduct web-based experiments to verify our method and confirm its effectiveness across varying design contexts.

econ.GN↗

arXiv2024

Detection prospects of long-lived quirk pairs at the LHC far detectors

We examine the sensitivity reaches of several LHC far detectors, such as FASER2, MATHUSLA, ANUBIS, SND@LHC, and FACET, to five simplified quirk scenarios. We include the next-to-leading order QCD corrections in our simulation of quirk events, which enhance the total production rate and increase the fraction of events in the forward direction for most cases. We calculate the time scales for the quirk pair to lose energy through radiations and for the quirk pair annihilation. Our results show that these far detectors can offer promising probes to the quirk scenario, complementing the searches at the main detectors. Especially, FACET and FASER2 detectors can surpass the majority of searches conducted at the LHC main detector, with the exception of the HSCP search, for the color-neutral quirk $\mathcal{E}$.

hep-ph↗

arXiv2023

Improving Neural Ranking Models with Traditional IR Methods

Neural ranking methods based on large transformer models have recently gained significant attention in the information retrieval community, and have been adopted by major commercial solutions. Nevertheless, they are computationally expensive to create, and require a great deal of labeled data for specialized corpora. In this paper, we explore a low resource alternative which is a bag-of-embedding model for document retrieval and find that it is competitive with large transformer models fine tuned on information retrieval tasks. Our results show that a simple combination of TF-IDF, a traditional keyword matching method, with a shallow embedding model provides a low cost path to compete well with the performance of complex neural ranking models on 3 datasets. Furthermore, adding TF-IDF measures improves the performance of large-scale fine tuned models on these tasks.

cs.IR↗

arXiv2023

A Cross-Domain Evaluation of Approaches for Causal Knowledge Extraction

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain have largely focused on binary classification of a text segment as causal or non-causal. In this regard, we perform a thorough analysis of three sequence tagging models for causal knowledge extraction and compare it with a span based approach to causality extraction. Our experiments show that embeddings from pre-trained language models (e.g. BERT) provide a significant performance boost on this task compared to previous state-of-the-art models with complex architectures. We observe that span based models perform better than simple sequence tagging models based on BERT across all 4 data sets from diverse domains with different types of cause-effect phrases.

cs.CL↗

arXiv2022

A Generative Model for Relation Extraction and Classification

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model for relation extraction and classification (which we call GREC), where RE is modeled as a sequence-to-sequence generation task. We explore various encoding representations for the source and target sequences, and design effective schemes that enable GREC to achieve state-of-the-art performance on three benchmark RE datasets. In addition, we introduce negative sampling and decoding scaling techniques which provide a flexible tool to tune the precision and recall performance of the model. Our approach can be extended to extract all relation triples from a sentence in one pass. Although the one-pass approach incurs certain performance loss, it is much more computationally efficient.

cs.CL↗

arXiv2020

Cross-Lingual Relation Extraction with Transformers

Relation extraction (RE) is one of the most important tasks in information extraction, as it provides essential information for many NLP applications. In this paper, we propose a cross-lingual RE approach that does not require any human annotation in a target language or any cross-lingual resources. Building upon unsupervised cross-lingual representation learning frameworks, we develop several deep Transformer based RE models with a novel encoding scheme that can effectively encode both entity location and entity type information. Our RE models, when trained with English data, outperform several deep neural network based English RE models. More importantly, our models can be applied to perform zero-shot cross-lingual RE, achieving the state-of-the-art cross-lingual RE performance on two datasets (68-89% of the accuracy of the supervised target-language RE model). The high cross-lingual transfer efficiency without requiring additional training data or cross-lingual resources shows that our RE models are especially useful for low-resource languages.

cs.CL↗

arXiv2020

Event Presence Prediction Helps Trigger Detection Across Languages

The task of event detection and classification is central to most information retrieval applications. We show that a Transformer based architecture can effectively model event extraction as a sequence labeling task. We propose a combination of sentence level and token level training objectives that significantly boosts the performance of a BERT based event extraction model. Our approach achieves a new state-of-the-art performance on ACE 2005 data for English and Chinese. We also test our model on ERE Spanish, achieving an average gain of 2 absolute F1 points over prior best performing model.

cs.CL↗

arXiv2020

Cascaded Models for Better Fine-Grained Named Entity Recognition

Named Entity Recognition (NER) is an essential precursor task for many natural language applications, such as relation extraction or event extraction. Much of the NER research has been done on datasets with few classes of entity types (e.g. PER, LOC, ORG, MISC), but many real world applications (disaster relief, complex event extraction, law enforcement) can benefit from a larger NER typeset. More recently, datasets were created that have hundreds to thousands of types of entities, sparking new lines of research (Sekine, 2008;Ling and Weld, 2012; Gillick et al., 2014; Choiet al., 2018). In this paper we present a cascaded approach to labeling fine-grained NER, applying to a newly released fine-grained NER dataset that was used in the TAC KBP 2019 evaluation (Ji et al., 2019), inspired by the fact that training data is available for some of the coarse labels. Using a combination of transformer networks, we show that performance can be improved by about 20 F1 absolute, as compared with the straightforward model built on the full fine-grained types, and show that, surprisingly, using course-labeled data in three languages leads to an improvement in the English data.

cs.CL↗

arXiv2019

Towards Lingua Franca Named Entity Recognition with BERT

Information extraction is an important task in NLP, enabling the automatic extraction of data for relational database filling. Historically, research and data was produced for English text, followed in subsequent years by datasets in Arabic, Chinese (ACE/OntoNotes), Dutch, Spanish, German (CoNLL evaluations), and many others. The natural tendency has been to treat each language as a different dataset and build optimized models for each. In this paper we investigate a single Named Entity Recognition model, based on a multilingual BERT, that is trained jointly on many languages simultaneously, and is able to decode these languages with better accuracy than models trained only on one language. To improve the initial model, we study the use of regularization strategies such as multitask learning and partial gradient updates. In addition to being a single model that can tackle multiple languages (including code switch), the model could be used to make zero-shot predictions on a new language, even ones for which training data is not available, out of the box. The results show that this model not only performs competitively with monolingual models, but it also achieves state-of-the-art results on the CoNLL02 Dutch and Spanish datasets, OntoNotes Arabic and Chinese datasets. Moreover, it performs reasonably well on unseen languages, achieving state-of-the-art for zero-shot on three CoNLL languages.

cs.CL↗

arXiv2019

Neural Cross-Lingual Relation Extraction Based on Bilingual Word Embedding Mapping

Relation extraction (RE) seeks to detect and classify semantic relationships between entities, which provides useful information for many NLP applications. Since the state-of-the-art RE models require large amounts of manually annotated data and language-specific resources to achieve high accuracy, it is very challenging to transfer an RE model of a resource-rich language to a resource-poor language. In this paper, we propose a new approach for cross-lingual RE model transfer based on bilingual word embedding mapping. It projects word embeddings from a target language to a source language, so that a well-trained source-language neural network RE model can be directly applied to the target language. Experiment results show that the proposed approach achieves very good performance for a number of target languages on both in-house and open datasets, using a small bilingual dictionary with only 1K word pairs.

cs.CL↗

arXiv2019

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) is a challenging class of vision and knowledge transfer problems in which both seen and unseen classes appear during testing. Existing GZSL approaches either suffer from semantic loss and discard discriminative information at the embedding stage, or cannot guarantee the visual-semantic interactions. To address these limitations, we propose the Dual Adversarial Semantics-Consistent Network (DASCN), which learns primal and dual Generative Adversarial Networks (GANs) in a unified framework for GZSL. In particular, the primal GAN learns to synthesize inter-class discriminative and semantics-preserving visual features from both the semantic representations of seen/unseen classes and the ones reconstructed by the dual GAN. The dual GAN enforces the synthetic visual features to represent prior semantic knowledge well via semantics-consistent adversarial learning. To the best of our knowledge, this is the first work that employs a novel dual-GAN mechanism for GZSL. Extensive experiments show that our approach achieves significant improvements over the state-of-the-art approaches.

cs.CV↗

arXiv2017

Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping

The state-of-the-art named entity recognition (NER) systems are statistical machine learning models that have strong generalization capability (i.e., can recognize unseen entities that do not appear in training data) based on lexical and contextual information. However, such a model could still make mistakes if its features favor a wrong entity type. In this paper, we utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to our approach is the construction of high-accuracy, high-coverage multilingual Wikipedia entity type mappings. These mappings are built from weakly annotated data and can be extended to new languages with no human annotation or language-dependent knowledge involved. Based on these mappings, we develop several approaches to improve an NER system. We evaluate the performance of the approaches via experiments on NER systems trained for 6 languages. Experimental results show that the proposed approaches are effective in improving the accuracy of such systems on unseen entities, especially when a system is applied to a new domain or it is trained with little training data (up to 18.3 F1 score improvement).

cs.CL↗