Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2007.15084

Improving Performance of Relation Extraction Algorithm via Leveled Adversarial PCNN and Database Expansion

Diyah Puspitaningrum
View original source ↗Read source document ↗Export metadata ↓

Abstract

This study introduces database expansion using the Minimum Description Length (MDL) algorithm to expand the database for better relation extraction. Different from other previous relation extraction researches, our method improves system performance by expanding data. The goal of database expansion, together with a robust deep learning classifier, is to diminish wrong labels due to the incomplete or not found nature of relation instances in the relation database (e.g., Freebase). The study uses a deep learning method (Piecewise Convolutional Neural Network or PCNN) as the base classifier of our proposed approach: the leveled adversarial attention neural networks (LATTADV-ATT). In the database expansion process, the semantic entity identification is used to enlarge new instances using the most similar itemsets of the most common patterns of the data to get its pairs of entities. About the deep learning method, the use of attention of selective sentences in PCNN can reduce noisy sentences. Also, the use of adversarial perturbation training is useful to improve the robustness of system performance. The performance even further is improved using a combination of leveled strategy and database expansion. There are two issues: 1) database expansion method: rule generation by allowing step sizes on selected strong semantic of most similar itemsets with aims to find entity pair for generating instances, 2) a better classifier model for relation extraction. Experimental result has shown that the use of the database expansion is beneficial. The MDL database expansion helps improvements in all methods compared to the unexpanded method. The LATTADV-ATT performs as a good classifier with high precision P@100=0.842 (at no expansion). It is even better while implemented on the expansion data with P@100=0.891 (at expansion factor k=7).

Explore related subjects

cs.IR

Keep this discovery

BibTeXRIS

Diyah Puspitaningrum. 2020-07-29. Improving Performance of Relation Extraction Algorithm via Leveled Adversarial PCNN and Database Expansion. https://doi.org/10.1109/citsm47753.2019.8965423

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, and independently tuned downstream fusion can offset upstream improvements. Existing multi-task fusion methods focus on multi-objective fusion within the ranking stage, and cross-stage methods typically only add a downstream score factor to upstream ranking. Joint optimization of fusion modules across both stages remains largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings and are trained in a single computation graph, so gradients from either stage propagate through the shared representation and influence the other. Second, we introduce a dual-axis preference alignment objective: a vertical cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score, and a horizontal compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence. Third, we find that unconstrained end-to-end fusion optimization can exploit imbalances in item attribute distributions, over-concentrating on high-reward regions at the cost of other objectives. We therefore add an attribute group-relative regularization that computes advantages within attribute groups and normalizes the policy over the same groups, so uniformly promoting an entire high-reward group yields no optimization gain. Offline, UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines. Online A/B tests show a 0.616\% gain in app usage duration. UniRec is fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

cs.IR↗
arXiv2026

TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents

Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.

cs.IR↗