paper-with-me

홈 › Papers

A Systematic Investigation of KB-Text Embedding Alignment at Scale

2021-06-03 · ACL 2021 5 · Vardaan Pahuja, Yu Gu, Wenhu Chen, Mehdi Bahrami, Lei Liu, Wei-Peng Chen, Yu Su

Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way. Separately embedding the individual knowledge sources into vector spaces has demonstrated tremendous successes in encoding the respective knowledge, but how to jointly embed and reason with both knowledge sources to fully leverage the complementary information is still largely an open problem. We conduct a large-scale, systematic investigation of aligning KB and text embeddings for joint reasoning. We set up a novel evaluation framework with two evaluation tasks, few-shot link prediction and analogical reasoning, and evaluate an array of KB-text embedding alignment methods. We also demonstrate how such alignment can infuse textual information into KB embeddings for more accurate link prediction on emerging entities and events, using COVID-19 as a case study.

📄 PDF Abstract BibTeX arXiv:2106.01586

Code (1)

dki-lab/joint-kb-text-embedding 공식 구현 pytorch

Tasks

Link Prediction

Similar Papers 제목 키워드 기반

Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models

2024-09-15 · Sahil Kuchlous, Marvin Li, Jeffrey G. Wang

With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models…

DiversityFairness

Quantifying Phonosemantic Iconicity Distributionally in 6 Languages

2025-10-15 · George Flint, Kaustubh Kislay arxiv

Language is, as commonly theorized, largely arbitrary. Yet, systematic relationships between phonetics and semantics have been observed in many specific cases. To what degree could those systematic relationships manifest…

Semantic Similarity

Investigating Cross-Lingual Alignment Methods for Contextualized Embeddings with Token-Level Evaluation

2019-11-01 · CONLL 2019 11 · Qianchu Liu, Diana McCarthy, Ivan Vuli{\'c}, Anna Korhonen

In this paper, we present a thorough investigation on methods that align pre-trained contextualized embeddings into shared cross-lingual context-aware embedding space, providing strong reference benchmarks for future con…

RetrievalSentenceSentence RetrievalWord Similarity

Training Alignment Auditors via Reinforcement Learning

2026-08-26 · Paul Rosu, Rowan Wang arxiv

Alignment auditing of frontier models increasingly relies on LLM auditors to surface undesirable behaviors at scale, but current automated auditors can struggle with coherent investigation and audit realism. In this work…

Reinforcement Learning

An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage

2025-01-03 · Fan Bu, Zheng Wang, Siyi Wang, Ziyao Liu

As Large Language Models (LLMs) become increasingly prevalent in tasks related to cultural heritage, such as generating descriptions of historical monuments, translating ancient texts, preserving oral traditions, and cre…