paper-with-me

Papers

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each entity in the graph, which results in large model sizes on real-world graphs with millions of entities. Their atomic entity representation also necessitates a multi-stage approach to downstream tasks, which limits their utility. We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model obtaining state-of-the-art results for KG link prediction and KGQA. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with a generative decoding approach. Such a simple but powerful method reduces the model size up to 90% compared to conventional KGE models and attains the best performance among small-sized models. An ensemble with a traditional KGE model even sets a new state-of-the-art. After finetuning this model on the task of KGQA over incomplete KGs, our approach outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderGraph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingLink PredictionQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

2022-03-19 · ACL 2022 5 · Apoorv Saxena, Adrian Kochsiek, Rainer Gemulla

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answ…

DecoderGraph EmbeddingKnowledge Graph CompletionKnowledge Graph Embedding+3

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation

2022-10-14 · Ying Su, ZiHao Wang, Tianqing Fang, Hongming Zhang 외

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representat…

Contrastive LearningKnowledge Graph CompletionKnowledge GraphsQuestion Answering+2

From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer

2022-02-04 · Xin Xie, Ningyu Zhang, Zhoubo Li, Shumin Deng 외

Knowledge graph completion aims to address the problem of extending a KG with missing triples. In this paper, we provide an approach GenKGC, which converts knowledge graph completion to sequence-to-sequence generation ta…

Knowledge Graph CompletionLanguage ModelingLanguage ModellingLink Prediction+1

GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs

2025-05-29 · Amel Gader, Alsayed Algergawy

Knowledge graph completion aims to address the gaps of knowledge bases by adding new triples that represent facts. The complexity of this task depends on how many parts of a triple are already known. Instance completion …

Knowledge Graph CompletionKnowledge GraphsLink PredictionMulti-Label Classification+2

Link Prediction using Embedded Knowledge Graphs

2016-11-14 · Yelong Shen, Po-Sen Huang, Ming-Wei Chang, Jianfeng Gao

Since large knowledge bases are typically incomplete, missing facts need to be inferred from observed facts in a task called knowledge base completion. The most successful approaches to this task have typically explored …

Knowledge Base CompletionKnowledge GraphsLink PredictionPrediction