Solving Hard Analogy Questions with Relation Embedding Chains

• URL: http://arxiv.org/abs/2310.12379v1
• Date: Wed, 18 Oct 2023 23:13:22 GMT
• Title: Solving Hard Analogy Questions with Relation Embedding Chains
• Abstract summary: Modelling how concepts are related is a central topic in Lexical Semantics. KGs are limited to a fixed set of relation types, and they are incomplete and often noisy. We distill relation embeddings from a fine-tuned language model. We show that our proposed representations are useful for solving hard analogy questions.
• Score: 21.31821067426995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modelling how concepts are related is a central topic in Lexical Semantics. A common strategy is to rely on knowledge graphs (KGs) such as ConceptNet, and to model the relation between two concepts as a set of paths. However, KGs are limited to a fixed set of relation types, and they are incomplete and often noisy. Another strategy is to distill relation embeddings from a fine-tuned language model. However, this is less suitable for words that are only indirectly related and it does not readily allow us to incorporate structured domain knowledge. In this paper, we aim to combine the best of both worlds. We model relations as paths but associate their edges with relation embeddings. The paths are obtained by first identifying suitable intermediate words and then selecting those words for which informative relation embeddings can be obtained. We empirically show that our proposed representations are useful for solving hard analogy questions.

Related papers

• Soft Reasoning Paths for Knowledge Graph Completion [63.23109723605835]
  Reasoning paths are reliable information in knowledge graph completion (KGC)<n>In real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities.<n>We introduce soft reasoning paths to make the proposed algorithm more stable against missing path circumstances.
  arXiv  Detail & Related papers  (2025-05-06T08:12:48Z)
• Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering [60.6042489577575]
  We introduce Konstruktor - an efficient and robust approach that breaks down the problem into three steps. Our approach integrates language models and knowledge graphs, exploiting the power of the former and the interpretability of the latter. We show that for relation detection, the most challenging step of the workflow, a combination of relation classification/generation and ranking outperforms other methods.
  arXiv  Detail & Related papers  (2024-09-24T09:19:11Z)
• Relational Sentence Embedding for Flexible Semantic Matching [86.21393054423355]
  We present Sentence Embedding (RSE), a new paradigm to discover further the potential of sentence embeddings. RSE is effective and flexible in modeling sentence relations and outperforms a series of state-of-the-art embedding methods.
  arXiv  Detail & Related papers  (2022-12-17T05:25:17Z)
• Discovering Fine-Grained Semantics in Knowledge Graph Relations [5.619233302594469]
  Polysemous relations between different types of entities represent multiple semantics. For numerous use cases, such as entity type classification, question answering and knowledge graph completion, the correct semantic interpretation is necessary. We propose a strategy for discovering the different semantics associated with abstract relations and deriving many sub-relations with fine-grained meaning.
  arXiv  Detail & Related papers  (2022-02-17T22:05:41Z)
• What is Learned in Knowledge Graph Embeddings? [3.224929252256631]
  A knowledge graph (KG) is a data structure which represents entities and relations as the vertices and edges of a directed graph with edge types. We investigate whether learning rules between relations is indeed what drives the performance of embedding-based methods. Using experiments on synthetic KGs, we show that KG models can learn motifs and how this ability is degraded by non-motif edges.
  arXiv  Detail & Related papers  (2021-10-19T13:52:11Z)
• Distilling Relation Embeddings from Pre-trained Language Models [35.718167335989854]
  We show that it is possible to distill relation embeddings from pre-trained language models. We encode word pairs using a (manually or automatically generated) prompt, and we fine-tune the language model. The resulting relation embeddings are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks.
  arXiv  Detail & Related papers  (2021-09-21T15:05:27Z)
• Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [31.887770824130957]
  We propose a novel logic-guided semantic representation learning model for zero-shot relation classification. Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules.
  arXiv  Detail & Related papers  (2020-10-30T04:30:09Z)
• Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference [60.048447849653876]
  We propose a novel joint semantics and data-driven path representation that balances explainability and generalization in the framework of KG embedding. Our proposed model is evaluated on two classes of tasks: link prediction and path query answering task.
  arXiv  Detail & Related papers  (2020-10-06T10:24:45Z)
• End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings [20.4826750211045]
  We propose the first end-to-end neural network approach that employs KG as well as word embeddings to perform joint relation and entity classification of simple questions. An empirical evaluation shows that the proposed approach achieves a performance comparable to state-of-the-art entity linking.
  arXiv  Detail & Related papers  (2020-02-25T19:07:54Z)
• Relational Message Passing for Knowledge Graph Completion [78.47976646383222]
  We propose a relational message passing method for knowledge graph completion. It passes relational messages among edges iteratively to aggregate neighborhood information. Results show our method outperforms stateof-the-art knowledge completion methods by a large margin.
  arXiv  Detail & Related papers  (2020-02-17T03:33:41Z)
• Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning [157.62595449130973]
  We study the fundamental problem of simplistic class modeling in current few-shot learning methods. We propose a novel Absolute-relative Learning paradigm to fully take advantage of label information to refine the image representations.
  arXiv  Detail & Related papers  (2020-01-12T12:25:46Z)
• Multiplex Word Embeddings for Selectional Preference Acquisition [70.33531759861111]
  We propose a multiplex word embedding model, which can be easily extended according to various relations among words. Our model can effectively distinguish words with respect to different relations without introducing unnecessary sparseness.
  arXiv  Detail & Related papers  (2020-01-09T04:47:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.