Inspecting the concept knowledge graph encoded by modern language models
The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these models. Despite this, attempts to understand their semantic capabilities have not been successful, often leading to non-conclusive, or contradictory conclusions among different works. Via a probing classifier, we extract the underlying knowledge graph of nine of the most influential language models of the last years, including word embeddings, text generators, and context encoders. This probe is based on concept relatedness, grounded on WordNet. Our results reveal that all the models encode this knowledge, but suffer from several inaccuracies. Furthermore, we show that the different architectures and training strategies lead to different model biases. We conduct a systematic evaluation to discover specific factors that explain why some concepts are challenging. We hope our insights will motivate the development of models that capture concepts more precisely.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language UnderstandingWord EmbeddingsSimilar Papers 제목 키워드 기반
GreaseLM: Graph REASoning Enhanced Language Models
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA syste…
Knowledge GraphsMedical Question AnsweringMedQANegation+3Graph-Sparse LDA: A Topic Model with Structured Sparsity
Originally designed to model text, topic modeling has become a powerful tool for uncovering latent structure in domains including medicine, finance, and vision. The goals for the model vary depending on the application: …
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA syste…
Knowledge GraphsMedical Question AnsweringMedQANegation+3Semantic Hypergraphs
Approaches to Natural language processing (NLP) may be classified along a double dichotomy open/opaque - strict/adaptive. The former axis relates to the possibility of inspecting the underlying processing rules, the latt…
Open Information ExtractionPolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs
Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built…