Related papers: A Knowledge Compilation Map
Knowledge graphs (KGs) contain rich information about world knowledge, entities and relations. Thus, they can be great supplements to existing pre-trained language models. However, it remains a challenge to efficiently integrate information…
Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned.…
Many recent works have demonstrated the benefits of knowledge graph embeddings in completing monolingual knowledge graphs. Inasmuch as related knowledge bases are built in several different languages, achieving cross-lingual knowledge…
In artificial intelligence (AI), knowledge is the information required by an intelligent system to accomplish tasks. While traditional knowledge bases use discrete, symbolic representations, detecting knowledge encoded in the continuous…
We introduce an NLP toolkit based on object-oriented knowledge base and multi-level grammar base. This toolkit focuses on semantic parsing, it also has abilities to discover new knowledge and grammar automatically, new discovered knowledge…
With the rapid development of deep learning, there have been an unprecedentedly large number of trained deep network models available online. Reusing such trained models can significantly reduce the cost of training the new models from…
Encyclopedic knowledge graphs, such as Wikidata, host an extensive repository of millions of knowledge statements. However, domain-specific knowledge from fields such as history, physics, or medicine is significantly underrepresented in…
Autoregressive large language models (LLMs) pre-trained by next token prediction are inherently proficient in generative tasks. However, their performance on knowledge-driven tasks such as factual knowledge querying remains unsatisfactory.…
We study planning in a fragment of PDDL with qualitative state-trajectory constraints, capturing safety requirements, task ordering conditions, and intermediate sub-goals commonly found in real-world problems. A prominent approach to tackle…
Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to…
Knowledge graph embedding aims at translating the knowledge graph into numerical representations by transforming the entities and relations into continuous low-dimensional vectors. Recently, many methods [1, 5, 3, 2, 6] have been proposed…
Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?) in different languages by reasoning a tail entity t thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained…
Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…
The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is…
Given a natural language phrase, relation linking aims to find a relation (predicate or property) from the underlying knowledge graph to match the phrase. It is very useful in many applications, such as natural language question answering,…
Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…
Multi-target prediction (MTP) is concerned with the simultaneous prediction of multiple target variables of diverse type. Due to its enormous application potential, it has developed into an active and rapidly expanding research field that…
Information systems usually show as a particular point of failure the vagueness between user search terms and the knowledge orders of the information space in question. Some kind of guided searching therefore becomes more and more important…
Complex software-driven systems often interleave distributed, concurrent computation processes with physical interactions with the environment. Developing these systems more efficiently and safely can be achieved by employing actionable,…
Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…