Reading The Web with Learned Syntactic-Semantic Inference Rules

By Ni Lao, A. Subramanya, Fernando C Pereira, William W. Cohen. 2012

90 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

End-to-end Differentiable Proving (2017, background): “In addition, NTPs are related to random walk [48, 49, 11, 12] and path encoding models [14, 16].”
Open Question Answering with Weakly Supervised Embedding Models (2014, background): “Initial works attempting to learn to connect KBs and natural language with less supervision have actually been tackling the information extraction problem [16,11,14,19].”
Representing Text for Joint Embedding of Text and Knowledge Bases (2015, methodology): “To incorporate textual information, we follow prior work (Lao et al., 2012; Riedel et al., 2013) and represent both textual and knowledge base relations in a single graph of “universal” relations.”
Modeling Relation Paths for Representation Learning of Knowledge Bases (2015, methodology): “Relation paths have also been used for inference on large-scale KBs, such as Path Ranking algorithm (PRA) (Lao and Cohen, 2010), which has been adopted for expert ﬁnding (Lao and Cohen, 2010) and information retrieval (Lao et al., 2012).”
PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text (2019, methodology): “Combinations of KBs and text have also been used for relation extraction and Knowledge Base Completion (KBC) (Lao et al., 2012; Toutanova et al., 2015; Das et al., 2017).”
Observed versus latent features for knowledge base and text inference (2015, methodology): “…al., 2014; Yang et al., 2015), work containing comparisons between observed and latent feature mod- 57 els (Dong et al., 2014; Nickel et al., 2014), and work using inference from both text and knowledge base relations (Lao et al., 2012; Riedel et al., 2013; Dong et al., 2014; Gardner et al., 2014).”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “:3) arraga et al., 2015) improve the ef ﬁ ciency of AMIE RLvLR (Omran et al., 2018) reduce the search space by the embedding technique RuLES (Ho et al., 2018) leverage the embedding technique to measure the quality of the rules Neural-Symbolic Reasoning Symbolic-driven Neural Reasoning KALE (Guo et ”
Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks (2016, methodology): “Lao et al. (2012) extend PRA by augmenting KB-schema relations with observed text patterns (also known as OpenIE relations (Banko et al., 2007)).”
Incorporating Relation Paths in Neural Relation Extraction (2016, methodology): “Path Ranking algorithm (PRA) (Lao and Co-hen, 2010) has been adopted for expert ﬁnding (Lao and Cohen, 2010), information retrieval (Lao et al., 2012), and further for relation classiﬁcation based on KB structure (Lao et al., 2011; Gardner et al., 2013).”
Compositional Vector Space Models for Knowledge Base Completion (2015, methodology): “On this challenging large-scale dataset our compositional method outperforms PRA (Lao et al., 2012), and Cluster PRA (Gardner et al., 2013) by 11% and 7% respectively.”
Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text (2018, background): “Another line of work has looked at learning combined representations of KBs and text for relation extraction and Knowledge Base Completion (KBC) (Lao et al., 2012; Riedel et al., 2013; Toutanova et al., 2015; Verga et al., 2016; Das et al., 2017b; Han et al., 2016).”
Multi-Hop Knowledge Graph Reasoning with Reward Shaping (2018, unknown): “Early work treats it as a link prediction problem and perform maximum-likelihood classiﬁcation over either discrete path features (Lao et al., 2011, 2012; Gardner et al., 2013) or their hidden representations in a vector space (Guu et al., 2015; Toutanova et al., 2016; Das et al., 2017).”