Focused Entailment Graphs for Open IE Propositions
By Omer Levy, Ido Dagan, Jacob Goldberger. 2014
47 citations recorded by the source corpus.
Open IE methods extract structured propositions from text. However, these propositions are neither consolidated nor generalized, and querying them may lead to insufficient or redundant information. This work suggests an approach to organize open IE propositions using entailment graphs. The entailment relation unifies equivalent propositions and induces a specific-to-general structure. We create a large dataset of gold-standard proposition entailment graphs, and provide a novel algorithm for automatically constructing them. Our analysis shows that predicate entailment is extremely context-sensitive, and that current lexical-semantic resources do not capture many of the lexical inferences induced by proposition entailment.
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Omer Levy
- Percy Liang
- Mohit Bansal
- Hannaneh Hajishirzi
- Jonathan Berant
- Eunsol Choi
- Jianfeng Gao
In Molecular Biology
- Luke S. Zettlemoyer
- Omer Levy
- Ido Dagan
- Daniel S. Weld
- Mandar Joshi
- Chris Biemann
- Percy Liang
- Jonathan Berant
Citations in the corpus
- Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations (2018, unknown): “…on 10 standard datasets: BLESS (Baroni & Lenci, 2011), EVALution (Santus et al., 2015), (Benotto, 2015), (Weeds et al., 2014), BIBLESS (Kiela et al., 2015), (Baroni et al., 2012), (Kotlerman et al., 2010), (Levy et al., 2014), HypeNet-Test (Shwartz et al., 2016), and (Turney & Mohammad, 2015).”
- Do Supervised Distributional Methods Really Learn Lexical Inference Relations? (2015, methodology): “(Levy et al., 2014) Based on manually annotated entailment graphs of subject-verb-object tuples (propositions).”
- Annotating Relation Inference in Context via Question Answering (2016, background): “Levy et al. (2014) annotated inference between in-stantiated relations sharing at least one argument (“aspirin eliminates headaches” → “drugs treat headaches”).”
- pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference (2018, methodology): “Method We interpolate pair2vec and 3CosAdd (Mikolov et al., 2013b; Levy et al., 2014) scores on fastText embeddings, as follows: where a , b , x , and y represent fastText embed-dings 6 and r a,b , r x,y represent the pair2vec embedding for the word pairs ( a, b ) and ( x, y ) , respectively; α is…”