Leveraging Linguistic Structure For Open Domain Information Extraction

By Gabor Angeli, Melvin Johnson, Christopher D. Manning. Annual Meeting of the Association for Computational Linguistics, 2015

821 citations recorded by the source corpus.

Relation triples produced by open domain information extraction (open IE) systems are useful for question answering, inference, and other IE tasks. Traditionally these are extracted using a large set of patterns; however, this approach is brittle on out-of-domain text and long-range dependencies, and gives no insight into the substructure of the arguments. We replace this large pattern set with a few patterns for canonically structured sentences, and shift the focus to a classifier which learns to extract self-contained clauses from longer sentences. We then run natural logic inference over these short clauses to determine the maximally specific arguments for each candidate triple. We show that our approach outperforms a state-of-the-art open IE system on the end-to-end TAC-KBP 2013 Slot Filling task.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/3171ec184b5fec0bc7b47356ad74d8598e858ddc

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

In Information Systems

Citations in the corpus

Deep Biaffine Attention for Neural Dependency Parsing (2016, methodology): “…humans and computers alike to understand—have been found to be extremely useful for a sizable number of NLP tasks, especially those involving natural language understanding in some way (Bowman et al., 2016; Angeli et al., 2015; Levy & Goldberg, 2014; Toutanova et al., 2016; Parikh et al., 2015).”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, background): “” and assumes that a relation extraction (e.g., OpenIE [2]) system is available to convert natural language queries or statements from the user into query triples ( s , r ?, t ) or (supporting) fact triples ( s , r , t ).”
Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, methodology): “Similarly, it assumes an information extraction tool like OpenIE (Angeli et al., 2015) is employed to extract facts as triples (h, r, t) from”
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward (2020, methodology): “, 2014) to first obtain outputs from coreference resolution and open information extraction (OpenIE) models (Angeli et al., 2015).”
Most “babies” are “little” and most “problems” are “huge”: Compositional Entailment in Adjective-Nouns (2016, methodology): “While these are not the same question, they are often conﬂated in NLP, for example, in information extraction, when we use statements about ANs as justiﬁcation for extracting facts about the head N (Angeli et al., 2015).”
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning (2018, methodology): “These triples are extracted from the observations using Stanford’s Open Information Extraction (OpenIE) (Angeli et al., 2015).”
Describing a Knowledge Base (2018, methodology): “However, the performance of state-of-theart open-domain slot filling (Wu and Weld, 2010; Fader et al., 2011; Min et al., 2012; Xu et al., 2013; Angeli et al., 2015; Bhutani et al., 2016; Yu et al., 2017) is still far from satisfactory to serve as an automatic extraction tool for evaluating generatio”
Stack-Pointer Networks for Dependency Parsing (2018, background): “, 2017), information extraction (Nguyen et al., 2009; Angeli et al., 2015; Peng et al., 2017), word sense disambiguation (Fauceglia et al.”
Matching the Blanks: Distributional Similarity for Relation Learning (2019, methodology): “Inspired by open information extraction (Banko et al., 2007; Angeli et al., 2015), which derives relations”
GSum: A General Framework for Guided Neural Abstractive Summarization (2020, methodology): “For oracle extraction, we ﬁrst use Stanford Ope-nIE (Angeli et al., 2015) to extract relational triples from the source document.”
So-Called Non-Subsective Adjectives (2016, background): “In information extraction, it is assumed that systems cannot extract useful rules from sentences containing non-subsective modifiers (Angeli et al., 2015), and in RTE, it is assumed that systems should uniformly penalize insertions and deletions of non-subsective adjectives (Amoia and Gardent, 2006)”
Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning (2021, methodology): “Knowledge graph triples are extracted from sentences using Stanford Open Information Extraction (OpenIE) (Angeli et al., 2015).”
Automated Storytelling via Causal, Commonsense Plot Ordering (2020, methodology): “Simultaneously, we also extract a setR of 〈subject, relation, object〉 triples from the story text using OpenIE (Angeli et al. 2015).”
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, background): “…(1) Open information extraction (Open IE) , as shown in Figure 8, extracts relation phrases and arguments (entities) from text (Banko et al., 2007; Fader et al., 2011; Mausam et al., 2012; Del Corro and Gemulla, 2013; Angeli et al., 2015; Stanovsky and Dagan, 2016; Mausam, 2016; Cui et al., 2018).”
Toward Automated Quest Generation in Text-Adventure Games (2019, methodology): “This graph is partially extracted from static cooking guides online using a mixture of OpenIE (Angeli et al., 2015) and hand-authored rules to account for the irregularities of cooking guides.”
Relational Memory-Augmented Language Models (2022, methodology): “In this work, we use OpenIE (Angeli et al., 2015; Etzioni et al., 2008) to obtain relation triples.”
G-DAug: Generative Data Augmentation for Commonsense Reasoning (2020, methodology): “Specifically, we run the Stanford Open IE package (Angeli et al., 2015) and report the number of unique triplets, relations and entities extracted from our WINOGRANDE-M data sets in Figure 4.”