Results 1 - 10
of
96
Identifying relations for open information extraction. In:
- Proc. Conference on Empirical Methods in Natural Language Processing (EMNLP),
, 2011
"... Abstract Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. This paper shows that the output of state-ofthe-art Open IE systems is rife with uninformative and incoherent extractions. To overcome these problems, we ..."
Abstract
-
Cited by 140 (4 self)
- Add to MetaCart
(Show Context)
Abstract Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. This paper shows that the output of state-ofthe-art Open IE systems is rife with uninformative and incoherent extractions. To overcome these problems, we introduce two simple syntactic and lexical constraints on binary relations expressed by verbs. We implemented the constraints in the REVERB Open IE system, which more than doubles the area under the precision-recall curve relative to previous extractors such as TEXTRUNNER and WOE pos . More than 30% of REVERB's extractions are at precision 0.8 or highercompared to virtually none for earlier systems. The paper concludes with a detailed analysis of REVERB's errors, suggesting directions for future work.
Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations
"... Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web’s natural language text. Knowledge-based weak supervision, using structured data to heuristically label a training corpus, works towards this goal by enabling the automated learning of a potentially ..."
Abstract
-
Cited by 104 (15 self)
- Add to MetaCart
(Show Context)
Information extraction (IE) holds the promise of generating a large-scale knowledge base from the Web’s natural language text. Knowledge-based weak supervision, using structured data to heuristically label a training corpus, works towards this goal by enabling the automated learning of a potentially unbounded number of relation extractors. Recently, researchers have developed multiinstance learning algorithms to combat the noisy training data that can come from heuristic labeling, but their models assume relations are disjoint — for example they cannot extract the pair Founded(Jobs, Apple) and CEO-of(Jobs, Apple). This paper presents a novel approach for multi-instance learning with overlapping relations that combines a sentence-level extraction model with a simple, corpus-level component for aggregating the individual facts. We apply our model to learn extractors for NY Times text using weak supervision from Freebase. Experiments show that the approach runs quickly and yields surprising gains in accuracy, at both the aggregate and sentence level. 1
BabelNet: The automatic construction, evaluation and application of a . . .
- ARTIFICIAL INTELLIGENCE
, 2012
"... ..."
Open Information Extraction: The Second Generation
- PROCEEDINGS OF THE TWENTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
, 2011
"... How do we scale information extraction to the massive size and unprecedented heterogeneity of the Web corpus? Beginning in 2003, our KnowItAll project has sought to extract high-quality knowledge from the Web. In 2007, we introduced the Open Information Extraction (Open IE) paradigm which eschews ha ..."
Abstract
-
Cited by 41 (0 self)
- Add to MetaCart
How do we scale information extraction to the massive size and unprecedented heterogeneity of the Web corpus? Beginning in 2003, our KnowItAll project has sought to extract high-quality knowledge from the Web. In 2007, we introduced the Open Information Extraction (Open IE) paradigm which eschews handlabeled training examples, and avoids domainspecific verbs and nouns, to develop unlexicalized, domain-independent extractors that scale to the Web corpus. Open IE systems have extracted billions of assertions as the basis for both commonsense knowledge and novel question-answering systems. This paper describes the second generation of Open IE systems, which rely on a novel model of how relations and their arguments are expressed in English sentences to double precision/recall compared with previous systems such as TEXTRUNNER and WOE.
Learning 5000 relational extractors
- In ACL
, 2010
"... Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale ..."
Abstract
-
Cited by 31 (5 self)
- Add to MetaCart
Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations — more than an order of magnitude greater than any previous approach — with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. 1
Stanford typed dependencies manual
, 2008
"... The Stanford typed dependencies representation was designed to provide a simple description of the grammatical relationships in a sentence that can easily be understood and effectively used by people without linguistic expertise who want to extract textual relations. In particular, rather than the p ..."
Abstract
-
Cited by 27 (1 self)
- Add to MetaCart
(Show Context)
The Stanford typed dependencies representation was designed to provide a simple description of the grammatical relationships in a sentence that can easily be understood and effectively used by people without linguistic expertise who want to extract textual relations. In particular, rather than the phrase structure representations that have long dominated in the computational
Learning to simplify sentences with quasi-synchronous grammar and integer programming
- in Proceedings of the Conference on Empirical Methods in Natural Language Processing
"... Text simplification aims to rewrite text into simpler versions, and thus make information accessible to a broader audience. Most pre-vious work simplifies sentences using hand-crafted rules aimed at splitting long sentences, or substitutes difficult words using a prede-fined dictionary. This paper p ..."
Abstract
-
Cited by 24 (1 self)
- Add to MetaCart
(Show Context)
Text simplification aims to rewrite text into simpler versions, and thus make information accessible to a broader audience. Most pre-vious work simplifies sentences using hand-crafted rules aimed at splitting long sentences, or substitutes difficult words using a prede-fined dictionary. This paper presents a data-driven model based on quasi-synchronous grammar, a formalism that can naturally capture structural mismatches and complex rewrite operations. We describe how such a grammar can be induced from Wikipedia and propose an integer linear programming model for selecting the most appropriate simplifica-tion from the space of possible rewrites gen-erated by the grammar. We show experimen-tally that our method creates simplifications that significantly reduce the reading difficulty of the input, while maintaining grammaticality and preserving its meaning. 1
Weakly Supervised Training of Semantic Parsers
"... We present a method for training a semantic parser using only a knowledge base and an unlabeled text corpus, without any individually annotated sentences. Our key observation is that multiple forms of weak supervision can be combined to train an accurate semantic parser: semantic supervision from a ..."
Abstract
-
Cited by 20 (0 self)
- Add to MetaCart
(Show Context)
We present a method for training a semantic parser using only a knowledge base and an unlabeled text corpus, without any individually annotated sentences. Our key observation is that multiple forms of weak supervision can be combined to train an accurate semantic parser: semantic supervision from a knowledge base, and syntactic supervision from dependencyparsed sentences. We apply our approach to train a semantic parser that uses 77 relations from Freebase in its knowledge representation. This semantic parser extracts instances of binary relations with state-of-theart accuracy, while simultaneously recovering much richer semantic structures, such as conjunctions of multiple relations with partially shared arguments. We demonstrate recovery of this richer structure by extracting logical forms from natural language queries against Freebase. On this task, the trained semantic parser achieves 80 % precision and 56 % recall, despite never having seen an annotated logical form. 1
Joint learning of words and meaning representations for open-text semantic parsing
- In Proceedings of 15th International Conference on Artificial Intelligence and Statistics
, 2012
"... Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to lack of directly supervised data. We propose here a method that ..."
Abstract
-
Cited by 19 (5 self)
- Add to MetaCart
(Show Context)
Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to lack of directly supervised data. We propose here a method that learns to assign MRs to a wide range of text (using a dictionary of more than 70,000 words, which are mapped to more than 40,000 entities) thanks to a training scheme that combines learning from knowledge bases (WordNet and ConceptNet) with learning from raw text. The model jointly learns representations of words, entities and MRs via a multi-task training process operating on these diverse sources of data. Hence, the system ends up providing methods for knowledge acquisition and word-sense disambiguation within the context of semantic parsing in a single elegant framework. Experiments on these various tasks indicate the promise of the approach. 1
QAKiS: an open domain QA system based on relational patterns
- In Proc. of the 11th International Semantic Web Conference (ISWC 2012), demo paper
, 2012
"... Abstract. We present QAKiS, a system for open domain Question Answering over linked data. It addresses the problem of question interpretation as a relation-based match, where fragments of the question are matched to binary relations of the triple store, using relational textual patterns automaticall ..."
Abstract
-
Cited by 18 (5 self)
- Add to MetaCart
(Show Context)
Abstract. We present QAKiS, a system for open domain Question Answering over linked data. It addresses the problem of question interpretation as a relation-based match, where fragments of the question are matched to binary relations of the triple store, using relational textual patterns automatically collected. For the demo, the relational patterns are automatically extracted from Wikipedia, while DBpedia is the RDF data set to be queried using a natural language interface. 1
