Results 1 - 10
of
10
A hierarchical bayesian model for unsupervised induction of script knowledge
- In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics
, 2014
"... Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valu-able resource for NLP applications. We present a hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities. Events and con ..."
Abstract
-
Cited by 9 (2 self)
- Add to MetaCart
(Show Context)
Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valu-able resource for NLP applications. We present a hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities. Events and constraints on event ordering are induced jointly in one unified framework. We use a statistical model over permutations which captures event ordering constraints in a more flexible way than previous approaches. In order to alleviate the sparsity problem caused by using relatively small datasets, we incorporate in our hierarchical model an informed prior on word distributions. The resulting model substantially outperforms a state-of-the-art method on the event ordering task. 1
Inducing Neural Models of Script Knowledge
"... Induction of common sense knowledge about prototypical sequence of events has recently received much attention (e.g., Chambers and Jurafsky (2008); Regneri et al. (2010)). Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representa ..."
Abstract
-
Cited by 7 (0 self)
- Add to MetaCart
(Show Context)
Induction of common sense knowledge about prototypical sequence of events has recently received much attention (e.g., Chambers and Jurafsky (2008); Regneri et al. (2010)). Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representations of event real-izations are computed based on distributed representations of predicates and their ar-guments, and then these representations are used to predict prototypical event or-derings. The parameters of the composi-tional process for computing the event rep-resentations and the ranking component of the model are jointly estimated. We show that this approach results in a sub-stantial boost in performance on the event ordering task with respect to the previous approaches, both on natural and crowd-sourced texts. 1
Learning to Extract International Relations from Political Context
"... We describe a new probabilistic model for extracting events between major political actors from news corpora. Our unsupervised model brings together familiar components in natural language processing (like parsers and topic models) with contextual political information— temporal and dyad dependence— ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
We describe a new probabilistic model for extracting events between major political actors from news corpora. Our unsupervised model brings together familiar components in natural language processing (like parsers and topic models) with contextual political information— temporal and dyad dependence—to infer latent event classes. We quantitatively evaluate the model’s performance on political science benchmarks: recovering expert-assigned event class valences, and detecting real-world conflict. We also conduct a small case study based on our model’s inferences. A supplementary appendix, and replication software/data are available online, at:
Unsupervised Discovery of Biographical Structure from Text
"... event classes in biographies, based on a prob-abilistic latent-variable model. Taking as in-put timestamped text, we exploit latent corre-lations among events to learn a set of event classes (such as BORN, GRADUATES HIGH SCHOOL, and BECOMES CITIZEN), along with the typical times in a person’s life w ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
event classes in biographies, based on a prob-abilistic latent-variable model. Taking as in-put timestamped text, we exploit latent corre-lations among events to learn a set of event classes (such as BORN, GRADUATES HIGH SCHOOL, and BECOMES CITIZEN), along with the typical times in a person’s life when those events occur. In a quantitative evalua-tion at the task of predicting a person’s age for a given event, we find that our genera-tive model outperforms a strong linear regres-sion baseline, along with simpler variants of the model that ablate some features. The ab-stract event classes that we learn allow us to perform a large-scale analysis of 242,970 Wikipedia biographies. Though it is known that women are greatly underrepresented on Wikipedia—not only as editors (Wikipedia, 2011) but also as subjects of articles (Reagle and Rhue, 2011)—we find that there is a bias in their characterization as well, with biogra-phies of women containing significantly more emphasis on events of marriage and divorce than biographies of men. 1
A Unified Bayesian Model of Scripts, Frames and Language
"... We present the first probabilistic model to capture all lev-els of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fill-more’s related notion of frame, as captured in sentence-level, ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
We present the first probabilistic model to capture all lev-els of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fill-more’s related notion of frame, as captured in sentence-level, FrameNet semantic parses; as part of this, we resurrect the coupling among Minsky’s frames, Schank’s scripts and Fill-more’s frames, as originally laid out by those authors. Em-pirically, our approach yields improved scenario representa-tions, reflected quantitatively in lower surprisal and more co-herent latent scenarios.
Unsupervised induction of semantic roles within a reconstructionerror minimization framework
- In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
, 2015
"... We introduce a new approach to unsupervised estimation of feature-rich semantic role la-beling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexi-cal features; (2) a reconstruction compon ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
We introduce a new approach to unsupervised estimation of feature-rich semantic role la-beling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexi-cal features; (2) a reconstruction component: a tensor factorization model which relies on roles to predict argument fillers. When the components are estimated jointly to minimize errors in argument reconstruction, the induced roles largely correspond to roles defined in an-notated resources. Our method performs on par with most accurate role induction methods on English and German, even though, unlike these previous approaches, we do not incorpo-rate any prior linguistic knowledge about the languages. 1
Learning Frames from Text with an Unsupervised Latent Variable Model
, 2014
"... We develop a probabilistic latent-variable model to discover semantic frames—types of events and their participants—from corpora. We present a Dirichlet-multinomial model in which frames are latent cate-gories that explain the linking of verb-subject-object triples, given document-level sparsity. We ..."
Abstract
- Add to MetaCart
We develop a probabilistic latent-variable model to discover semantic frames—types of events and their participants—from corpora. We present a Dirichlet-multinomial model in which frames are latent cate-gories that explain the linking of verb-subject-object triples, given document-level sparsity. We analyze what the model learns, and compare it to FrameNet, noting it learns some novel and interesting frames. This document also contains a discussion of inference issues, including concentration parameter learn-ing; and a small-scale error analysis of syntactic parsing accuracy. Note: this work was originally posted online October 2012 as part of CMU MLD’s Data Analysis Project requirement. This version has no new experiments or results, but has added some discussion of new related work. 1
A Step-wise Usage-based Method for Inducing Polysemy-aware Verb Classes
"... Abstract We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb uses in a scalable manner, but also deal with verb polysemy, which is bypassed by most of the previous studies on verb clustering. In our experiments, we acquire semantic frames and verb classes from two giga-word corpora, the larger comprising 20 billion words. The effectiveness of our approach is verified through quantitative evaluations based on polysemy-aware gold-standard data.
Statistical Models for Frame-Semantic Parsing
"... We present a brief history and overview of statistical methods in frame-semantic parsing – the automatic analysis of text using the theory of frame semantics. We discuss how the FrameNet lexicon and frameannotated datasets have been used by statistical NLP researchers to build usable, state-of-the-a ..."
Abstract
- Add to MetaCart
We present a brief history and overview of statistical methods in frame-semantic parsing – the automatic analysis of text using the theory of frame semantics. We discuss how the FrameNet lexicon and frameannotated datasets have been used by statistical NLP researchers to build usable, state-of-the-art systems. We also focus on future directions in frame-semantic parsing research, and discuss NLP applications that could benefit from this line of work. 1 Frame-Semantic Parsing Frame-semantic parsing has been considered as the task of automatically finding semantically
