scholarly journals Joint Prediction of Word Alignment with Alignment Types

2017 ◽  
Vol 5 ◽  
pp. 501-514
Author(s):  
Anahita Mansouri Bigvand ◽  
Te Bu ◽  
Anoop Sarkar

Current word alignment models do not distinguish between different types of alignment links. In this paper, we provide a new probabilistic model for word alignment where word alignments are associated with linguistically motivated alignment types. We propose a novel task of joint prediction of word alignment and alignment types and propose novel semi-supervised learning algorithms for this task. We also solve a sub-task of predicting the alignment type given an aligned word pair. In our experimental results, the generative models we introduce to model alignment types significantly outperform the models without alignment types.

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 198
Author(s):  
Stephen Fox

Active inference is a physics of life process theory of perception, action and learning that is applicable to natural and artificial agents. In this paper, active inference theory is related to different types of practice in social organization. Here, the term social organization is used to clarify that this paper does not encompass organization in biological systems. Rather, the paper addresses active inference in social organization that utilizes industrial engineering, quality management, and artificial intelligence alongside human intelligence. Social organization referred to in this paper can be in private companies, public institutions, other for-profit or not-for-profit organizations, and any combination of them. The relevance of active inference theory is explained in terms of variational free energy, prediction errors, generative models, and Markov blankets. Active inference theory is most relevant to the social organization of work that is highly repetitive. By contrast, there are more challenges involved in applying active inference theory for social organization of less repetitive endeavors such as one-of-a-kind projects. These challenges need to be addressed in order for active inference to provide a unifying framework for different types of social organization employing human and artificial intelligence.


2010 ◽  
Vol 36 (3) ◽  
pp. 481-504 ◽  
Author(s):  
João V. Graça ◽  
Kuzman Ganchev ◽  
Ben Taskar

Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Probabilistic models for word alignment present a fundamental trade-off between richness of captured constraints and correlations versus efficiency and tractability of inference. In this article, we use the Posterior Regularization framework (Graça, Ganchev, and Taskar 2007) to incorporate complex constraints into probabilistic models during learning without changing the efficiency of the underlying model. We focus on the simple and tractable hidden Markov model, and present an efficient learning algorithm for incorporating approximate bijectivity and symmetry constraints. Models estimated with these constraints produce a significant boost in performance as measured by both precision and recall of manually annotated alignments for six language pairs. We also report experiments on two different tasks where word alignments are required: phrase-based machine translation and syntax transfer, and show promising improvements over standard methods.


2020 ◽  
Vol 34 (05) ◽  
pp. 8886-8893
Author(s):  
Kai Song ◽  
Kun Wang ◽  
Heng Yu ◽  
Yue Zhang ◽  
Zhongqiang Huang ◽  
...  

We investigate the task of constraining NMT with pre-specified translations, which has practical significance for a number of research and industrial applications. Existing works impose pre-specified translations as lexical constraints during decoding, which are based on word alignments derived from target-to-source attention weights. However, multiple recent studies have found that word alignment derived from generic attention heads in the Transformer is unreliable. We address this problem by introducing a dedicated head in the multi-head Transformer architecture to capture external supervision signals. Results on five language pairs show that our method is highly effective in constraining NMT with pre-specified translations, consistently outperforming previous methods in translation quality.


2021 ◽  
Author(s):  
Xhoena Polisi ◽  
Ali Osman Topal ◽  
Arban Uka

Abstract Caused by an extra copy of the human chromosome21 (Hsa21), Down syndrome produces an intellectual disability that is still unknown and requires further research in order to have a better perception. One research conducted in this area of study has analysed different protein levels of the Ts65Dn mouse model of DS. Many researchers are trying to find the critical proteins that categorize the mice classes accurately by using machine learning. In this study, we expand the problem by trying to find the critical proteins that affect different types of learning. The protein subsets are found using forward feature selection method, ReliefF respectively and four different supervised learning algorithms are used. The experimental results are compared with previous related work, and demonstrated that the proposed method outperforms, or is comparable to, its competitors in term of accuracy. Then, a thorough analysis is done to identify the critical proteins for each learning case, by lowering the number to 9 critical proteins that can help in a better categorization of the mice. We hope that our work withhelp the scientists on their further research on finding a treatment that may help the learning process and ease the intellectual disability caused by Down Syndrome.


1967 ◽  
Vol 19 (1) ◽  
pp. 64-69 ◽  
Author(s):  
D. R. J. Laming

A large number of subjects was required for a series of choice-reaction experiments. An ample supply of volunteer subjects was obtained without excessive trouble by sending a circular letter to every undergraduate in Trinity College, Cambridge. Several different types of circular were compared, but none of them proved any more effective than the others. A probabilistic model is developed which accounts adequately for the times times taken by the undergraduates to reply. The discussion following covers the implication of this model, and a technical reason why the different letters should appear equally effective.


2021 ◽  
Vol 2 ◽  
Author(s):  
George Tsialiamanis ◽  
David J. Wagg ◽  
Nikolaos Dervilis ◽  
Keith Worden

Abstract A framework is proposed for generative models as a basis for digital twins or mirrors of structures. The proposal is based on the premise that deterministic models cannot account for the uncertainty present in most structural modeling applications. Two different types of generative models are considered here. The first is a physics-based model based on the stochastic finite element (SFE) method, which is widely used when modeling structures that have material and loading uncertainties imposed. Such models can be calibrated according to data from the structure and would be expected to outperform any other model if the modeling accurately captures the true underlying physics of the structure. The potential use of SFE models as digital mirrors is illustrated via application to a linear structure with stochastic material properties. For situations where the physical formulation of such models does not suffice, a data-driven framework is proposed, using machine learning and conditional generative adversarial networks (cGANs). The latter algorithm is used to learn the distribution of the quantity of interest in a structure with material nonlinearities and uncertainties. For the examples considered in this work, the data-driven cGANs model outperforms the physics-based approach. Finally, an example is shown where the two methods are coupled such that a hybrid model approach is demonstrated.


2021 ◽  
Author(s):  
Frédéric Parrenin ◽  
Lucie Bazin ◽  
Christo Buizert ◽  
Emilie Capron ◽  
Jai Chowdry Beeman ◽  
...  

<p>Past climatic and environmental changes can be reconstructed thanks to paleoclimatic archives such as ice cores, marine sediment cores, lake sediment cores, speleothems, tree rings, corals, etc. The dating of these natural archives is crucial for deciphering the temporal sequence of events during past climate changes. It is also essential to estimate the absolute and relative errors of such estimated chronologies. This task is, however, complex since it involves the combination of different dating approaches on different paleoclimatic sites and often different types of archives. Here we present Paleochrono, a new probabilistic model to derive a common and probalistically optimal chronology for several paleoclimatic sites with potentially different types of archives. Paleochrono is based on the inversion of an archiving model: a varying deposition rate (also named sedimentation or accumulation rate) and also, for ice cores, a lock-in-depth of air bubbles (since air is not trapped at surface) and a thinning function (since ice undergoes flow). The model integrates several types of chronological information: prior knowledge of the archiving process, independently dated horizons, depth intervals of known duration, undated stratigraphic links between records, and, for ice cores, Δdepth observations (depth differences between synchronous events recorded in the bubbles and ice, respectively). The optimization is formulated as a least-squares problem, assuming that all densities of probabilities are near-Gaussian and that the model is almost linear in the vicinity of the best solution. Paleochrono is the successor of IceChrono, which was dealing only with ice-core records. Paleochrono performs better than IceChrono in terms of computational efficiency, ease of use, and accuracy. We demonstrate the ability of Paleochrono in a new AICC2012-Hulu dating experiment, which combines the AICC2012 dating experiment, based on records from five polar ice cores, with data from two U/Th-dated speleothems from Hulu Cave (China). We analyse the performance of Paleochrono in terms of computing time and memory usage in various dating experiments. Paleochrono is freely available under the MIT open source license.</p>


2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Liang Tian ◽  
Derek F. Wong ◽  
Lidia S. Chao ◽  
Francisco Oliveira

In the last years, researchers conducted several studies to evaluate the machine translation quality based on the relationship between word alignments and phrase table. However, existing methods usually employ ad-hoc heuristics without theoretical support. So far, there is no discussion from the aspect of providing a formula to describe the relationship among word alignments, phrase table, and machine translation performance. In this paper, on one hand, we focus on formulating such a relationship for estimating the size of extracted phrase pairs given one or more word alignment points. On the other hand, a corpus-motivated pruning technique is proposed to prune the default large phrase table. Experiment proves that the deduced formula is feasible, which not only can be used to predict the size of the phrase table, but also can be a valuable reference for investigating the relationship between the translation performance and phrase tables based on different links of word alignment. The corpus-motivated pruning results show that nearly 98% of phrases can be reduced without any significant loss in translation quality.


2011 ◽  
Vol 48 (03) ◽  
pp. 832-842
Author(s):  
Nader Ebrahimi ◽  
Yarong Yang

We construct an integrated probabilistic model to capture interactions between atoms of a nanocomponent. We then use this model to assess reliabilities of nanocomponents with different structures. Several properties of our proposed model are also described under a sparseness condition. The model is an extension of our previous model based on Markovian random field theory. The proposed integrated model is flexible in that pairwise relationship information among atoms as well as features of individual atoms can be easily incorporated. An important feature that distinguishes the integrated probabilistic model from our previous model is that the integrated approach uses all available sources of information with different weights for different types of interaction. In this paper we consider the nanocomponent at a fixed moment of time, say the present moment, and we assume that the present state of the nanocomponent depends only on the present states of its atoms.


2010 ◽  
Vol 36 (3) ◽  
pp. 303-339 ◽  
Author(s):  
Yang Liu ◽  
Qun Liu ◽  
Shouxun Lin

Word alignment plays an important role in many NLP tasks as it indicates the correspondence between words in a parallel text. Although widely used to align large bilingual corpora, generative models are hard to extend to incorporate arbitrary useful linguistic information. This article presents a discriminative framework for word alignment based on a linear model. Within this framework, all knowledge sources are treated as feature functions, which depend on a source language sentence, a target language sentence, and the alignment between them. We describe a number of features that could produce symmetric alignments. Our model is easy to extend and can be optimized with respect to evaluation metrics directly. The model achieves state-of-the-art alignment quality on three word alignment shared tasks for five language pairs with varying divergence and richness of resources. We further show that our approach improves translation performance for various statistical machine translation systems.


Sign in / Sign up

Export Citation Format

Share Document