Disambiguating grammars by exclusion of sub-parse trees

A method is presented for disambiguation of grammars, based on the idea of excluding certain forbidden sub-parse trees. Combined with recent developments in the theory of parser generation for ambiguous grammars, the method disambiguates large classes of grammars guaranteeing that the generated language is unchanged.     

Disambiguating grammars by exclusion of sub-parse trees

A method is presented for disambiguation of grammars, based on the idea of excluding certain forbidden sub-parse trees. Combined with recent developments in the theory of parser generation for ambiguous grammars, the method disambiguates large classes of grammars guaranteeing that the generated language is unchanged. Received February 28, 1994 / May 11, 1995     

Disambiguating visual motion through contextual feedback modulation

Motion of an extended boundary can be measured locally by neurons only orthogonal to its orientation (aperture problem) while this ambiguity is resolved for localized image features, such as corners or nonocclusion junctions. The integration of local motion signals sampled along the outline of a moving form reveals the object velocity. We propose a new model of V1-MT feedforward and feedback processing in which localized V1 motion signals are integrated along the feedforward path by model MT cells. Top-down feedback from MT cells in turn emphasizes model V1 motion activities of matching velocity by excitatory modulation and thus realizes an attentional gating mechanism. The model dynamics implement a guided filling-in process to disambiguate motion signals through biased on-center, off-surround competition. Our model makes predictions concerning the time course of cells in area MT and V1 and the disambiguation process of activity patterns in these areas and serves as a means to link physiological mechanisms with perceptual behavior. We further demonstrate that our model also successfully processes natural image sequences.     

一种基于概念关联式的词义消岐方法

词义排岐是自然语言处理中最关键也是最困难的问题之一,至今仍没有得到完全有效的解决。在研究HNC表达汉语知识的基础上,提出了一种基于概念关联式的汉语词义消歧方法,用于处理汉语的歧义字段。该方法综合了词语概念的层次性、网络性、结构性特征,用一种统一的表示式来规范这类特征,解决了多个不同概念之间的知识关联表示问题。实验对20个汉语高频多义词进行了测试,平均正确率为94%,验证了该方法的有效性。     

Disambiguating authors in citations on the web and authorship correlations

Members of the academic community have increasingly turned to digital libraries to search for the latest work of their peers. On account of their role in the academic community, it is very important that these digital libraries collect citations in a consistent, accurate, and up-to-date manner, yet they do not correctly compile citations for myriads of authors for various reasons including authors with the same name, a problem known as the “name ambiguity problem.” This problem occurs when multiple authors share the same name and particularly when names are simplified as in cases where names merely contain the first initial and the last name. This paper proposes a reliable and accurate pair-wise similarities approach to disambiguate names using supervised classification on Web correlations and authorship correlations. This approach makes use of Web correlations among citations assuming citations that co-refer on publication lists on the Web should to refer to the same author. This approach also makes use of authorship correlations assuming citations with the same rare author name refer to the same author, and furthermore, citations with the same full names of authors or e-mail addresses likely refer to the same author. These two types of correlations are measured in our approach using pair-wise similarity metrics. In addition, a binary classifier, as part of supervised classification, is applied to label matching pairs of citations using pair-wise similarity metrics, and these labels are then used to group citations into different clusters such that each cluster represents an individual author. Results show our approach greatly improves upon the name disambiguation accuracy and performance of other proposed approaches, especially in some name clusters with high degree of ambiguity.     

Disambiguating named entities with deep supervised learning via crowd labels

Named entity disambiguation (NED) is the task of linking mentions of ambiguous entities to their referenced entities in a knowledge base such as Wikipedia. We propose an approach to effectively disentangle the discriminative features in the manner of collaborative utilization of collective wisdom (via human-labeled crowd labels) and deep learning (via human-generated data) for the NED task. In particular, we devise a crowd model to elicit the underlying features (crowd features) from crowd labels that indicate a matching candidate for each mention, and then use the crowd features to fine-tune a dynamic convolutional neural network (DCNN). The learned DCNN is employed to obtain deep crowd features to enhance traditional hand-crafted features for the NED task. The proposed method substantially benefits from the utilization of crowd knowledge (via crowd labels) into a generic deep learning for the NED task. Experimental analysis demonstrates that the proposed approach is superior to the traditional hand-crafted features when enough crowd labels are gathered.     

Disambiguating Visual Motion by Form-Motion Interaction—a Computational Model

The neural mechanisms underlying motion segregation and integration still remain unclear to a large extent. Local motion estimates often are ambiguous in the lack of form features, such as corners or junctions. Furthermore, even in the presence of such features, local motion estimates may be wrong if they were generated near occlusions or from transparent objects. Here, a neural model of visual motion processing is presented that involves early stages of the cortical dorsal and ventral pathways. We investigate the computational mechanisms of V1-MT feedforward and feedback processing in the perception of coherent shape motion. In particular, we demonstrate how modulatory MT-V1 feedback helps to stabilize localized feature signals at, e.g. corners, and to disambiguate initial flow estimates that signal ambiguous movement due to the aperture problem for single shapes. In cluttered environments with multiple moving objects partial occlusions may occur which, in turn, generate erroneous motion signals at points of overlapping form. Intrinsic-extrinsic region boundaries are indicated by local T-junctions of possibly any orientation and spatial configuration. Such junctions generate strong localized feature tracking signals that inject erroneous motion directions into the integration process. We describe a simple local mechanism of excitatory form-motion interaction that modifies spurious motion cues at T-junctions. In concert with local competitive-cooperative mechanisms of the motion pathway the motion signals are subsequently segregated into coherent representations of moving shapes. Computer simulations demonstrate the competency of the proposed neural model.     

Disambiguating identity web references using Web 2.0 data and semantics

As web users disseminate more of their personal information on the web, the possibility of these users becoming victims of lateral surveillance and identity theft increases. Therefore web resources containing this personal information, which we refer to as identity web references must be found and disambiguated to produce a unary set of web resources which refer to a given person. Such is the scale of the web that forcing web users to monitor their identity web references is not feasible, therefore automated approaches are required. However, automated approaches require background knowledge about the person whose identity web references are to be disambiguated. Within this paper we present a detailed approach to monitor the web presence of a given individual by obtaining background knowledge from Web 2.0 platforms to support automated disambiguation processes. We present a methodology for generating this background knowledge by exporting data from multiple Web 2.0 platforms as RDF data models and combining these models together for use as seed data. We present two disambiguation techniques; the first using a semi-supervised machine learning technique known as Self-training and the second using a graph-based technique known as Random Walks, we explain how the semantics of data supports the intrinsic functionalities of these techniques. We compare the performance of our presented disambiguation techniques against several baseline measures including human processing of the same data. We achieve an average precision level of 0.935 for Self-training and an average f-measure level of 0.705 for Random Walks in both cases outperforming several baselines measures.     

基于加权投票K—近邻法的生物医学缩略语消歧

生物医学文献信息抽取对充分挖掘利用生物医学领域取得的重要成果,促进生物医学的进一步发展具有重要意义。本文针对生物医学缩略语的分析理解问题,提出了基于加权投票K—近邻法的生物医学缩略语消歧算法。该算法基于“One Sense Per Discourse”假设自动生成带类标实例数据,消歧特征选用能表达文本主题的全局特征词,分类算法采用加权投票K—近邻法。在包含177 762篇Medline摘要的真实语料上进行的实验表明,本文所提出的算法明显优于相关工作中的算法。此外,实验还表明,对于缩略语消歧,加权投票K—近邻法与经典K—近邻法相比,不但具有高的预测准确率,而且性能更加稳定。     

Multimodal Machine Learning for Natural Language Processing: Disambiguating Prepositional Phrase Attachments with Images

Neural Processing Letters - Although documents are increasingly multimodal, their automatic processing is often monomodal. In particular, natural language processing tasks are typically performed...     

Secondary predication and the lexical representation of verbs

In this paper it is assumed that syntactic structure is projected from the lexicon. The lexical representation, which encodes the linguistically relevant aspects of the meanings of words, thus determines and constrains the syntax. Therefore, if semantic analysis of syntactic structures is to be possible, it is necessary to determine the content and structure of lexical semantic representations. The paper argues for a certain form of lexical representation by presenting the problem of a particular non-standard structure, the verb phrase of the form V-NP-Adj corresponding to various constructions of secondary predication in English. It is demonstrated that the solution to the semantic analysis of this structure lies in the meaning of the structure's predicators, in particular the lexical semantic representation of the verb. Verbs are classified according to the configuration of the lexical semantic representations, whether basic or derived. It is these specific configurations that restrict the possibilities of secondary predication. Given the class of a verb, its relation to the secondary predicate is predictable; and the correct interpretation of the V-NP-Adj string is therefore possible.This work is based on papers presented to the 1988 meetings of the Canadian Linguistic Association and the Brandeis Workshop on Theoretical and Computational Issues in Lexical Semantics. I am grateful to the audiences at these two meetings for comments, and to Anna-Maria di Sciullo, Diane Massam, Yves Roberge and James Pustejovsky for helpful discussion. I also thank SSHRC for funding the research of which this work forms part.     

On the identification of verbs in computer programs of physiological models

The rationale for identifying verbs (actions modeled) in the source code of a mathematical model is presented, with algorithms leading to computational techniques for devising explanations of such models. Using flow graph methodology the source code of a program can be described as disjoint intervals of its directed acyclic graph. Intervals of this set containing complete loops represent the code structure conceptually equivalent to verbs modeled. In turn, such structures can be mapped uniquely as functional dependencies of the intensional form of a relational data base which is the model output. Simulation, then, can be viewed as retrieval, and the logical inferences of a model appear to be derivable via relational algebra of the data base. In these terms, a verb is a relation consisting of at least one variable defined in an interval. The relation's key attributes must include at least one variable, also defined in the interval. Verb definitions are essential if programs are to explain themselves.     

A robot language for parts handling based on hierarchical structure of verbs

An operation-level robot language for parts handling has been developed, in which stress is laid on the systematization of the hierarchical structure of verbs (and verb phases) and the realization of and interpreter of the language for controlling a robot arm. In this research, the circumstances are defined as a robot arm, shelves (work benches), boxes and objects on a floor. In the user's programming, eighteen verbs can be utilized: [Level 3] place on, stack on, lift down, carry, direct to, put in, put out, push and draw; [Level 2] have, lift and put; [Level 1] go, raise, lower, seize (grip), detach and turn. In the system, a verb module is reduced to a sequence of the verb modules immediately one level below it, and a series of control commands to a robot controller is automatically generated.     

Error diagnosis in a tutoring system for the conjugation and spelling of Dutch verbs

A flexible knowledge-based tutoring system for the conjugation and spelling of Dutch verbs is described. The program, called Het Spelraam, is intended to communicate procedural knowledge about the spelling of verb forms to students with elementary spelling knowledge. The student has to fill in gapped sentences. If an incorrect answer is entered, the system locates the point where the student deviated from the path through the spelling algorithm that is leading to the correct answer. From that particular point the student is guided through the spelling algorithm. The error diagnosis techniques applied are described in detail. Het Spelraam is a commercial product which is used in both schools and language-training institutes. Results from initial evaluations are promising.     

Combining formal concept analysis and translation to assign frames and semantic role sets to French verbs

In Natural Language Processing, verb classifications have been shown to be useful both theoretically (to capture syntactic and semantic generalisations about verbs) and practically (to support factorisation and the supervised learning of shallow semantic parsers). Acquiring such classifications manually is both costly and errror prone however. In this paper, we present a novel approach for automatically acquiring verb classifications. The approach uses FCA to build a concept lattice from existing linguistic resources; and stability and separation indices to extract from this lattice those concepts that most closely capture verb classes. The approach is evaluated on an established benchmark and shown to differ from previous approaches and in particular, from clustering approaches, in two main ways. First, it supports polysemy (because a verb may belong to several classes). Second, it naturally provides a syntactic and semantic characterisation of the verb classes produced (by creating concepts which systematically associate verbs with their syntactic and semantic attributes).     

Ez Japanese writer

Technical review

Ez Japanese writer