A Semantic Network of English: The Mother of All WordNets

We give a brief outline of the design and contents of the English lexical database WordNet, which serves as a model for similarly conceived wordnets in several European languages. WordNet is a semantic network, in which the meanings of nouns, verbs, adjectives, and adverbs are represented in terms of their links to other (groups of) words via conceptual-semantic and lexical relations. Each part of speech is treated differently reflecting different semantic properties. We briefly discuss polysemy in WordNet, and focus on the case of meaning extensions in the verb lexicon. Finally, we outline the potential uses of WordNet not only for applications in natural language processing, but also for research in stylistic analyses in conjunction with a semantic concordance.     

Verb semantics for English-Chinese translation

A common practice in operational Machine Translation (MT) and Natural Language Processing (NLP) systems is to assume that a verb has a fixed number of senses and rely on a precompiled lexicon to achieve large coverage. This paper demonstrates that this assumption is too weak to cope with the similar problems of lexical divergences between languages and unexpected uses of words that give rise to cases outside of the pre-compiled lexicon coverage. We first examine the lexical divergences between English verbs and Chinese verbs. We then focus on a specific lexical selection problem—translating Englishchange-of-state verbs into Chinese verb compounds. We show that an accurate translation depends not only on information about the participants, but also on contextual information. Therefore, selectional restrictions on verb arguments lack the necessary power for accurate lexical selection. Second, we examine verb representation theories and practices in MT systems and show that under the fixed sense assumption, the existing representation schemes are not adequate for handling these lexical divergences and extending existing verb senses to unexpected usages. We then propose a method of verb representation based on conceptual lattices which allows the similarities among different verbs in different languages to be quantitatively measured. A prototype system UNICON implements this theory and performs more accurate MT lexical selection for our chosen set of verbs. An additional lexical module for UNICON is also provided that handles sense extension.     

SALDO: a touch of yin to WordNet’s yang

The English-language Princeton WordNet (PWN) and some wordnets for other languages have been extensively used as lexical–semantic knowledge sources in language technology applications, due to their free availability and their size. The ubiquitousness of PWN-type wordnets tends to overshadow the fact that they represent one out of many possible choices for structuring a lexical–semantic resource, and it could be enlightening to look at a differently structured resource both from the point of view of theoretical–methodological considerations and from the point of view of practical text processing requirements. The resource described here—SALDO—is such a lexical–semantic resource, intended primarily for use in language technology applications, and offering an alternative organization to PWN-style wordnets. We present our work on SALDO, compare it with PWN, and discuss some implications of the differences. We also describe an integrated infrastructure for computational lexical resources where SALDO forms the central component.     

基于神经网络的中文谓语动词识别研究

识别谓语动词是理解句子的关键。由于中文谓语动词结构复杂、使用灵活、形式多变,识别谓语动词在中文自然语言处理中是一项具有挑战的任务。本文从信息抽取角度,介绍了与中文谓语动词识别相关的概念,提出了一种针对中文谓语动词标注方法。在此基础上,研究了一种基于Attentional-BiLSTM-CRF神经网络的中文谓语动词识别方法。该方法通过双向递归神经网络获取句子内部的依赖关系,然后用注意力机制建模句子的焦点角色。最后通过条件随机场（Conditional random field, CRF)层返回一条最大化的标注路径。此外,为解决谓语动词输出唯一性的问题,提出了一种基于卷积神经网络的谓语动词唯一性识别模型。通过实验,该算法超出传统的序列标注模型CRF,在本文标注的中文谓语动词数据上到达76.75%的F值。     

藏语述说动词小句宾语及其标记3

本文讨论藏语述说动词管控的句子性小句宾语。藏语述说动词包括“说”类动词、认知动词、思考动词、询问动词及其他语义相关的动词。从小句自身结构看,可以是完整的句子,带主语、谓语以及句末动词体貌标记和语气词,也可能只是单一的谓语动词。小句宾语自身具有谓词性,通常通过添加名词化标记使之名词化。小句宾语的标记来自古代述说类动词的类典型zer 的语法化,而在现代藏语中作为小句标记语音和书写形式上都有多个变体。小句宾语内部也有复杂的关系和层次,类似于英语的直接引语与间接引语。小句缺省主语的情况下,动作发出者可通过表示体貌、情态的语法词以及上下文来确定。小句的句类包括陈述、疑问、祈使和感叹,可带不同的句类语气词。最后应该指出,有一部分述说动词小句宾语经常不带名词化标记,这种现象会给句法处理算法带来一定的麻烦,相关原因和解决办法还须进一步研究。     

Challenges for a multilingual wordnet

Wordnets have been created in many languages, revealing both their lexical commonalities and diversity. The next challenge is to make multilingual wordnets fully interoperable. The EuroWordNet experience revealed the shortcomings of an interlingua based on a natural language. Instead, we propose a model based on the division of the lexicon and a language-independent, formal ontology that serves as the hub interlinking the language-specific lexicons. The ontology avoids the idiosyncracies of the lexicon and furthermore allows formal reasoning about the concepts it contains. We address the division of labor between ontology and lexicon. Finally, we illustrate our model in the context of a domain-specific multilingual information system based on a central ontology and interconnected wordnets in seven languages.     

PQAC-WN: constructing a wordnet for Pre-Qin ancient Chinese

The Princeton WordNet^® (PWN) is a widely used lexical knowledge database for semantic information processing. There are now many wordnets under creation for languages worldwide. In this paper, we endeavor to construct a wordnet for Pre-Qin ancient Chinese (PQAC), called PQAC WordNet (PQAC-WN), to process the semantic information of PQAC. In previous work, most recently constructed wordnets have been established either manually by experts or automatically using resources from which translation pairs between English and the target language can be extracted. The former method, however, is time-consuming, and the latter method, owing to a lack of language resources, cannot be performed on PQAC. As a result, a method based on word definitions in a monolingual dictionary is proposed. Specifically, for each sense, kernel words are first extracted from its definition, and the senses of each kernel word are then determined by graph-based Word Sense Disambiguation. Finally, one optimal sense is chosen from the kernel word senses to guide the mapping between the word sense and PWN synset. In this research, we obtain 66 % PQAC senses that can be shared with English and another 14 % language-specific senses that were added to PQAC-WN as new synsets. Overall, the automatic mapping achieves a precision of over 85 %.     

ECO and Onto.PT: a flexible approach for creating a Portuguese wordnet automatically

A wordnet is an important tool for developing natural language processing applications for a language. However, most wordnets are handcrafted by experts, which limits their growth. In this article, we propose an automatic approach to create wordnets by exploiting textual resources, dubbed ECO. After extracting semantic relation instances, identified by discriminating textual patterns, ECO discovers synonymy clusters, used as synsets, and attaches the remaining relations to suitable synsets. Besides introducing each step of ECO, we report on how it was implemented to create Onto.PT, a public lexical ontology for Portuguese. Onto.PT is the result of the automatic exploitation of Portuguese dictionaries and thesauri, and it aims to minimise the main limitations of existing Portuguese lexical knowledge bases.     

The chicken-and-egg problem in wordnet design: synonymy, synsets and constitutive relations

Wordnets are built of synsets, not of words. A synset consists of words. Synonymy is a relation between words. Words go into a synset because they are synonyms. Later, a wordnet treats words as synonymous because they belong in the same synset $\ldots$ … Such circularity, a well-known problem, poses a practical difficulty in wordnet construction, notably when it comes to maintaining consistency. We propose to make a wordnet a net of words or, to be more precise, lexical units. We discuss our assumptions and present their implementation in a steadily growing Polish wordnet. A small set of constitutive relations allows us to construct synsets automatically out of groups of lexical units with the same connectivity. Our analysis includes a thorough comparative overview of systems of relations in several influential wordnets. The additional synset-forming mechanisms include stylistic registers and verb aspect.     

Effect of retroflex sounds on the recognition of Hindi voiced and unvoiced stops

As development of the speech recognition system entirely depends upon the spoken language used for its development, and the very fact that speech technology is highly language dependent and reverse engineering is not possible, there is an utmost need to develop such systems for Indian languages. In this paper we present the implementation of a time delay neural network system (TDNN) in a modular fashion by exploiting the hidden structure of previously phonetic subcategory network for recognition of Hindi consonants. For the present study we have selected all the Hindi phonemes for srecognition. A vocabulary of 207 Hindi words was designed for the task-specific environment and used as a database. For the recognition of phoneme, a three-layered network was constructed and the network was trained using the back propagation learning algorithm. Experiments were conducted to categorize the Hindi voiced, unvoiced stops, semi vowels, vowels, nasals and fricatives. A close observation of confusion matrix of Hindi stops revealed maximum confusion of retroflex stops with their non-retroflex counterparts.     

Combining corpus and machine-readable dictionary data for building bilingual lexicons

This paper describes and discusses some theoretical and practical problems arising from developing a system to combine the structured but incomplete information from machine readable dictionaries (MRDs) with the unstructured but more complete information available in corpora for the creation of a bilingual lexical data base, presenting a methodology to integrate information from both sources into a single lexical data structure. The BICORD system (BIlingual CORpus-enhanced Dictionaries) involves linking entries in Collins English-French and French-English bilingual dictionary with a large English-French and French-English bilingual corpus. We have concentrated on the class of action verbs of movement, building on earlier work on lexical correspondences specific to this verb class between languages (Klavans and Tzoukermann, 1989), (Klavans and Tzoukermann, 1990a), (Klavans and Tzoukermann, 1990b).¹ We first examine the way prototypical verbs of movement are translated in the Collins-Robert (Atkins, Duval, and Milne, 1978) bilingual dictionary, and then analyze the behavior of some of these verbs in a large bilingual corpus. We incorporate the results of linguistic research on the theory of verb types to motivate corpus analysis coupled with data from MRDs for the purpose of establishing lexical correspondences with the full range of associated translations, and with statistical data attached to the relevant nodes.     

Towards a cross-linguistically valid classification of spatial prepositions

This article proposes a classification for a subset of English spatial prepositions which is argued to have cross-linguistic validity by using it to classify a subset of Spanish spatial prepositions. The classification consists of a hierarchy of spatial relations where each node in the hierarchy satisfies a series of syntactic and semantic tests. These tests define properties which are then inherited uniformly throughout. Prepositions are assigned values from the lower nodes in the hierarchy either in the lexicon or through lexical rules. Similarities and differences between the spatial system of different languages can be described by appealing to the relations and lexical rules that the language allows. It is shown how the hierarchy is used for building a lexicon for the machine translation of spatial prepositions in a transfer-based system.     

The variability of multi-word verbal expressions in Estonian

This article focuses on the variability of one of the subtypes of multi-word expressions, namely those consisting of a verb and a particle or a verb and its complement(s). We build on evidence from Estonian, an agglutinative language with free word order, analysing the behaviour of verbal multi-word expressions (opaque and transparent idioms, support verb constructions and particle verbs). Using this data we analyse such phenomena as the order of the components of a multi-word expression, lexical substitution and morphosyntactic flexibility.     

A Default Logic Based Framework for Context-Dependent Reasoning with Lexical Knowledge

Lexical knowledge is increasingly important in information systems—for example in indexing documents using keywords, or disambiguating words in a query to an information retrieval system, or a natural language interface. However, it is a difficult kind of knowledge to represent and reason with. Existing approaches to formalizing lexical knowledge have used languages with limited expressibility, such as those based on inheritance hierarchies, and in particular, they have not adequately addressed the context-dependent nature of lexical knowledge. Here we present a framework, based on default logic, called the dex framework, for capturing context-dependent reasoning with lexical knowledge. Default logic is a first-order logic offering a more expressive formalisation than inheritance hierarchies: (1) First-order formulae capturing lexical knowledge about words can be inferred; (2) Preferences over formulae can be based on specificity, reasoning about exceptions, or explicit priorities; (3) Information about contexts can be reasoned with as first-order formulae formulae; and (4) Information about contexts can be derived as default inferences. In the dex framework, a word for which lexical knowledge is sought is called a query word. The context for a query word is derived from further words, such as words in the same sentence as the query word. These further words are used with a form of decision tree called a context classification tree to identify which contexts hold for the query word. We show how we can use these contexts in default logic to identify lexical knowledge about the query word such as synonyms, antonyms, specializations, meronyms, and more sophisticated first-order semantic knowledge. We also show how we can use a standard machine learning algorithm to generate context classification trees.     

Computational verb systems: Verb logic

Computational verb systems are new platforms for artificial intelligence. They embed the dynamical knowledge expressed by dynamical experiences of human brains into machines by using pattern thinking. In this paper, the relationship defined by verbs in human natural languages is modeled by computational verb logic (verb logic for short). To unify different verbs with different contexts into comparable standard forms, the concepts of BE transformation and canonical BE transformation are given. The atomic and molecular verb sentences under canonical BE transformations are also defined for verb logic. The basic verb logic operations are given. Some examples are given to demonstrate the concepts of BE transformation and verb logic. ©1999 John Wiley & Sons, Inc.     

Methodology and construction of the Basque WordNet

Semantic interpretation of language requires extensive and rich lexical knowledge bases (LKB). The Basque WordNet is a LKB based on WordNet and its multilingual counterparts EuroWordNet and the Multilingual Central Repository. This paper reviews the theoretical and practical aspects of the Basque WordNet lexical knowledge base, as well as the steps and methodology followed in its construction. Our methodology is based on the joint development of wordnets and annotated corpora. The Basque WordNet contains 32,456 synsets and 26,565 lemmas, and is complemented by a hand-tagged corpus comprising 59,968 annotations.     

Two collapsing hierarchies of subregularly tree controlled languages

Tree controlled grammars are context-free grammars where the associated language only contains those terminal words which have a derivation where the word of any level of the corresponding derivation tree belongs to a given regular language. In this paper, we consider first as control sets such regular languages which can be represented by finite unions of monoids. We show that the corresponding hierarchy of tree controlled languages collapses already at the second level. Second, we restrict the number of states allowed in the accepting automaton of the regular control language. We prove that the associated hierarchy has at most five levels.     

Interlingua-based English–Hindi Machine Translation and Language Divergence

Interlingua and transfer-based approaches tomachine translation have long been in use in competing and complementary ways. The former proves economical in situations where translation among multiple languages is involved, and can be used as a knowledge-representation scheme. But given a particular interlingua, its adoption depends on its ability (a) to capture the knowledge in texts precisely and accurately and (b) to handle cross-language divergences. This paper studies the language divergence between English and Hindi and its implication to machine translation between these languages using the Universal Networking Language (UNL). UNL has been introduced by the United Nations University, Tokyo, to facilitate the transfer and exchange of information over the internet. The representation works at the level of single sentences and defines a semantic net-like structure in which nodes are word concepts and arcs are semantic relations between these concepts. The language divergences between Hindi, an Indo-European language, and English can be considered as representing the divergences between the SOV and SVO classes of languages. The work presented here is the only one to our knowledge that describes language divergence phenomena in the framework of computational linguistics through a South Asian language.     

Multilingual generation: The role of telicity in lexical choice and syntactic realization

Multilingual generation in machine translation (MT) requires a knowledge organization that facilitates the task of lexical choice, i.e. selection of lexical units to be used in the generation of a target-language sentence. This paper investigates the extent to which lexicalization patterns involving the lexical aspect feature [+telic] may be used for translating events and states among languages. Telicity has been correlated syntactically with both transitivity and unaccusativity, and semantically with Talmy's path of a motion event, the representation of which characterizes languages parametrically.Taking as our starting point the syntactic/semantic classification in Levin's English Verb Classes and Alternations, we examine the relation between telicity and the syntactic contexts, or alternations, outlined in this work, identifying systematic relations between the lexical aspect features and the semantic components that potentiate these alternations. Representing lexical aspect — particularly telicity — is therefore crucial for the tasks of lexical choice and syntactic realization. Having enriched the data in Levin (by correlating the syntactic alternations (Part I) and semantic verb classes (Part II) and marking them for telicity) we assign to verbs lexical semantic templates (LSTs). We then demonstrate that it is possible from these templates to build a large-scale repository for lexical conceptual structures which encode meaning components that correspond to different values of the telicity feature. The LST framework preserves both semantic content and semantic structure (following Grimshaw during the processes of lexical choice and syntactic realization. Application of this model identifies precisely where the Knowledge Representation component may profitably augment our rules of composition, to identify cases where the interlingua underlying the source language sentence must be either reduced or modified in order to produce an appropriate target language sentence.