The main verb is also called the lexical verb or the principal verb. This term refers to the important verb in the sentence, the one that typically shows the action or state of being of the subject



Yüklə 45,43 Kb.
səhifə3/10
tarix22.05.2023
ölçüsü45,43 Kb.
#111917
1   2   3   4   5   6   7   8   9   10
aziza

The methods of course paper were used in the work: descriptive, analytical, conceptual, and component analysis.
Practical value of the work. All the analysis investigated and recommended lesson plans can be utilized during teaching.
The structure of course work consists of introduction, three main chapters, conclusion, resume and the list of used literature.
CHAPTER I.CATEGORIZATION OF VERBS
1.1 Semantic categories of verbs
Lexical-semantic classes which aim to capture the close relationship between the syntax and semantics of verbs have attracted considerable interest in both linguistics and computational linguistics Such classes can capture generalizations over a range of linguistic properties, and can therefore be used as a valuable means of reducing redundancy in the lexicon and for filling gaps in lexical knowledge.2
Verb classes have proved useful in various multilingual natural language processing tasks and applications, such as computational lexicography language generation, machine translation, word sense disambiguation, document classification , and sub-categorization acquisition. Fundamentally, such classes define the mapping from surface realization of arguments to predicate-argument structure and are therefore a critical component of any NLP system which needs to recover predicate-argument structure. In many operational contexts, lexical information must be acquired from small application- and/or domain-specific corpora. The predictive power of classes can help compensate for lack of suf- ficient data fully exemplifying the behaviour of relevant words, through use of back-off smoothing or similar techniques.
Although several classifications are now available for English verbs they are all restricted to certain class types and many of them have few exemplars with each class. For example, the largest and the most widely deployed classification in English, Levin’s taxonomy, mainly deals with verbs taking noun and prepositional phrase complements, and does not provide large numbers of exemplars of the classes. The fact that no comprehensive classification is available limits the usefulness of the classes for practical NLP.
Some experiments have been reported recently which indicate that it should be possible, in the future, to automatically supplement extant classifications with novel verb classes and member verbs from corpus data. While the automatic approach will avoid the expensive overhead of manual classification, the very development of the technology capable of large-scale automatic classification will require access to a target classification and gold standard exemplification of it more extensive than that available currently.3
In this paper, we address these problems by introducing a substantial extension to Levin’s classification which incorporates 57 novel classes for verbs not covered by Levin. These classes, many of them drawn initially from linguistic resources, were created semi-automatically by looking for diathesis alternations shared by candidate verbs. 106 new alternations not covered by Levin were identified for this work. We demonstrate the usefulness of our novel classes by using them to improve the performance of our extant subcategorization acquisition system. We show that the resulting extended classification has good coverage over the English verb lexicon. Discussion is provided on how the classification could be further refined and extended in the future, and integrated as part of Levin’s extant taxonomy.
Levin’s classification provides a summary of the variety of theoretical research done on lexical semantic verb classification over the past decades. In this classification, verbs which display the same or similar set of diathesis alternations in the realization of their argument structure are assumed to share certain meaning components and are organized into a semantically coherent class. Although alternations are chosen as the primary means for identifying verb classes, additional properties related to sub categorization, morphology and extended meanings of verbs are taken into account as well. For instance, the Levin class of “Break Verbs”, which refers to actions that bring about a change in the material integrity of some entity, is characterized by its participation or non-participation in the following alternations and other constructions:4
1. Causative/inchoative alternation:
Tony broke the window
The window broke
2. Middle alternation:
Tony broke the window
The window broke easily
3. Instrument subject alternation:
Tony broke the window with the hammer
The hammer broke the window
4. With/against alternation:
Tony broke the cup against the wall
Tony broke the wall with the cup
5. Conative alternation:
Tony broke the window
Tony broke at the window
6. Body-Part possessor ascension alternation:
Tony broke herself on the arm
Tony broke her arm
7. Unintentional interpretation available (some verbs):
Reflexive object: Tony broke himself
Body-part object: Tony broke his finger
8. Resultative phrase:
Tony broke the piggy bank open, Tony broke the glass to pieces
Levin’s taxonomy provides a classification of 3,024 verbs (4,186 senses) into 48 broad and 192 fine-grained classes according to their participation in 79 alternations involving NP and PP complements.5
Some extensions have recently been proposed to this resource. Dang et al. have supplemented the taxonomy with inter sective classes: special classes for verbs which share membership of more than one Levin class because of regular polysemy. Bonnie Dorr. (University of Maryland) has provided a reformulated and extended version of Levin’s classification in her LCS database . This resource groups 4,432 verbs ,1,000 senses into 466 Levin-based and 26 novel classes. The latter are Levin classes refined according to verbal telicity patterns, while the former are additional classes for non-Levin verbs which do not fall into any of the Levin classes due to their distinctive syntactic behavior.
As a result of this work, the taxonomy has gained considerably in depth, but not to the same extent in breadth.
Verbs taking ADJP, ADVP, ADL, particle, predicative, control and sentential complements are still largely excluded, except where they show interesting behaviour with respect to NP and PP complementation. As many of these verbs are highly frequent in language, NLP applications utilizing lexical-semantic classes would benefit greatly from a linguistic resource which provides adequate classification of their senses. When extending Levin’s classification with new classes, we particularly focussed on these verbs.
3 Creating Novel Classes Levin’s original taxonomy was created by
1. selecting a set of diathesis alternations from linguistic resources
2. classifying a large number of verbs according to their participation in these alternations,
3. grouping the verbs into semantic classes based on their participation in sets of alternations.
We adopted a different, faster approach. This involved
1. composing a set of diathesis alternations for verbs not covered comprehensively by Levin,
2. selecting a set of candidate lexical-semantic classes for these verbs from linguistic resources,
3. examining whether sets of verbs in each candidate class could be related to each other via alternations and thus warrant creation of a new class. In what follows, we will describe these steps in detail.6
The evaluation reported in the previoussection showsthat the novel classes can used to support a NLP task and that the extended classification has good coverage over the English verb lexicon and thus constitutes a resource suitable for large-scale NLP use.
Although the classes resulting from our work can be readily employed for NLP purposes, we plan, in the future, to further integrate them into Levin’s taxonomy to yield a maximally useful resource for the research community. While some classes can simply be added to her taxonomy as new classes or subclasses of extant classes others will require modifying extant Levin classes. The latter classes are mostly those whose members classify more naturally in terms of their sentential rather than NP and PP complementation.
This work will require resolving some conflicts between our classification and Levin’s. Because lexical semantic classes are based on partial semantic descriptions manifested in alternations, it is clear that different, equally viable classification schemes can be constructed using the same data and methodology. One can grasp this easily by looking at inter sective Levin classes, created by grouping together subsets of existing classes with overlapping members. Given that there is strong potential for cross-classification, we will aim to resolve any conflicts by preferring those classes which show the best balance between the accuracy in capturing syntactic-semantic features and the ability to generalize to as many lexical items as possible.7
An issue which we did not address in the present work as we worked on candidate classes, is the granularity of the classification. It is clear that the ‘suitable’ level of granularity varies from one NLP task to another. For example, tasks which require maximal accuracy from the classification are likely to benefit the most from finegrained classes (e.g. refined versions of Levin’s classes, while tasks which rely more heavily on the capability of a classification to capture adequate generalizations over a set of lexical items benefit the most from broad classes. Therefore, to provide a general purpose classification suitable for various NLP use, we intend to refine and organize our novel classes into taxonomies which incorporate different degrees of granularity.
Finally, we plan to supplement the extended classification with additional novel information. In the absence of linguistic resources exemplifying further candidate classes we will search for additional novel classes, intersective classes and member verbs using automatic methods, such as clustering. For example, clustering sense disambiguated subcategorization data (acquired e.g. from the SemCor corpus)should yield suitable (sense specific) data to work with. We will also include in the classification statistical information concerning the relative likelihood of different classes, SCFs and alternations for verbs in corpus data, using e.g. the automatic methods proposed by McCarthy (2001) and Korhonen (2002). Such information can be highly useful for statistical NLP systems utilizing lexical-semantic classes.



Yüklə 45,43 Kb.

Dostları ilə paylaş:
1   2   3   4   5   6   7   8   9   10




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©genderi.org 2024
rəhbərliyinə müraciət

    Ana səhifə