| 期刊全称 | Automatic Syntactic Analysis Based on Selectional Preferences | | 影响因子2023 | Alexander Gelbukh,Hiram Calvo | | 视频video | | | 发行地址 | Describes recent methods for automatically analyzing a sentence, based on the syntactic and semantic characteristics of the elements that form it.Presents a disambiguation algorithm based on linguisti | | 学科分类 | Studies in Computational Intelligence | | 图书封面 |  | | 影响因子 | .This book describes effective methods for automatically analyzing a sentence, based on the syntactic and semantic characteristics of the elements that form it. To tackle ambiguities, the authors use selectional preferences (SP), which measure how well two words fit together semantically in a sentence. Today, many disciplines require automatic text analysis based on the syntactic and semantic characteristics of language and as such several techniques for parsing sentences have been proposed. Which is better? In this book the authors begin with simple heuristics before moving on to more complex methods that identify nouns and verbs and then aggregate modifiers, and lastly discuss methods that can handle complex subordinate and relative clauses. During this process, several ambiguities arise. SP are commonly determined on the basis of the association between a pair of words. However, in many cases, SP depend on more words. For example, something (such as grass) may be edible, depending on who is eating it (a cow?). Moreover, things such as popcorn are usually eaten at the movies, and not in a restaurant. The authors deal with these phenomena from different points of view.. | | Pindex | Book 2018 |
| 1 |
Front Matter |
|
|
Abstract
|
| 2 |
,Introduction, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
The most valuable treasure of humankind is knowledge. Computers have a better capability than humans to handle great amounts of information: search for information, apply simple inference, and look for answers to questions…. However, our treasure, which exists in the form of natural language texts—news boards, newspapers, and books in digital libraries and the Internet—is not understandable to computers; they deal with it as a chain of letters and not as knowledge.
|
| 3 |
,First Approach: Sentence Analysis Using Rewriting Rules, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
Some of the earliest useful user interaction systems involving sentence analysis used rewriting rules. A famous example of one such system is SHRDLU, which was created in the 1960s by Terry Winograd at the Massachusetts Institute of Technology and was able to solve many of the problems that arise when conversing with a computer.
|
| 4 |
,Second Approach: Constituent Grammars, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
In this chapter, we tackle sentence analysis using the constituent approach. This approach has two problems. The first is the difficulty of extracting information about characters and actions from factual reports such as news articles, web pages, and circumscribed stories. To construct the structure of a sentence, there should be interaction with previously acquired knowledge. In turn, such knowledge should be expressed in a structured way so that simple inferences may be used when necessary. We will deal with this problem in detail in Sect. ..
|
| 5 |
,Third Approach: Dependency Trees, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
After exploring several approaches and representational structures in the previous two chapters, we found that the formalism that best suits our needs is the dependency tree representation. Thus, in this chapter, we present a parser that is based on a dependency tree. This parser’s algorithm uses heuristic rules to infer dependency relationships between words, and it uses word co-occurrence statistics (which are learned in an unsupervised manner) to resolve ambiguities such as PP attachments. If a complete parse cannot be produced, a partial structure is built with some (if not all) dependency relations identified.
|
| 6 |
,Evaluation of the Dependency Parser, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
Many corpora are annotated using constituent formalism. However, our goal is to evaluate parsers within the dependency formalism, which means we need a gold standard in the dependency formalism.
|
| 7 |
,Applications, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
In this chapter, we propose a method for extracting selectional preferences that are linked to an ontology: namely, WordNet. This information is used, among other possible applications, to perform word sense disambiguation. An evaluation of this method, using Senseval-2, is also given. The results of this experiment are comparable to those obtained by Resnik when he used selectional preferences for the English language; however, our proposed method is more advantageous in that it does not require any previous morphological, syntactic, or semantic annotation of the text.
|
| 8 |
,Prepositional Phrase Attachment Disambiguation, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
The problem of disambiguating PP attachments consists of determining if a PP is part of a noun phrase (as in .) or a verb phrase (as in .).
|
| 9 |
,The Unsupervised Approach: Grammar Induction, |
Omar J. Gambino,Hiram Calvo |
|
Abstract
There are mainly two approaches for creating syntactic dependency analyzers: supervised and unsupervised. The main goal of the first approach is to attain the best possible performance for a single language. For this purpose, a large collection of resources is gathered (using manually annotated corpora with part-of-speech annotations and syntactic and structure tags), which requires a significant amount of work and time. The state of the art in this approach attains syntactic annotation in about 85% of all full sentences (Rooth in Proceedings of the symposium on representation and acquisition of lexical knowledge. AAAI, 1995 [172]); in English, it attains over 90%. On the other hand, the unsupervised approach tries to discover the structure of a text using only raw text, which allows the creation of a dependency analyzer for virtually any language. Here, we explore this second approach. We present the model of an unsupervised dependency analyzer, named DILUCT-GI (GI short for grammar inference).
|
| 10 |
,Multiple Argument Handling, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
A sentence can be regarded as a verb with multiple arguments. The plausibility of each argument depends not only on the verb but also on other arguments. Measuring the plausibility of verb arguments is necessary in several tasks, such as semantic role labeling, where grouping verb arguments and measuring the plausibility increases performance [70, 135]. Metaphor recognition also requires knowledge of verb argument plausibility in order to recognize uncommon usages, which would suggest either the presence of a metaphor or a coherence mistake (e.g., .). Malapropism detection can use the measure of the plausibility of an argument to determine word misuse [185]—such as in . instead of ., . instead of ., . instead of a ., and . instead of ..
|
| 11 |
,The Need for Full Co-Occurrence, |
Alexander Gelbukh,Hiram Calvo |
|
Abstract
We have previously shown that simultaneously considering three arguments yields better precision than does considering only two, though with a certain loss of recall. Kawahara and Kurohashi [107] differentiate the main verb using the closest argument in order to disambiguate verbs for learning preferences.
|
| 12 |
Back Matter |
|
|
Abstract
|
|
|
发表于 2025-3-21 16:47:37
