2 Constituency and Recursion in Language 3 4
نویسندگان
چکیده
6 Upon reflection, most people would agree that the words in a sen7 tence are not merely arranged like beads on a string. Rather, the 8 words group together to form coherent building blocks within a 9 sentence. Consider the sentence, The girl liked a boy. Intuitively, 10 the chunks the girl and liked a boy constitute the basic components 11 of this sentence (compared to a simple listing of the individual 12 words or alternative groupings, such as the girl liked and a boy). 13 Linguistically, these chunks comprise the two major constituents 14 of a sentence: a subject noun phrase (NP), the girl, and a verb 15 phrase (VP), liked a boy. Such phrasal constituents may contain 16 two types of syntactic elements: other phrasal constituents (e.g., 17 the NP a boy in the above VP) or lexical constituents (e.g., the 18 determiner the and the noun girl in the NP the girl). Both types of 19 constituent are typically defined distributionally using the so-called 20 replacement test: If a novel word or phrase has the same distribu21 tion as a word or phrase of a known constituent type—that is if the 22 former can be replaced by the latter—then they are the same type 23 of constituent. Thus, the lexical constituents the and a both belong 24 to the lexical category of determiners because they occur in similar 25 contexts and therefore can replace each other (e.g., A girl liked the 26 boy). Likewise, the girl and a boy belong to the same phrasal cate27 gory, NP, because they can be swapped around, as in A boy liked 28 the girl (note, however, that there may be semantic constraints on 29 constituent replacements. For example, replacing the animate sub30 ject NP the girl with the inanimate NP the chair yields the seman31 tically anomalous sentence, The chair liked a boy). 32 In linguistics, grammar rules and/or principles determine how 33 constituents can be put together to form sentences. For instance, 34 we can use the following phrase structure rules to describe the 35 relationship between the constituents in the example sentences 36 above:
منابع مشابه
تبدیل خودکار درختبانک وابستگی فارسی به درختبانک سازهای
There are two major types of treebanks: dependency-based and constituency-based. Both of them have applications in natural language processing and computational linguistics. Several dependency treebanks have been developed for Persian. However, there is no available big size constituency treebank for this language. In this paper, we aim to propose an algorithm for automatic conversion of a depe...
متن کاملConstituency and Recursion in Language
artificial languages, Christiansen and Chater (1999) show that the SRN’s general pattern of performance is relatively invariant across network size and training corpus, and conclude that the human-like pattern of performance derive from intrinsic constraints inherent in the SRN architecture. Connectionist models of recursive syntax typically use “toy” fragments of grammar and small vocabularies...
متن کاملConstituency-Tree Recursive Neural Network for Quiz Bowl Answering
Quiz bowl answering represents a challenging task in natural language processing where few indication entities of answers are given in the questions. Traditional approaches such as manual feature engineering and bag of words representations can fail to reason the correct answers due to such lack of direct indications. Recently recursive neural network (RNN) model shows promising performance in ...
متن کاملRecursion, Language, and Starlings
It has been claimed that recursion is one of the properties that distinguishes human language from any other form of animal communication. Contrary to this claim, a recent study purports to demonstrate center-embedded recursion in starlings. I show that the performance of the birds in this study can be explained by a counting strategy, without any appreciation of center-embedding. To demonstrat...
متن کاملA Multi-Teraflop Constituency Parser using GPUs
Constituency parsing with rich grammars remains a computational challenge. Graphics Processing Units (GPUs) have previously been used to accelerate CKY chart evaluation, but gains over CPU parsers were modest. In this paper, we describe a collection of new techniques that enable chart evaluation at close to the GPU’s practical maximum speed (a Teraflop), or around a half-trillion rule evaluatio...
متن کاملAppropriators not Position Takers: The Distorting Effects of Electoral Incentives on Congressional Representation: Supplemental Information
1 Alignment of Members of Congress and Constituency 3 1.1 Literature on Members of Congress and Constituency . . . . . . . . . . . . . . . . . 3 1.2 Demonstrating the Increasing Alignment and Sorting in Districts . . . . . . . . . . . 4 1.3 Connection to Constituent Sanction and Reelection Rates . . . . . . . . . . . . . . . 8 2 Number of Press Releases and Alignment 11 3 A General Indication o...
متن کامل