Rules for syntax, vectors for semantics

2007

Both criteria are taken as primitives: the developmental evidence of communicative intentions is given in . That communicating implies understanding hence the need of semantic processing follows.

2020

The article explains the use of generative grammars in linguistic modeling. Describes syntax modeling of sentence that used to automate the analysis and synthesis of natural-language texts. The article proposes content analysis methods for an online-newspaper.

2008

Semantic inference is an important component in many natural language understanding applications. Classical approaches to semantic inference rely on logical representations for meaning, which may be viewed as being “external” to the natural language itself. However, practical applications usually adopt shallower lexical or lexical-syntactic representations, which correspond closely to language structure. In many cases, such approaches lack a principled meaning representation and inference framework. We describe a generic semantic inference framework that operates directly on language-based structures, particularly syntactic trees. New trees are inferred by applying entailment rules, which provide a unified representation for varying types of inferences. Rules were generated by manual and automatic methods, covering generic linguistic structures as well as specific lexical-based inferences. Initial empirical evaluation in a Relation Extraction setting supports the validity and potential of our approach. Additionally, such inference is shown to improve the critical step of unsupervised learning of entailment rules, which in turn enhances the scope of the inference system. This paper corresponds to the invited talk of the first author at CICLING 2008.

A controversy has existed over the interaction of syntax and semantics in natural language understanding systems. According to theories of integrated parsing, syntactic and semantic processing should take place simultaneously, with the parsing process driven by a single rule base which contains both syntactic and semantic knowledge. This is in sharp contrast to traditional linguistic approaches to language analysis, in which syntact,ic and semantic processing are performed separately from one another, driven by completely separate sets of syntactic and semantic rules. This paper presents an approach to natural language understanding which is a compromise between these two views. It is an integrated approach, in the sense that syntactic and semantic processing take place at the same time. However, unlike previous integrated systems, the approach described here uses largely separate bodies of syntactic and semantic knowledge, which are combined only at the time of processing.

2010

Abstract The pervasive ambiguity of language allows sentences that differ in just one lexical item to have rather different inference patterns. This would be no problem if the different lexical items fell into clearly definable and easy to represent classes. But this is not the case. To draw the correct inferences we need to look how the referents of the lexical items in the sentence (or broader context) interact in the described situation.

The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.

2000

Proceedings of the 14th conference on Computational linguistics -, 1992

\Ve propose a two-layered model for computing semantic and (:onceI)tual interpretations from del)endency struetm'es. Abstract interl)retatio,t s(:hemata generate semantic interpretations of 'minimal' dependency sul)gral)hs , while production rules whose sl)eeitieation is rooted ill ontologi(:al categories derive a canonical con(:eptual il~terl)retation from selna.ntic int;ert)retal;ion sl;ruel;ures. Configm'ational descriptions of del)endeney gral)hs increase the linguistic generality of interl)rel,ation s(:hemata, while interfimillg sehemata and t)ro(htcl;ions t() lexi(:al and COll(:el)l:tl~ll (;lass hierarchies re(ht(:es the amount and complexity of semantic sl)e(:iti(:atJons.