Building shallow semantic representations from text corpora is the first step to perform more complex tasks such as text entailment, enrichment of knowledge bases, or question answering. Open Information Extraction (OIE) is a recent unsupervised strategy to extract billions of basic assertions from massive corpora, which can be considered as being a shallow semantic representation of those corp...

We present a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame. Given an input sentence and a target word and frame, the system labels constituents with either abstract semantic roles such as AGENT or PATIENT, or more domain-specific semantic roles such as SPEAKER, MESSAGE, and TOPIC. The system is based on statist...

In this paper we deal with the verb valency lexicon of Czech verbs named VerbaLex, which contains complex valency verb frames (CVFs) including both surface and deep valencies. The most notable features of CVFs include two-level semantic labels with linkage to the Princeton and EuroWordNet Top Ontology hierarchy and the corresponding surface verb frame patterns capturing the morphological cases ...

Parsing Chinese serial verb sentences is a key issue in NLP. Many controversies arise from serial verb sentences. This paper puts forward a novel model “the Feature Structure theory” to resolve the semantic labeling of Chinese serial verb sentences. We analyze the difficulties in annotating these sentences, and compare Feature Structure with traditional dependency structure. Feature Structure r...

Issues regarding the nature of the semantic relationships holding between a verb (or other predicating element) and its arguments have been the focus of much research and controversy since the mid-1960’s. Starting from Gruber (1965)’s notion of thematic relations and Fillmore (1968)’s concept of case roles, most contemporary theories of grammar assume some system of semantic predicate-argument ...

As in lexical semantics in general, distributional methods have also proven a successful technique for the automatic modeling of verb meaning. However, much more than with other lexical categories, the research into verb semantics has been based on the idea that a verb’s meaning is strongly linked to its syntactic behavior and more specifically, to its selectional preferences. This has led dist...

This paper explores how verb meanings that differ in semantic complexity are processed and represented. In particular, we compare eventive verbs, which denote causally structured events, with stative verbs, which denote facts without causal structure. We predicted that the conceptually more complex eventive verbs should take longer to process than stative verbs. Two experiments, a lexical decis...

The work described in this paper was originally motivated by the construction of a lexical semantic knowledge base for analysis of Ideational Metafunction of language in Systemic Functional Grammar and the Generalized Upper Model ontology. The work involves mapping FrameNet Frames with Ideational Meanings and instantiating WordNet Verb as the meaning evoking linguistic elements. As the work evo...

A formal architecture for Construction Grammar (CG) is sketched. Modeling domain objects (constructs) are constituent structures with feature structures at the nodes, aka Feature Structure Trees (FTs). Constructions are partial descriptions of FTs, expressed as sets of constituent structure equations and path equations. Uni-cation of constructions is deened. A construct c is licensed by a gramm...