Collectively, the papers in this session are mainly concerned with parsing, semantic interpretation, and inference. Interest in these processes can be motivated if we recognize that the overall goal of the field of NLP is the manipulation of natural language in ways that depend on meaning. Parsing, the recovery of the linguistic or grammatical structure of a natural-language utterance, is of co...

We examined the time course of cross-language activation during word recognition in the context of semantic priming with interlingual homographs. Spanish-English bilinguals were presented pairs of English words visually one word at a time and judged whether the two words were related in meaning while recording event-related potentials. Interlingual homographs (e.g., "pie": "Pie" in Spanish is a...

In this paper, a semantic categorization method in generic home photos is proposed. In recent years, the semantic categorization of image has been a challenge due to the proliferation of digital home photos. Our approach is to detect semantically meaningful concepts contained in a photo. The proposed method incorporates an intermediate level of concepts, called local concept, so that it catches...

This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can be inferred from the meaning of another and from background knowledge. Our system generates semantic graphs as a representation of the meaning of a text. This paper presents new results for aligning...

Grammar encodes meaning (Wierzbicka 1988). “Grammar is simply the structuring and symbolization of semantic content” (Langacker 1987). Grammatical variation is largely the result of a compromise between the differing requirements for the encoding of both semantic and discourse pragmatic aspects of meaning (Givón 1984). “One should prefer a semantic theory that explains otherwise arbitrary gener...

this study is carried out to shed light on one of the lexical problems affecting the performance of translators while attempting to translate from an original text into a target language (in present study, from french to persian). polysemy is one of the well identified semantic problems. the words possess different meanings and significations according to the situation and the context in which ...

It is well known that the meaning of a verb-based construction depends not only on the lexical meaning of the verb but also on its specific syntagmatic environment. Lexical meaning interacts with constructional meaning in intricate ways and this interaction is crucial for theories of argument linking and the syntax-semantics interface. These insights have led proponents of Construction Grammar ...

Local semantic labels are relevant to the verb meaning in question, while global semantic labels are relevant across different verbs and verb meanings. We show that global semantic labels from different frameworks are not necessarily compatible and argue that, therefore, corpora should be annotated with local semantic labels and that global semantic labels should then be automatically annotated...

Although the semantic analysis and the grammatical distribution are treated as separate issues in linguistic theories, there is a close interconnection between the two in that the differences in the lexical meanings are often realized at the levels both of the grammatical function and of the lexical collocation. This is the basic assumption utilized when we design and develop Knowledge Base of ...

In this chapter, several knowledge representation and processing techniques based on a symbolic and semantic approach are briefly described. The majority of present-day techniques, like the relational database model or OWL (Web Ontology Language), is based on the symbolic approach and supports the representation and processing of semantically related knowledge. Although these two techniques hav...