MPSC: A Multiple-Perspective Semantics-Crossover Model for Matching Sentences

Bilateral Multi-Perspective Matching for Natural Language Sentences

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (wordby-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model. Given two sentences P and Q, our model first encodes them with a BiLSTM encoder. Next,...

On Semantics for Characterizing Sentences∗

The paper presents semantics for a subset of generics, so-called “characterizing sentences”. It is argued that claims about the relationship between the truth of characterizing sentences and claims about the distribution of properties among individuals can be viewed independently of considerations about logical form. Some extant approaches are presented and criticized, and a positive analysis o...

Using Generalized Language Model for Question Matching

Question and answering service is one of the popular services in the World Wide Web. The main goal of these services is to finding the best answer for user's input question as quick as possible. In order to achieve this aim, most of these use new techniques foe question matching. . We have a lot of question and answering services in Persian web, so it seems that developing a question matching m...

Denotational Semantics for interrogative Sentences in Japanese

We present a new approach to a sentence of interrogative form in Japanese within the framework of Montague Grammar. The possibility of various uses of an interrogative sentence; uses as a question, an exclamation, a rhetorical question, a demand and a recommendation is explained based on the same denotation for the sentence. The denotation which is neutral for all possible uses is defined in te...

Permission Sentences in Dynamic Semantics