Answer selection is an important task in question answering (QA) from the Web. To address the intrinsic difficulty in encoding sentences with semantic meanings, we introduce a general framework, i.e., Lexical Semantic Feature based Skip Convolution Neural Network (LSF-SCNN), with several optimization strategies. The intuitive idea is that the granular representations with more semantic features...

the pragmalinguistic and sociopragmatic aspects of language use vary across different situations, languages, and cultures. the separation of these two facets of language use can help to map out the socio-cultural norms and conventions as well as the linguistic forms and strategies that underlie the pragmatic performance of different language speakers in a variety of target language use situatio...

Patients with low-grade glioma (LGG) have been studied as a model of functional brain reorganization due to their slow-growing nature. However, there is no information regarding which brain areas are involved during verbal memory encoding after extensive left frontal LGG resection. In addition, it remains unknown whether these patients can improve their memory performance after instructions to ...

shared ontologies and reasoning strategies (generated by the framework and semantically represented), which can be accessed and re-used by other applications. This paper proposes a semantic framework built on multidimensional ontological planes for the design of adaptive systems. The core of the framework is composed by three matrices whose different planes contain the ontological representatio...

Biological studies of obsessive-compulsive disorder (OCD) provide consistent evidence of dysfunction in orbitofrontal cortex (OFC). We have used the California Verbal Learning Test (CVLT) in behavioral studies to examine episodic memory in OCD. In two separate investigations, we found that OCD patients failed to spontaneously apply semantic organizational strategies during encoding and this led...

CHAUCER is a Q/A system developed for (a) combining several strategies for modeling the target of a series of questions and (b) optimizing the extraction of answers. Targets were modeled by (1) topic signatures; (2) semantic types; (3) lexico-semantic patterns; (4) frame dependencies; and (5) predictive questions. Several strategies for answer extraction were also tried. The best-performing str...

Reducing redundancy in search has been a major concern for automated deduction. Subgoal-reduction strategies prevent redundant search by using lemmaizing and caching, whereas contraction-based strategies prevent redundant search by using contraction rules, such as subsumption. In this work we show that lemmaizing and contraction can coexist in the framework of semantic resolution. On the lemmai...

Measuring the semantic meaning between words is an important issue because it is the basis for many applications, such as word sense disambiguation, document summarization, and so forth. Although it has been explored for several decades, most of the studies focus on improving the effectiveness of the problem, i.e., precision and recall. In this paper, we propose to address the efficiency issue,...

In this paper, we study user modeling on Twitter. We investigate different strategies for mining user interest profiles from microblogging activities ranging from strategies that analyze the semantic meaning of Twitter messages to strategies that adapt to temporal patterns that can be observed in the microblogging behavior. We evaluate the quality of the user modeling methods in the context of ...

In Natural Language Generation, the task of attribute selection (AS) consists of determining the appropriate attribute-value pairs (or semantic properties) that represent the contents of a referring expression. Existing work on AS includes a wide range of algorithmic solutions to the problem, but the recent availability of corpora annotated with referring expressions data suggests that corpus-b...