the current paper is an outlook toward lexical aspect and its types exist as a semantic parameter in verb and indicate trend of doing task of verb in terms of continuance, iteration, duration etc. although discourse aspect is considered as independent factor in verb morphology, but the resultant syntactic reflection does not solely corresponds to grammatical aspect; instead, it includes lexical...

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...

This paper describes our system for participating in the system validation subtask of NTCIR-11 RITE-VAL. We trained a SVM model with LibSVM using features extracted from labeled sentence pairs. Besides features based on lexical, syntactic and semantic analysis, we introduce a novel approach of extracting “concepts” from a sentence and generating features based on it. Unlabeled testing sentence ...

Modal verbs have different interpretations depending on their context. Previous approaches to modal sense classification achieve relatively high performance using shallow lexical and syntactic features. In this work we uncover the difficulty of particular modal sense distinctions by eliminating both distributional bias and sparsity of existing small-scale annotated corpora used in prior work. W...

This paper describes our work in NTCIR-11 on RITE-VAL System Validation task in Simplified Chinese including Binary-class (BC) subtask and Multi-class (MC) subtask. We construct the classification model based on support vector machine to recognize semantic inference in Chinese text pair. In our system, we use multiple features including statistical features, lexical features and syntactic featu...

For SENSEVAL-2, we disambiguated the lexical sample using two different sense inventories. Official SENSEVAL-2 results were generated using WordNet, and separately using the New Oxford Dictionary of English (NODE). Since our initial submission, we have implemented additional routines and have now examined the differences in the features used for making sense selections. We report here the contr...

In most of the languages today, the sequence of words is quite restricted. It is quite obvious that an underlying structure which is, in general, abstract, generates such word orders. This underlying structure is basically the syntax of the language. Also, it is shown in previous researches that syntactic features are the most informative features in lexical class discovery such as verb classif...