Connor et al. (2008) mention “specifying textual requirements of genres” (p.12) as one of the reasons which have motivated researchers in the analysis of writing. Members of each genre should be able to produce and retrieve these textual requirements appropriately to be considered communicatively proficient. One of the textual requirements of genres is regularities of specific forms and content...

It is generally recognized that many second language learners have difficulties with cohesion in academic texts.  Writing seems to be the most difficult subject for many students. To produce good writing, it is necessary to know how to organize Theme and Rheme in a text. Thematic structure as an important feature in textual metafunction plays a significant role in promoting the textual coherenc...

In this paper we investigate the relation between positive and negative pairs in Textual Entailment (TE), in order to highlight the role of contradiction in TE datasets. We base our analysis on the decomposition of Text-Hypothesis pairs into monothematic pairs, i.e. pairs where only one linguistic phenomenon at a time is responsible for entailment judgment and we argue that such a deeper inspec...

In recent years, writing, as one of the most important communicative skills, has been drawing increasing attention in English language teaching in China. This paper presents an investigation into the use of decomposition in Latent Semantic Analysis (LSA) to analyze textual coherence. Based on LSA and Halliday and Hasan’s (1976) concepts of cohesion and their categorization of cohesive devices, ...

Event factuality is information about whether events mentioned in natural language correspond to either actual events that have occurred in the real world or events that are of uncertain interpretation. Factuality analysis is useful for information extraction and textual entailment recognition, among others, but sufficient performance has not yet been achieved by the machine learning-based appr...

Rich geo-textual data is available online and the data keeps increasing at a high speed. We propose two user behavior models to learn several types of user preferences from geo-textual data, and a prototype system on top of the user preference models for mining and search geo-textual data (called PreMiner) to support personalized maps. Different from existing recommender systems and data analys...