Table 6: Contextual Information for Answer Detection.

Linear CRFs with contextual information perform better than those without context.

The results clearly shows that contextual information greatly improves the performance of answer detection.

As shown in the example, a forum question usually requires contextual information to provide background or constraints.

Moreover, it sometimes needs contextual information to provide explicit link to its answers.

We call contextual information the context of a question in this paper.

We also compared the performance of our model based on different contextual information , and show that both large-scale monolingual data and parallel bilingual data can be helpful to generate correct measure words.

Then, the collocation between measure words and head words and their surrounding contextual information are extracted to train the measure word selection models.

Then, contextual information within the windows in the source and the target sentence is extracted and fed to the measure word selection model.

We do not integrate our measure word generation module into the SMT decoder since there is only little target contextual information available during SMT decoding.

Based on contextual information contained in both input source sentence and SMT system’s output translation, a measure word candidate set M is constructed.

After obtaining the measure word candidate set M, a measure word selection model is employed to select the best one from M. Given the contextual information C in both source window and target

CP enriches the representation of textual objects with typical contextual information that constrains or disambiguates their meaning, and provides matching functions that compare the preferences of objects involved in the inference.

Overall, such incorrect inferences may be avoided by considering contextual information for t, h and 7“ during their matching process.

In this framework, the representation of an object 2, where 2 may be a text, a template or an entailment rule, is enriched with contextual information denoted cp(z).

In addition, we will try to make better use of the context information when replacing paraphrase patterns in context sentences.

In Section 4.1, we have evaluated the precision of the paraphrase patterns without considering context information .

The context information was also considered by our judges.