| Causal Relations for Why-QA | A bansetsa is a syntactic constituent composed of a content word and several function words such as postpositions and case markers. |
| Causal Relations for Why-QA | Our term matching method judges that a causal relation is a candidate of an appropriate causal relation if its effect part contains at least one content word (nouns, verbs, and adjectives) in the question. |
| Causal Relations for Why-QA | The n-grams of 75 f1 and tfg are restricted to those containing at least one content word in a question. |
| System Architecture | We retrieved documents from Japanese web texts using Boolean AND and OR queries generated from the content words in why-questions. |
| Application to Essay Scoring | Likewise, a feature that calculates the average PMI for all pairs of content word types in the text failed to produce an improvement over the baseline for setA pl-p6. |
| Methodology | The second is which pairs of words in a text to consider when building a profile for the text; we opted for all pairs of content word types occurring in a text, irrespective of the distance between them. |
| Methodology | Thus, the text “The dog barked and wagged its tail” is much tighter than the text “Green ideas sleep furiously”, with all the six content word pairs scoring above PMI=5.5 in the first and below PMI=2.2 in the second.4 |
| Conclusion | With this approach, using a stop list does not have a major effect on results for most relation classes, which suggests most of the word pairs affecting performance are content word pairs which may truly be semantically related to the discourse structure. |
| Introduction | We show that our formulation outperforms the original one while requiring less features, and that using a stop list of functional words does not significantly affect performance, suggesting that these features indeed represent semantically related content word pairs. |
| Word Pairs | An analysis in (Pitler et al., 2009) also shows that the top word pairs (ranked by information gain) all contain common functional words, and are not at all the semantically-related content words that were imagined. |
| Architecture of BRAINSUP | ning, 2003) and produce the patterns by stripping away all content words from the parses. |
| Evaluation | Two or three content words appearing in each slogan were randomly selected as the target words 1:. |
| Evaluation | Furthermore, we only considered sentences in which all the content words are listed in WordNet (Miller, 1995) with the observed part of speech.8 The LSA space used for the semantic feature functions was also learned on BNC data, but in this case no filtering was applied. |
| Content Selection | A valid indicator-argument pair should have at least one content word and satisfy one of the following constraints: |
| Content Selection | For training data construction, we consider a relation instance to be a positive example if it shares any content word with its corresponding abstracts, and a negative example otherwise. |
| Surface Realization | number of content words in indicator/argument number of content words that are also in previous DA indicator/argument only contains stopword? |