Abstract | We use linear-chain conditional random fields (CRF) for sentence type tagging, and a 2D CRF to label the dependency relation between sentences. |
Introduction | Towards this goal, in this paper, we define two tasks: labeling the types for sentences, and finding the dependency relations between sentences. |
Introduction | In this study, we use two approaches for labeling of dependency relation between sentences. |
Introduction | Our experimental results show that our proposed sentence type tagging method works very well, even for the minority categories, and that using 2D CRF further improves performance over linear-chain CRFs for identifying dependency relation between sentences. |
Related Work | In this paper, in order to provide a better foundation for question answer detection in online forums, we investigate tagging sentences with a much richer set of categories, as well as identifying their dependency relationships . |
Thread Structure Tagging | Knowing only the sentence types without their dependency relations is not enough for question answering tasks. |
Thread Structure Tagging | Note that sentence dependency relations might not be a one-to-one relation. |
Thread Structure Tagging | Dependency relationship could happen between many different types of sentences, for example, answer(s) to question(s), problem clarification to question inquiry, feedback to solutions, etc. |
Beyond lexical CLTE | builds on two additional feature sets, derived from i) semantic phrase tables, and ii) dependency relations . |
Beyond lexical CLTE | Dependency Relation (DR) matching targets the increase of CLTE precision. |
Beyond lexical CLTE | We define a dependency relation as a triple that connects pairs of words through a grammatical relation. |
Experiments and results | Dependency relations (DR) have been extracted running the Stanford parser (Rafferty and Manning, 2008; De Marneffe et al., 2006). |
Experiments and results | Dependency relations (DR) have been extracted parsing English texts and Spanish hypotheses with DepPattern (Gamallo and Gonzalez, 2011). |
Experiment and Results | Interestingly, the underspecified dependency relation DEP which is typically used in cases for which no obvious syntactic dependency comes to mind shows a suspicion rate of 0.61 (595F/371P). |
Mining Dependency Trees | First, dependency trees are converted to Breadth—First Canonical Form whereby lexicographic order can apply to the word forms labelling tree nodes, to their part of speech, to their dependency relation or to any combination thereof3. |
Mining Dependency Trees | 3For convenience, the dependency relation labelling the edges of dependency trees is brought down to the daughter node of the edge. |
Gaining Dependency Structures | Dependency Relation |
Gaining Dependency Structures | Table 1: Mapping from HPS G’s PAS types to dependency relations . |
Gaining Dependency Structures | heads and (2) appending dependency relations for those words/punctuation that do not have any head. |