Abstract | Text-level discourse parsing remains a challenge. |
Introduction | Discourse parsing is the task of identifying the presence and the type of the discourse relations between discourse units. |
Introduction | While research in discourse parsing can be partitioned into several directions according to different theories and frameworks, Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) is probably the most ambitious one, because it aims to identify not only the discourse relations in a small local context, but also the hierarchical tree structure for the full text: from the relations relating the smallest discourse units (called elementary discourse units, EDUs), to the ones connecting paragraphs. |
Introduction | Conventionally, there are two major subtasks related to text-level discourse parsing : (l) EDU segmentation: to segment the raw text into EDUs, and (2) tree-building: to build a discourse tree from EDUs, representing the discourse relations in the text. |
Related work | 2.1 HILDA discourse parser |
Related work | The HILDA discourse parser by Hernault et al. |
Related work | (2010) is the first attempt at RST-style text-level discourse parsing . |
Abstract | Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. |
Abstract | In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing . |
Abstract | The resulting shift-reduce discourse parser obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank. |
Introduction | Unfortunately, the performance of discourse parsing is still relatively weak: the state-of-the-art F—measure for text-level relation detection in the RST Treebank is only slightly above 55% (Joty |
Introduction | In this paper, we present a representation leam-ing approach to discourse parsing . |
Introduction | Our method is implemented as a shift-reduce discourse parser (Marcu, 1999; Sagae, 2009). |
Model | The core idea of this paper is to project lexical features into a latent space that facilitates discourse parsing . |
Model | Thus, we name the approach DPLP: Discourse Parsing from Linear Projection. |
Model | We apply transition-based (incremental) structured prediction to obtain a discourse parse , training a predictor to make the correct incremental moves to match the annotations of training data in the RST Treebank. |
Abstract | Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. |
Abstract | In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). |
Abstract | Experiments show that our discourse dependency parsers achieve a competitive performance on text-level discourse parsing . |
Add arc <eC,ej> to GC with | The third feature type (Position) is also very helpful to discourse parsing . |
Discourse Dependency Parsing | Figure 5 shows the details of the Chu-Liu/Edmonds algorithm for discourse parsing . |
Discourse Dependency Structure and Tree Bank | Section 3 presents the discourse parsing approach based on the Eisner and MST algorithms. |
Introduction | Researches in discourse parsing aim to acquire such relations in text, which is fundamental to many natural language processing applications such as question answering, automatic summarization and so on. |
Introduction | One important issue behind discourse parsing is the representation of discourse structure. |
Introduction | 1 EDU segmentation is a relatively trivial step in discourse parsing . |
Abstract | We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. |
Conclusions and Future Work | First, we defined two simple discourse-aware similarity metrics (lexicalized and un-lexicalized), which use the all-subtree kernel to compute similarity between discourse parse trees in accordance with the Rhetorical Structure Theory. |
Introduction | One possible reason could be the unavailability of accurate discourse parsers . |
Introduction | We first design two discourse-aware similarity measures, which use DTs generated by a publicly-available discourse parser (J oty et al., 2012); then, we show that they can help improve a number of MT evaluation metrics at the segment- and at the system-level in the context of the WMT11 and the WMT12 metrics shared tasks (Callison-Burch et al., 2011; Callison-Burch et al., 2012). |
Our Discourse-Based Measures | In order to develop a discourse-aware evaluation metric, we first generate discourse trees for the reference and the system-translated sentences using a discourse parser , and then we measure the similarity between the two discourse trees. |
Our Discourse-Based Measures | In Rhetorical Structure Theory, discourse analysis involves two subtasks: (i) discourse segmentation, or breaking the text into a sequence of EDUs, and (ii) discourse parsing , or the task of linking the units (EDUs and larger discourse units) into labeled discourse trees. |
Our Discourse-Based Measures | (2012) proposed discriminative models for both discourse segmentation and discourse parsing at the sentence level. |
Related Work | Compared to the previous work, (i) we use a different discourse representation (RST), (ii) we compare discourse parses using all-subtree kernels (Collins and Duffy, 2001), (iii) we evaluate on much larger datasets, for several language pairs and for multiple metrics, and (iv) we do demonstrate better correlation with human judgments. |
CR + LS + DMM + DPM 39.32* +24% 47.86* +20% | This is a motivating result for discourse analysis, especially considering that the discourse parser was trained on a domain different from the corpora used here. |
Experiments | Due to the speed limitations of the discourse parser , we randomly drew 10,000 QA pairs from the corpus of how questions described by Surdeanu et al. |
Models and Features | 4.2 Discourse Parser Model |
Models and Features | The discourse parser model (DPM) is based on the RST discourse framework (Mann and Thompson, 1988). |
Models and Features | However, this also introduces noise because discourse analysis is a complex task and discourse parsers are not perfect. |
Related Work | In terms of discourse parsing , Verberne et al. |
Related Work | Discourse Parser (deep) |
Related Work | They later concluded that while discourse parsing appears to be useful for QA, automated discourse parsing tools are required before this approach can be tested at scale (Verbeme et al., 2010). |