Much work has examined the emergence of discourse structure from the choices speakers make at the linguistic and intentional level (Grosz and Sid-ner, 1986).

In prior work, the way that people influence discourse structure is described through the two tightly-related concepts of initiative and control.

However, that body of work focuses on influencing discourse structure through positioning.

In this work, we seek to formalize the ways speak-empmfimfimehwfiuMamm:deomfim a way that maintains a notion of discourse structure , and which can be aggregated to evaluate a speaker’s overall stance in a dialogue.

Constructs such as Initiative and Control (Whittaker and Stenton, 1988), which attempt to operationalize the authority over a discourse’s structure , fall under the umbrella of positioning.

We cannot compare with the results of Feng and Hirst (2012), because they do not evaluate on the overall discourse structure , but rather treat each relation as an indiVidual classification problem.

Discourse structure describes the high-level organization of text or speech.

Figure 1: An example of RST discourse structure .

Based on this observation, our goal is to learn a function that transforms lexical features into a much lower-dimensional latent representation, while simultaneously learning to predict discourse structure based on this latent representation.

Prior learning-based work has largely focused on lexical, syntactic, and structural features, but the close relationship between discourse structure and semantics (Forbes-Riley et al., 2006) suggests that shallow feature sets may struggle to capture the long tail of alternative lexicalizations that can be used to realize discourse relations (Prasad et al., 2010; Marcu and Echihabi, 2002).

In this work, we show how discourse structure annotations can function as a superVision signal to discriminatively learn a transformation from lexical features to a latent space that is well-suited for discourse parsing.

We present experiments in using discourse structure for improving machine translation evaluation.

In this paper we have shown that discourse structure can be used to improve automatic MT evaluation.

Overall, from the experimental results in this section, we can conclude that discourse structure is an important information source to be taken into account in the automatic evaluation of machine translation output.

Our experiments show that many existing metrics can benefit from additional knowledge about discourse structure .

We experimentally demonstrate that the discourse structure of non-factoid answers provides information that is complementary to lexical semantic similarity between question and answer, improving performance up to 24% (relative) over a state-of-the-art model that exploits lexical semantic similarity alone.

Driven by this observation, our main hypothesis is that the discourse structure of NF answers provides complementary information to state-of-the-art QA models that measure the similarity (either lexical and/or semantic) between question and answer.

Argument labels indicate only if lemmas from the question were found in a discourse structure present in an answer candidate, and do not speak to the specific lemmas that were found.

Second, these features model the intensity of the match between the text surrounding the discourse structure and the question text using both the assigned argument labels and the feature values.

The focus stack takes into account the discourse structure by keeping track of discourse states.

the score function based on current input and discourse structure given the focus stack.

In addition to the hypothesis score, we defined the discourse score SD at the discourse level to consider the discourse structure between the previous node and current node given the focus stack 8.

6It is interesting to note that this type of staged training is evocative of language acquisition in children: lexical associations are formed (Model 1) before higher-level discourse structure is learned (Model 3).

We did not experiment with Model 3 since the discourse structure on records in this domain is not at all governed by a simple Markov model on record types—indeed, most regions do not refer to any records at all.

,rlrl), where each record 7“,- E s. This model is intended to capture two types of regularities in the discourse structure of language.

While the entity-based model captures repetitive mentions of entities, our discourse relation-based model gleans its evidence from the argumentative and discourse structure of the text.

The coherence of a text is usually reflected by its discourse structure and relations.

In this paper, we detail our model to capture the coherence of a text based on the statistical distribution of the discourse structure and relations.

The nucleus is more salient to the discourse structure , while the other span, the satellite, represents supporting information.

It is important for generated summaries to have a discourse structure that is similar to that of the source document.

Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) is one way of introducing the discourse structure of a document to a summarization task (Marcu, 1998; Daume III and Marcu, 2002; Hirao et al., 2013).

Soricut and Marcu (2003) use a standard bottom-up chart parsing algorithm to determine the discourse structure of sentences.

One important issue behind discourse parsing is the representation of discourse structure .

Here is the basic idea: the discourse structure consists of EDUs which are linked by the binary, asymmetrical relations called dependency relations.