Hierarchical Pointer Net Parsing

Abstract

Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity.However, the decoder of these parsers has a sequential structure, which does not yield the most appropriate inductive bias for deriving tree structures. In this paper, we propose hierarchical pointer network parsers, and apply them to dependency and sentence-level discourse parsing tasks. Our results on standard benchmark datasets demonstrate the effectiveness of our approach, outperforming existing methods and setting a new state-of-the-art.

A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure

“…In this paper, we present a top-down neural architecture to text-level discourse rhetorical structure parsing. Different from Lin et al (2019) and Liu et al (2019), we propose a hierarchical discourse encoder to better present the text span using both EDUs and split points. Benefiting from effective representation for large text spans, our text-level discourse parser achieves competitive or even better results than those best reported discourse parsers either neural or non-neural with hand-engineered features.…”

“…Among them, the EDU encoder and the split point encoder are responsible for representing the EDUs and the split points, respectively. Different from Lin et al (2019) and Liu et al (2019), we combine the representation of both EDUs and split points hierarchically to better represent the text span rather than only using the representation of the last EDU as the representation of the text span. In this way, the global information can be exploited for our text-level discourse parsing.…”

Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event

“…Several well-studied discourse analysis tasks have been shown useful for many NLP applications. The RST (Mann and Thompson, 1988;Soricut and Marcu, 2003;Feng and Hirst, 2012;Ji and Eisenstein, 2014;Li et al, 2014a;Liu et al, 2019) and PDTB style (Prasad et al, 2008;Pitler and Nenkova, 2009;Lin et al, 2014;Rutherford and Xue, 2016;Qin et al, 2016;Xu et al, 2018) discourse parsing tasks identify discourse units that are logically connected with a predefined set of rhetorical relations, and have been shown useful for a range of NLP applications such as text quality assessment (Lin et al, 2011), sentiment analysis (Bhatia et al, 2015), text summarization (Louis et al, 2010), machine translation (Li et al, 2014b) and text categorization (Ji and Smith, 2017). Text segmentation (Hearst, 1994;Choi, 2000;Eisenstein and Barzilay, 2008;Koshorek et al, 2018) is another well studied discourse analysis task that aims to divide a text into a sequence of topically coherent segments and has been shown useful for text summarization (Barzilay and Lee, 2004), sentiment analysis (Sauper et al, 2010) and dialogue systems (Shi et al, 2019).…”

RST Discourse Parser for Russian: An Experimental Study of Deep Learning Models

“…Recently, various top-down parsing approaches were proposed for simultaneous discourse parsing and elementary unit segmentation that address the computational performance issue. In [16], the segmenter and the sentence-level parser are trained jointly as parts of the unified encoder-decoder architecture, achieving superior results in the parsing performance, as well as in the parsing speed compared to previous end-to-end sentence-level bottom-up discourse parsers, namely SPADE [26] and DCRF [13]. Kobayashi et al [15] has recently proposed a top-down method that takes into account granularity levels of spans, namely document, paragraph, and sentence.…”

“…The practical usefulness of RST discourse parsing was shown in various NLP applications, such as text summarization, automatic essay scoring, and sentiment analysis [2,4,19]. There is a long history of research publications on automatic text-level rhetorical parsing for English [8,10,16,28] inter alia. Recently, the Russian-language corpus annotated with rhetorical structures (Ru-RSTreebank) [23] was released, which has unlocked the possibility of research on discourse parsing also for Russian.…”