Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining

• URL: http://arxiv.org/abs/2011.03203v1
• Date: Fri, 6 Nov 2020 06:11:26 GMT
• Title: Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining
• Authors: Grigorii Guz, Patrick Huber and Giuseppe Carenini
• Abstract summary: RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parsing, incorporating recent contextual language models. Our establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT.
• Score: 26.517219486173598
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale "silver-standard" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis.

Related papers

• Llamipa: An Incremental Discourse Parser [6.9534924995446055]
  This paper provides the first discourse parsing experiments with a large language model finetuned on corpora in the style of SDRT. It can process discourse data, which is essential for the eventual use of discourse information in downstream tasks.
  arXiv  Detail & Related papers  (2024-06-26T11:08:17Z)
• Unsupervised Chunking with Hierarchical RNN [62.15060807493364]
  This paper introduces an unsupervised approach to chunking, a syntactic task that involves grouping words in a non-hierarchical manner. We present a two-layer Hierarchical Recurrent Neural Network (HRNN) designed to model word-to-chunk and chunk-to-sentence compositions. Experiments on the CoNLL-2000 dataset reveal a notable improvement over existing unsupervised methods, enhancing phrase F1 score by up to 6 percentage points.
  arXiv  Detail & Related papers  (2023-09-10T02:55:12Z)
• Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling [70.23876429382969]
  We propose a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge.
  arXiv  Detail & Related papers  (2023-07-16T15:18:25Z)
• Topic-driven Distant Supervision Framework for Macro-level Discourse Parsing [72.14449502499535]
  The task of analyzing the internal rhetorical structure of texts is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for training remains a major obstacle. Recent studies have attempted to overcome this limitation by using distant supervision.
  arXiv  Detail & Related papers  (2023-05-23T07:13:51Z)
• Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences [67.37544997614646]
  We present the first study on unsupervised spoken constituency parsing. The goal is to determine the spoken sentences' hierarchical syntactic structure in the form of constituency parse trees. We show that accurate segmentation alone may be sufficient to parse spoken sentences accurately.
  arXiv  Detail & Related papers  (2023-03-15T17:57:22Z)
• A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing [44.72809363746258]
  This paper explores a strong baseline by integrating existing simple parsing strategies, top-down and bottom-up, with various transformer-based pre-trained language models. The experimental results obtained from two benchmark datasets demonstrate that the parsing performance relies on the pretrained language models rather than the parsing strategies.
  arXiv  Detail & Related papers  (2022-10-15T18:38:08Z)
• Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation [8.688675709130289]
  RST-style discourse parsing plays a vital role in many NLP tasks. Despite its importance, one of the most prevailing limitations in modern day discourse parsing is the lack of large-scale datasets.
  arXiv  Detail & Related papers  (2021-12-12T10:16:45Z)
• RST Parsing from Scratch [14.548146390081778]
  We introduce a novel end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees.
  arXiv  Detail & Related papers  (2021-05-23T06:19:38Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision [30.615883375573432]
  We present a novel methodology to automatically generate discourse treebanks using distant supervision from sentiment-annotated datasets. Our approach generates trees incorporating structure and nuclearity for documents of arbitrary length by relying on an efficient beam-search strategy. Experiments indicate that a discourse trained on our MEGA-DT treebank delivers promising inter-domain performance gains.
  arXiv  Detail & Related papers  (2020-11-05T18:22:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.