paper-with-me

홈 › Papers

Labeling Explicit Discourse Relations using Pre-trained Language Models

2020-06-21 · Murathan Kurfali

Labeling explicit discourse relations is one of the most challenging sub-tasks of the shallow discourse parsing where the goal is to identify the discourse connectives and the boundaries of their arguments. The state-of-the-art models achieve slightly above 45% of F-score by using hand-crafted features. The current paper investigates the efficacy of the pre-trained language models in this task. We find that the pre-trained language models, when finetuned, are powerful enough to replace the linguistic features. We evaluate our model on PDTB 2.0 and report the state-of-the-art results in the extraction of the full relation. This is the first time when a model outperforms the knowledge intensive models without employing any linguistic features.

📄 PDF Abstract BibTeX arXiv:2006.11852

Code (0)

등록된 구현이 없습니다.

Tasks

Discourse Parsing

Similar Papers 제목 키워드 기반

Argument Labeling of Explicit Discourse Relations using LSTM Neural Networks

2017-08-11 · RANLP 2017 9 · Sohail Hooda, Leila Kosseim

Argument labeling of explicit discourse relations is a challenging task. The state of the art systems achieve slightly above 55% F-measure but require hand-crafted features. In this paper, we propose a Long Short Term Me…

Feature Engineering

Assessing Discourse Relations in Language Generation from GPT-2

2020-04-26 · INLG (ACL) 2020 12 · Wei-Jen Ko, Junyi Jessy Li

Recent advances in NLP have been attributed to the emergence of large-scale pre-trained language models. GPT-2, in particular, is suited for generation tasks given its left-to-right language modeling objective, yet the l…

Language ModelingLanguage ModellingText Generationvalid

Neural Methodius Revisited: Do Discourse Relations Help with Pre-Trained Models Too?

2021-08-01 · INLG (ACL) 2021 8 · Aleksandre Maskharashvili, Symon Stevens-Guille, Xintong Li, Michael White

Recent developments in natural language generation (NLG) have bolstered arguments in favor of re-introducing explicit coding of discourse relations in the input to neural models. In the Methodius corpus, a meaning repres…

RelationText Generation

Towards Identifying Alternative-Lexicalization Signals of Discourse Relations

2022-10-01 · COLING 2022 10 · René Knaebel, Manfred Stede

The task of shallow discourse parsing in the Penn Discourse Treebank (PDTB) framework has traditionally been restricted to identifying those relations that are signaled by a discourse connective (“explicit”) and those th…

Discourse Parsing

Generating Discourse Connectives with Pre-trained Language Models: Conditioning on Discourse Relations Helps Reconstruct the PDTB

2022-09-01 · SIGDIAL (ACL) 2022 9 · Symon Stevens-Guille, Aleksandre Maskharashvili, Xintong Li, Michael White

We report results of experiments using BART (Lewis et al., 2019) and the Penn Discourse Tree Bank (Webber et al., 2019) (PDTB) to generate texts with correctly realized discourse relations. We address a question left ope…

RelationText Generation