Does syntax help discourse segmentation? Not so much
Discourse segmentation is the first step in building discourse parsers.
Deep Enhanced Representation for Implicit Discourse Relation Recognition
diccooo/Deep_Enhanced_Repr_for_IDRR
•
•
COLING 2018
Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs.
Transition-based Neural RST Parsing with Implicit Syntax Features
fajri91/NeuralRST
•
•
COLING 2018
Syntax has been a useful source of information for statistical RST discourse parsing.
A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues
shizhouxing/DialogueDiscourseParsing
•
•
This paper presents a deep sequential model for parsing discourse dependency structures of multi-party dialogues.
Discourse Parsing in Videos: A Multi-modal Appraoch
arjunakula/Visual-Discourse-Parsing
•
•
We propose the task of Visual Discourse Parsing, which requires understanding discourse relations among scenes in a video.
RST-Tace A tool for automatic comparison and evaluation of RST trees
This paper presents RST-Tace, a tool for automatic comparison and evaluation of RST trees.
Hierarchical Pointer Net Parsing
ntunlp/ptrnet-depparser
•
•
IJCNLP 2019
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.
Unsupervised Discourse Constituency Parsing Using Viterbi EM
In this paper, we introduce an unsupervised discourse constituency parsing algorithm.
Top-Down RST Parsing Utilizing Granularity Levels in Documents
nttcslab-nlp/Top-Down-RST-Parser
•
•
To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures.
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
Research into the area of multiparty dialog has grown considerably over recent years.