@inproceedings{liu-etal-2026-multi-level,
title = "Multi-Level Implicit Discourse Relation Classification via Sequence-Level Reinforcement Learning",
author = "Liu, Wei and
Shen, Xiaoyu and
Fu, Xiyan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1801/",
pages = "41027--41040",
ISBN = "979-8-89176-459-0",
abstract = "Implicit Discourse Relation Classification (IDRC) identifies discourse relations between text spans when connectives are absent. The task is typically evaluated on the Penn Discourse Treebank (PDTB), where discourse senses are organized in a hierarchical structure. Recent unified models predict discourse labels level by level under teacher forcing, which leads to exposure bias and cascading errors across the hierarchy. Moreover, token-level training objectives fail to assess the correctness of the entire label sequence. We reformulate multi-level IDRC as hierarchical label sequence generation and optimize the full label sequence using sequence-level reinforcement learning. By sampling and ranking complete label sequences, the proposed framework directly optimizes global sequence correctness rather than isolated token-level decisions. Experiments on PDTB 2.0 and 3.0 demonstrate consistent improvements over strong baselines. Further analysis shows that fine-to-coarse decoding outperforms the conventional coarse-to-fine strategy, highlighting the importance of decoding order in hierarchical discourse modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-multi-level">
<titleInfo>
<title>Multi-Level Implicit Discourse Relation Classification via Sequence-Level Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Implicit Discourse Relation Classification (IDRC) identifies discourse relations between text spans when connectives are absent. The task is typically evaluated on the Penn Discourse Treebank (PDTB), where discourse senses are organized in a hierarchical structure. Recent unified models predict discourse labels level by level under teacher forcing, which leads to exposure bias and cascading errors across the hierarchy. Moreover, token-level training objectives fail to assess the correctness of the entire label sequence. We reformulate multi-level IDRC as hierarchical label sequence generation and optimize the full label sequence using sequence-level reinforcement learning. By sampling and ranking complete label sequences, the proposed framework directly optimizes global sequence correctness rather than isolated token-level decisions. Experiments on PDTB 2.0 and 3.0 demonstrate consistent improvements over strong baselines. Further analysis shows that fine-to-coarse decoding outperforms the conventional coarse-to-fine strategy, highlighting the importance of decoding order in hierarchical discourse modeling.</abstract>
<identifier type="citekey">liu-etal-2026-multi-level</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1801/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41027</start>
<end>41040</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Level Implicit Discourse Relation Classification via Sequence-Level Reinforcement Learning
%A Liu, Wei
%A Shen, Xiaoyu
%A Fu, Xiyan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-etal-2026-multi-level
%X Implicit Discourse Relation Classification (IDRC) identifies discourse relations between text spans when connectives are absent. The task is typically evaluated on the Penn Discourse Treebank (PDTB), where discourse senses are organized in a hierarchical structure. Recent unified models predict discourse labels level by level under teacher forcing, which leads to exposure bias and cascading errors across the hierarchy. Moreover, token-level training objectives fail to assess the correctness of the entire label sequence. We reformulate multi-level IDRC as hierarchical label sequence generation and optimize the full label sequence using sequence-level reinforcement learning. By sampling and ranking complete label sequences, the proposed framework directly optimizes global sequence correctness rather than isolated token-level decisions. Experiments on PDTB 2.0 and 3.0 demonstrate consistent improvements over strong baselines. Further analysis shows that fine-to-coarse decoding outperforms the conventional coarse-to-fine strategy, highlighting the importance of decoding order in hierarchical discourse modeling.
%U https://aclanthology.org/2026.emnlp-main.1801/
%P 41027-41040
Markdown (Informal)
[Multi-Level Implicit Discourse Relation Classification via Sequence-Level Reinforcement Learning](https://aclanthology.org/2026.emnlp-main.1801/) (Liu et al., EMNLP 2026)
ACL