China

We present a dataset of text revisions involving the deletion or replacement of discourse connectives. Manual annotation of a replacement subset reveals that only 19% of edits were judged either necessary or should be left unchanged, with the rest appearing optional. Surprisal metrics from GPT-2 token probabilities and prompt-based predictions from GPT-4.1 correlate with these judgments, particularly in such clear cases.

EMNLP 2025

Information-Theoretic and Prompt-Based Evaluation of Discourse Connective Edits in Instructional Text Revisions

workshop paper

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Previous work has shown that simple mask-filling can provide useful information about the discourse informativeness of syntactic structures. Dong et al. (2024) first adopted this approach to investigating preposing constructions. The problem with single token mask fillers was that they were, by and large, ambiguous. We address the issue by adapting the approach of Kalinsky et al. (2023) to support the prediction of multi-token connectives in masked positions. Our first experiment demonstrates that this multi-token mask-filling approach substantially outperforms the previously considered single-token approach in recognizing implicit discourse relations. Our second experiment corroborates previous findings, providing additional empirical support for the role of preposed syntactic constituents in signaling discourse coherence. Overall, our study extends existing mask-filling methods to a new discourse-level task and reinforces the linguistic hypothesis concerning the discourse informativeness of preposed structures.

Multi-token Mask-filling and Implicit Discourse Relations

This paper presents the results obtained by the MELODI team for the three tasks proposed within the DISRPT 2025 shared task on discourse: segmentation, connective identification, and relation classification. 
The competition involves corpora in various languages, in several underlying frameworks, and datasets are given with or without sentence segmentation. 
This year, for the ranked, closed track, the campaign adds as a constraint to train only one model for each task, with an upper bound on the size of the model (no more than 4B parameters).
An additional open track authorizes any size of, possibly non public, models that will not be reproduced by the organizers and thus not ranked.
We compared several fine-tuning approaches either based on encoder-only transformer-based models, or auto-regressive generative ones. 
To be able to train one model on the variety of corpora, we explored various ways of combining data -- by framework, language or language groups, with different sequential orderings --, and the addition of features to guide the model. 
For the closed track, our final submitted system is based on XLM-RoBERTa large for relation identification, and on InfoXLM for segmentation and connective identification. 
Our experiments demonstrate that building a single, multilingual model does not necessarily degrade the performance compared to language-specific systems, with at best 64.06% for relation identification, 90.19% for segmentation and 81.15% for connective identification (on average on the development sets), results that are similar or higher that the ones obtained in previous campaigns.
We also found that a generative approach could give even higher results on relation identification, with at best 64.65% on the dev sets.

DisCuT and DiscReT: MELODI at DISRPT 2025 Multilingual discourse segmentation, connective tagging and relation classification

We present our submission to Task 3 (Discourse Relation Classification) of the DISRPT 2025 shared task. Task 3 introduces a unified set of 17 discourse relation labels across 39 corpora in 16 languages and six discourse frameworks, posing significant multilingual and cross‑formalism challenges. We first benchmark the task by fine‑tuning multilingual BERT‑based models (mBERT, XLM‑RoBERTa‑Base, and XLM‑RoBERTa‑Large) with two argument‑ordering strategies and progressive unfreezing ratios to establish strong baselines. We then evaluate prompt‑based large language models (namely Claude Opus 4.0) in zero‑shot and few‑shot settings to understand how LLMs respond to the newly proposed unified labels. Finally, we introduce HiDAC, a Hierarchical Dual‑Adapter Contrastive learning model. Results show that while larger transformer models achieve higher accuracy, the improvements are modest, and that unfreezing the top 75% of encoder layers yields performance comparable to full fine‑tuning while training far fewer parameters. Prompt‑based models lag significantly behind fine‑tuned transformers, and HiDAC achieves the highest overall accuracy (67.5%) while remaining more parameter‑efficient than full fine‑tuning.

CLaC at DISRPT 2025: Hierarchical Adapters for Cross-Framework & Multi-lingual Discourse Relation Classification

This paper presents DeDisCo, Georgetown University's entry in the DISRPT 2025 shared task on discourse relation classification. We test two approaches, using an mt5-based encoder and a decoder based approach using the openly available Qwen model. We also experiment on training with augmented dataset for low-resource languages using matched data translated automatically from English, as well as using some additional linguistic features inspired by entries in previous editions of the Shared Task. Our system achieves a macro-accuracy score of 71.28, and we provide some interpretation and error analysis for our results.

DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification

This paper describes the submission of the HITS team to the DISRPT 2025 shared task. The shared task includes three sub-tasks: (1) discourse unit segmentation across formalisms, (2) cross-lingual discourse connective identification, and (3) cross-formalism discourse relation classification. This paper presents our strategies for the DISRPT 2025 Shared Task. In Task 1, our approach involves fine-tuning through multilingual joint training on linguistically motivated language groups. We incorporated two key techniques to improve model performance: a weighted loss function to address the task's significant class imbalance and Fast Gradient Method (FGM) adversarial training to boost the model's robustness.

In task 2, our approach involves building an ensemble of three encoder models whose embeddings are smartly fused together with a multi-head attention layer. We also add Part-Of-Speech tags and dependency relations present in the training file as linguistic features. A CRF layer is added after the classification layer to account for dependencies between adjacent labels. To account for label imbalance, we use focal loss and label smoothing. This ensures our model is robust and flexible enough to handle different languages.

In task 3, we use two-stage fine-tuning framework designed to transfer the nuanced reasoning capabilities of a very large "teacher" model to a compact "student" model so that the smaller model can learn complex discourse relationships. The fine-tuning process follows a curriculum learning framework. In such a framework the model learns to perform increasingly harder tasks. In our case, the model first learns to look at the discourse units and then predict the label followed by looking at Chain-Of-Thought reasoning for harder examples. This way it can learn to internalise such reasoning and increase prediction accuracy on the harder samples.

HITS at DISRPT 2025: Discourse Segmentation, Connective Detection, and Relation Classification

The work presented here describes our participation in DISRPT 2025 shared task in three tasks, Task1: Discourse Unit Segmentation across Formalisms, Task 2: Discourse Connective Identification across Languages and Task 3: Discourse Relation Classification across Formalisms. We have fine-tuned XLM-RoBERTa, a language model to address these three tasks. We have come up with one single multilingual language model for each task. Our system handles data in both the formats .conllu and .tok and different discourse formalisms. We have obtained encouraging results. The performance on test data in the three tasks is similar to the results obtained for the development data.

SeCoRel: Multilingual Discourse Analysis in DISRPT 2025

In this work we examine LLMs' ability to ask clarification questions in task-oriented dialogues that follow the asynchronous instruction-giver/instruction-follower format. We present a new corpus that combines two existing annotations of the Minecraft Dialogue Corpus --- one for reference and ambiguity in reference, and one for SDRT including clarifications --- into a single common format providing the necessary information to experiment with clarifications and their relation to ambiguity. With this corpus we compare LLM actions with original human-generated clarification questions, examining how both humans and LLMs act in the case of ambiguity. We find that there is only a weak link between ambiguity and humans producing clarification questions in these dialogues, and low correlation between humans and LLMs. Humans hardly ever produce clarification questions for referential ambiguity, but often do so for task-based uncertainty. Conversely, LLMs produce more clarification questions for referential ambiguity, but less so for task uncertainty. We question if LLMs' ability to ask clarification questions is predicated on their recent ability to simulate reasoning, and test this with different reasoning approaches, finding that reasoning does appear to increase question frequency and relevancy.

Referential ambiguity and clarification requests: comparing human and LLM behaviour

In this paper, we analyse coreference annotation of the German language, focussing on the phenomenon of simplification, that is, the tendency to use words and constructions that are assumed to be easier perceived, understood, or produced. Simplification is one of the tools used by language users in order to optimise communication effectively. We are interested in how simplification is reflected in coreference in two different language products exposed to the phenomena of simplification: simultaneous interpreting and Easy German. For this, we automatically annotate simplified texts with coreference. We then evaluate the outputs of automatic annotation. In addition, we also look into quantitative distributions of some coreference features. Our findings show that although the language products under analysis diverge in terms of simplification driving factors, they share some specific coreference features. We also show that this specificity may cause annotation errors in simplified language, e.g. in non-nominal or split antecedents.

Coreference in simplified German: Linguistic features and challenges of automatic annotation

We present the submissions of our team to the Unconstrained and LLM tracks of the Computational Models of Reference, Anaphora and Coreference (CRAC2025) shared task, where we ended respectively in the fifth and the first place, but nevertheless with similar scores: average CoNLL-F1 scores of 61.57 and 62.96 on the test set, but with very large differences in computational cost. Indeed, the classical pair-wise resolution system submitted to the Unconstrained track obtained similar performance but with less than 10\% of the computational cost. Reflecting on this fact, we point out problems that we ran into using generative AI to perform coreference resolution. We explain how the framework of text generation stands in the way of a reliable text-global coreference representation. Nonetheless, we realize there are many potential improvements of our LLM-system; we discuss them at the end of this article.

GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task?

This paper presents our submission to the CRAC 2025 Shared Task on Multilingual Coreference Resolution in the LLM track. We propose a prompt-based few-shot coreference resolution system where the final inference is performed by Grok-3 using in-context learning. The core of our methodology is a difficulty- aware sample selection pipeline that leverages Gemini Flash 2.0 to compute semantic diffi- culty metrics, including mention dissimilarity and pronoun ambiguity. By identifying and selecting the most challenging training sam- ples for each language, we construct highly informative prompts to guide Grok-3 in predict- ing coreference chains and reconstructing zero anaphora. Our approach secured 3rd place in the CRAC 2025 shared task.

Downloads

Next from EMNLP 2025

Multi-token Mask-filling and Implicit Discourse Relations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2025

Multi-token Mask-filling and Implicit Discourse Relations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads