The Two-Part Allegorical Saying (TPAS) is a Chinese linguistic phenomenon with a riddle-explanation structure, and an important component of Chinese metaphors. Existing research has primarily used TPAS to assist other semantic tasks, but lacks in-depth exploration of its intrinsic mechanisms: semantic rhetoric, logical reasoning, and metaphorical expression. To address this gap, we construct the first Chinese TPAS Reading Comprehension dataset (CTRC), which contains 18,103 TPASs and 75,296 passages. We frame it as a cloze test where the model selects the most suitable TPAS from candidates to fill passage blanks. To tackle the challenges of this CTRC task, we propose a Multi-view TPAS Contrastive Learning Network (MTCLN). Firstly, the joint vector cross-projection module extracts the rhetorical features of TPAS, such as homophonic puns, through vector space mapping to mitigate the semantic deviations caused by rhetoric. Then, the softened contrastive learning module strengthens the modeling of TPAS logical reasoning through feature association. Finally, the multi-view feature fusion module integrates contextual semantics with diverse TPAS features to facilitate the understanding of metaphorical expressions. Experiments on the CTRC dataset demonstrate that MTCLN achieves an average accuracy of 67.47%, outperforming large language models by 25.48%.

Understanding collaborative writing dynamics between native speakers (NS) and non-native speakers (NNS) is critical for enhancing collaboration quality and team inclusivity. In this paper, we partnered with communication researchers to develop visual analytics solutions for comparing NS and NNS behaviors in 162 writing sessions across 27 teams. The primary challenges in analyzing writing behaviors are data complexity and the uncertainties introduced by automated methods. In response, we present \textsc{COALA}, a novel visual analytics tool that improves model interpretability by displaying uncertainties in author clusters, generating behavior summaries using large language models, and visualizing writing-related actions at multiple granularities. We validated the effectiveness of \textsc{COALA} through user studies with domain experts (N=2+2) and researchers with relevant experience (N=8). We present the insights discovered by participants using \textsc{COALA}, suggest features for future AI-assisted collaborative writing tools, and discuss the broader implications for analyzing collaborative processes beyond writing.

Yimin Xiao, Yongle Zhang, Dayeon Ki, Calvin Bao, Marianna J. Martindale, Charlotte Vaughn, Ge Gao, Marine Carpuat. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Content creation today often takes place via collaborative writing. A longstanding interest of CSCW research lies in understanding and promoting the coordination between co-writers. However, little attention has been paid to individuals who write in their non-native language and to co-writer groups involving them. We present a mixed-method study that fills the above gap. Our participants included 32 co-writer groups, each consisting of one native speaker (NS) of English and one non-native speaker (NNS) with limited proficiency. They performed collaborative writing adopting two different workflows: half of the groups began with NNSs taking the first editing turn and half had NNSs act after NSs. Our data revealed a 'late-mover disadvantage' exclusively experienced by NNSs: an NNS's ideational contributions to the joint document were suppressed when their editing turn was placed after an NS's turn, as opposed to ahead of it. Surprisingly, editing help provided by AI-powered tools did not exempt NNSs from being disadvantaged. Instead, it triggered NSs' overestimation of NNSs' English proficiency and agency displayed in the writing, introducing unintended tensions into the collaboration. These findings shed light on the fair assessment and effective promotion of a co-writer's contributions in language diverse settings. In particular, they underscore the necessity of disentangling contributions made to the ideational, expressional, and lexical aspects of the joint writing.

A major challenge in the practical use of Machine Translation (MT) is that users lack guidance to make informed decisions about when to rely on outputs.Progress in quality estimation research provides techniques to automatically assess MT quality, but these techniques have primarily been evaluated in vitro by comparison against human judgments outside of a specific context of use.This paper evaluates quality estimation feedback in vivo with a human study simulating decision-making in high-stakes medical settings.Using Emergency Department discharge instructions, we study how interventions based on quality estimation versus backtranslation assist physicians in deciding whether to show MT outputs to a patient.We find that quality estimation improves appropriate reliance on MT, but backtranslation helps physicians detect more clinically harmful errors that QE alone often misses.

In this study, we created an imperative corpus with speech conversations from dialogues in The Big Bang Theory and with the written comments in Wikipedia’s Articles for Deletion discussions. For the TV show data, 59 episodes containing 25,076 statements are used. We manually annotated imperatives based on the annotation guideline adapted from Condoravdi and Lauer’s study (2012) and used the retrieved data to assess the performance of syntax-based classification rules. For the Wikipedia AfD comments data, we first developed and leveraged a syntax-based classifier to extract 10,624 statements that may be imperative, and we manually examined the statements and then identified true positives. With this corpus, we also examined the performance of the rule-based imperative detection tool. Our result shows different outcomes for speech (dialogue) and written data. The rule-based classification performs better in the written data in precision (0.80) compared to the speech data (0.44). Also, the rule-based classification has a low-performance overall for speech data with the precision of 0.44, recall of 0.41, and f-1 measure of 0.42. This finding implies the syntax-based model may need to be adjusted for a speech dataset because imperatives in oral communication have greater syntactic varieties and are highly context-dependent.