China

We introduce and explore the concept of potentially problematic word usages (PPWUs): word occurrences that are likely to cause communication breakdowns of a semantic nature. While much research has been devoted to lexical complexity, ambiguity, vagueness and related issues, no work has attempted to fully capture the intricate nature of PPWUs. We review linguistic factors, datasets and metrics that can be helpful for PPWU detection. We also discuss challenges to their study, such as their complexity and subjectivity, and highlight the need for future work on this phenomenon.

EMNLP 2025

Potentially Problematic Word Usages and How to Detect Them: A Survey

lexical relationships

lexical semantic change

polysemy

metaphor

text simplification

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

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." 

*Message from the General Chair, Dirk Hovy*

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

While supervised relation extraction (RE) models have considerably advanced the state-of-the-art, they often perform poorly in low-resource settings. Zero-shot RE is vital when annotations are not available either due to costs or time constraints. As a result, zero-shot RE has garnered interest in the research community. With the advent of large language models (LLMs) many approaches have been proposed for prompting LLMs for RE, but these methods often either rely on an accompanying small language model (e.g., for finetuning on synthetic data generated by LLMs) or require complex post-prompt processing. In this paper, we propose an effective prompt-based method that does not require any additional resources. Instead, we use an LLM to perform a two-step process. In the first step, we perform a targeted summarization of the text with respect to the underlying relation, reduce the applicable label space, and synthesize examples. Then, we combine the products of these processes with other elements into a final prompt. We evaluate our approach with various LLMs on four real-world RE datasets. Our evaluation shows that our method outperforms the previous state-of-the-art zero-shot methods by a large margin. This work can also be considered as a new strong baseline for zero-shot RE that is compatible with any LLM.

Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors

Retrieval-Augmented Generation (RAG) systems rely on high-quality embeddings to retrieve relevant context for large language models. This paper introduces the Semantic-Augmented Graph (SAG), a new architecture that improves domain-specific embeddings by capturing hierarchical semantic relationships between text segments. Inspired by human information processing, SAG organizes content from general to specific concepts using a graph-based structure. By combining static embeddings with dynamic semantic graphs, it generates context-aware representations that reflect both lexical and conceptual links. Experiments on text similarity and domain-specific question answering show that SAG consistently outperforms standard embedding methods within RAG pipelines.

SAG: Enhancing Domain-Specific Information Retrieval with Semantic-Augmented Graphs

Speech Emotion Recognition (SER) is essential for improving human-computer interaction, yet its accuracy remains constrained by the complexity of emotional nuances in speech. In this study, we distinguish between $descriptive\ semantics$, which represents the contextual content of speech, and $expressive\ semantics$, which reflects the speaker's emotional state. After watching emotionally charged movie segments, we recorded audio clips of participants describing their experiences, along with the intended emotion tags for each clip, participants' self-rated emotional responses, and their valence/arousal scores. Through experiments we show that descriptive semantics align with intended emotions, while expressive semantics correlate with evoked emotions. Our findings inform SER applications in human-AI interaction and pave the way for more context-aware AI systems.

Semantic Differentiation in Speech Emotion Recognition: Insights from Descriptive and Expressive Speech Roles

Semantic prosody is a collocational meaning formed through the co-occurrence of a linguistic unit and a consistent series of collocates, which should be treated separately from semantic meaning. Since words that are literal translation of each other may have different semantic prosody, more attention should be paid to this linguistic property in order to generate accurate translation. However, current machine translation models cannot handle this problem. To bridge the gap, we propose an approach to teach machine translation models about semantic prosody of a specific structure. We focus on Chinese BEI passives and create a dataset of English-Chinese sentence pairs with the purpose of demonstrating the negative semantic prosody of BEI passives. Then we fine-tune OPUS-MT, NLLB-600M and mBART50-mmt models with our dataset for the English-Chinese translation task. Our results show that fine-tuned MT models perform better on using BEI passives for translating unfavourable content and avoid using it for neutral and favourable content. Also, in NLLB-600M, which is a multilingual model, this knowledge of semantic prosody can be transferred from English-Chinese translation to other language pairs, such as Spanish-Chinese.

Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures

Large language models (LLMs) excel at general language tasks but often struggle with event-based questions—especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by ~5% on average over text-only baselines, with gains up to ~12% in zero-shot settings and ~18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.

TAG–EQA: Text–And–Graph for Event Question Answering via Structured Prompting Strategies

Large language models have demonstrated varying levels of competence across a range of reasoning tasks, but coarse-grained evaluations often do not reflect their specific strengths and weaknesses, particularly in complex tasks such as Narrative Question Answering. In this paper, we advocate for a multi-dimensional skill-based evaluation that assesses models across distinct core skill dimensions. Our proposed skill-focused evaluation framework offers a granular and more realistic measure of model performance, revealing targeted areas for improvement and guiding future development. Experiments on Narrative Question Answering demonstrate that dimension-level analysis captures the multifaceted nature of the task and informs more effective model evaluation.

Towards Evaluation of Language Models with Skill Dimensions: A Case Study on Narrative Question Answering

This work explores the impact of dataset quality and composition on Word-in-Context performance for Galician and Spanish. We assess existing datasets, validate their test sets, and create new manually constructed evaluation data. Across five experiments with controlled variations in training and test data, we find that while the validation of test data tends to yield better model performance, evaluations on manually created datasets suggest that contextual embeddings are not sufficient on their own to reliably capture word meaning variation. Regarding training data, our results suggest that performance is influenced not only by size and human validation but also by deeper factors related to the semantic properties of the datasets. All new resources will be freely released.

WiC Evaluation in Galician and Spanish: Effects of Dataset Quality and Composition

The GENDER1PERSON test suite is designed
to measure gender bias in translating singular
first-person forms from English into two Slavic
languages, Russian and Serbian. The test suite
consists of 1 000 Amazon product reviews, uni-
formly distributed over 10 different product
categories. Bias is measured through a gen-
der score ranging from -100 (all reviews are
feminine) to 100 (all reviews are masculine).
The test suite shows that the majority of the
systems participating in the WMT-2025 task
for these two target languages prefer the mas-
culine writer’s gender. There is no single sys-
tem which is biased towards the feminine vari-
ant. Furthermore, for each language pair, there
are seven systems that are considered balanced,
having the gender scores between -10 and 10.
Finally, the analysis of different products
showed that the choice of the writer’s gender
depends to a large extent on the product. More-
over, it is demonstrated that even the systems
with overall balanced scores are actually bi-
ased, but in different ways for different product
categories.

GENDER1PERSON: Test Suite for estimating gender bias of first-person singular forms

We analyze how English–Russian machine translation (MT) systems submitted to WMT25 perform on linguistically challenging translation tasks, similar to problems used in university professional translator training. 
We assessed the ten top-performing systems using a fine-grained test suite containing 465 manually devised test items, which cover 55 lexical, grammatical, and discourse phenomena, in 13 categories. 
By applying pass/fail rules with human adjudication and micro/macro aggregates, we observe three performance tiers. Compared with the official WMT25 ranking, our ranking broadly aligns but reveals notable shifts.

Our findings show that in 2025, even top-performing MT systems still struggle with translation problems that require deep understanding and rephrasing, much like human novices do. The best systems exhibit creativity and can be very good at handling such challenges, often producing more natural translations rather than producing word-for-word renditions. However, persistent structural and lexical problems remain: literal word order carry-overs, misused verb forms, and rigid phrase translations were common, mirroring errors typically seen in beginner translator assignments.

Fine-Grained Evaluation of English-Russian MT in 2025: Linguistic Challenges Mirroring Human Translator Training

This paper presents PediaMind-R1, a domain-specialized large language model designed to achieve active personalization in intelligent parenting scenarios. Unlike conventional systems that provide generic suggestions, PediaMind-R1 draws on insights from developmental psychology. It introduces temperament theory from the Thomas–Chess framework and builds a temperament knowledge graph for infants and toddlers (0–3 years). Our two-stage training pipeline first uses supervised fine-tuning to teach structured chain-of-thought reasoning, and then applies a GRPO-based alignment stage to reinforce logical consistency, domain expertise, and empathetic caregiving strategies. We further design an evaluation framework comprising temperament-sensitive multiple-choice tests and human assessments. The results demonstrate that PediaMind-R1 can accurately interpret early childhood temperament profiles and proactively engage in individualized reasoning. This work highlights the value of integrating vertical-domain modeling with psychological theory. It offers a novel approach to developing user-centered LLMs that advance the practice of active personalization in sensitive caregiving contexts.

Downloads

Next from EMNLP 2025

Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors

Similar lecture

Complexity and Indecision: A Proof-of-Concept Exploration of Lexical Complexity and Lexical Semantic Change

.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

Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors

Similar lecture

Complexity and Indecision: A Proof-of-Concept Exploration of Lexical Complexity and Lexical Semantic Change

Downloads