Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, Weihuang, Yining Wang, Junnan Zhu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Donglei Yu, Xiaomian Kang, Yuchen Liu, Feifei Zhai, Nanchang Cheng, Yu Zhou, Chengqing Zong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a decision path.Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations.These methods not only fail to precisely optimize the policy due to the inability to accurately assess the individual impact of each decision on SiMT performance, but also cannot sufficiently explore all potential paths because of their vast number.Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models.To solve these issues, we propose Self-Modifying State Modeling (SM 2 ), a novel training paradigm for SiMT task.Without building decision paths, SM 2 individually optimizes decisions at each state during training.To precisely optimize the policy, SM 2 introduces Self-Modifying process to independently assess and adjust decisions at each state.For sufficient exploration, SM 2 proposes Prefix Sampling to efficiently traverse all potential states.Moreover, SM 2 ensures compatibility with bidirectional encoders, thus achieving higher translation quality.Experiments show that SM 2 outperforms strong baselines.Furthermore, SM 2 allows offline machine translation models to acquire SiMT ability with fine-tuning 1 .

Previous methods incorporating knowledge graphs (KGs) into neural machine translation (NMT) adopt a static knowledge utilization strategy, that introduces many useless knowledge triples and makes the useful triples difficult to be utilized by NMT. To address this problem, we propose a KG guided NMT model with dynamic reinforce-selected triples. The proposed methods could dynamically select the different useful knowledge triples for different source sentences. Specifically, the proposed model contains two components: (1) knowledge selector, that dynamically selects useful knowledge triples for a source sentence, and (2) knowledge guided NMT (KgNMT), that utilizes the selected triples to guide the translation of NMT. Meanwhile, to overcome the non-differentiable problem and guide the training procedure, we propose a policy gradient strategy to encourage the model to select useful triples and improve the generation probability of gold target sentence. Various experimental results show that the proposed method can significantly outperform the baseline models in both translation quality and handling the entities.

Document-level neural machine translation (DocNMT) has yielded attractive improvements. In this article, we systematically analyze the discourse phenomena in Chinese-to-English translation, and focus on the most obvious ones, namely lexical translation consistency. To alleviate the lexical inconsistency, we propose an effective approach that is aware of the words which need to be translated consistently and constrains the model to produce more consistent translations. Specifically, we first introduce a global context extractor to extract the document context and consistency context, respectively. Then, the two types of global context are integrated into a encoder enhancer and a decoder enhancer to improve the lexical translation consistency. We create a test set to evaluate the lexical consistency automatically. Experiments demonstrate that our approach can significantly alleviate the lexical translation inconsistency. In addition, our approach can also substantially improve the translation quality compared to sentence-level Transformer.

This paper describes a generative model for extracting medical terms and their status from Chinese medical dialogues. Notably, the extracted semantic information plays an essential role in downstream tasks such as automatic medical scribe and automatic diagnosis system. However, how to effectively leverage dialogue context to generate medical terms and their corresponding status accurately remains less explored. Existing generative methods treat dialogue text as concentrated long text without considering the characteristics of conversation, such as colloquialism, redundancy, interactions, etc. Various colloquial medical information is frequently discussed between doctor and patient. Each of the speakers (doctor and patient) plays a specific role in the goals of interaction. Thus the role information and interactions between utterances are vital. Besides, current generative methods only utilize character-level tokens ignoring the word-level tokens, which is the smallest meaningful utterance in Chinese. In this paper, we propose a Multi-granularity Transformer (MGT) model to enhance the dialogue context understanding from multi-granularity features. We introduce word-level information by adapting a Lattice-based encoder with our proposed relative position encoding method. We further introduce utterance-level interaction information by proposing a Role Access Controlled Attention (RaCa) mechanism. Experimental results on two benchmark datasets illustrate our model's validity and effectiveness, achieving state-of-the-art performance on both datasets.

Document-level neural machine translation has yielded attractive improvements.However, majority of existing methods roughly use all context sentences in a fixed scope.They neglect the fact that different source sentences need different sizes of context.To address this problem, we propose an effective approach to select dynamic context so that the document-level translation model can utilize the more useful selected context sentences to produce better translations.Specifically, we introduce a selection module that is independent of the translation module to score each candidate context sentence.Then, we propose two strategies to explicitly select a variable number of context sentences and feed them into the translation module.We train the two modules end-to-end via reinforcement learning.A novel reward is proposed to encourage the selection and utilization of dynamic context sentences.Experiments demonstrate that our approach can select adaptive context sentences for different source sentences, and significantly improves the performance of document-level translation methods.

Deep neural networks (DNNs) have provably enhanced the state-of-the-art natural language process (NLP) with their capability of feature learning and representation. As one of the more challenging NLP tasks, neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy and word coverage. It is therefore a promising direction to combine the advantages of both NMT and SMT. In this article, we propose a deep neural network--based system combination framework leveraging both minimum Bayes-risk decoding and multi-source NMT, which take as input the N-best outputs of NMT and SMT systems and produce the final translation. In particular, we apply the proposed model to both RNN and self-attention networks with different segmentation granularity. We verify our approach empirically through a series of experiments on resource-rich Chinese⇒English and low-resource English⇒Vietnamese translation tasks. Experimental results demonstrate the effectiveness and universality of our proposed approach, which significantly outperforms the conventional system combination methods and the best individual system output.

A key element in computational discourse analysis is the design of a formal representation for the discourse structure of a text. With machine learning being the dominant method, it is important to identify a discourse representation that can be used to perform large-scale annotation. This survey provides a systematic analysis of existing discourse representation theories to evaluate whether they are suitable for annotation of Chinese text. Specifically, the two properties, expressiveness and practicality, are introduced to compare the representations of theories based on rhetorical relations and the representations of theories based on entity relations. The comparison systematically reveals linguistic and computational characteristics of the theories. After that, we conclude that none of the existing theories are quite suitable for scalable Chinese discourse annotation because they are not both expressive and practical. Therefore, a new discourse representation needs to be proposed, which should balance the expressiveness and practicality, and cover rhetorical relations and entity relations. Inspired by the conclusions, this survey discusses some preliminary proposals on how to represent the discourse structure that are worth pursuing.

Document-level sentiment classification aims to predict a user’s sentiment polarity in a document about a product. Most existing methods only focus on review contents and ignore users who post reviews. In fact, when reviewing a product, different users have different word-using habits to express opinions (i.e., word-level user preference), care about different attributes of the product (i.e., aspect-level user preference), and have different characteristics to score the review (i.e., polarity-level user preference). These preferences have great influence on interpreting the sentiment of text. To address this issue, we propose a model called Hierarchical User Attention Network (HUAN), which incorporates multi-level user preference into a hierarchical neural network to perform document-level sentiment classification. Specifically, HUAN encodes different kinds of information (word, sentence, aspect, and document) in a hierarchical structure and imports user embedding and user attention mechanism to model these preferences. Empirical results on two real-world datasets show that HUAN achieves state-of-the-art performance. Furthermore, HUAN can also mine important attributes of products for different users.