Zhihao Xu, Rumei Li, Jiahuan Li, Rongxiang Weng, Jingang Wang, Xunliang Cai, Xiting Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.

Hyperspectral imagery (HSI) provides detailed spectral information, enabling precise analysis of materials. However, HSI imaging suffers from blurring degradation which results in the loss of fine details and hinders subsequent applications. The degree of blurriness is highly related to wavelength and depth, existing deblurring methods either lack the utilization of spectral correlation or ignore the depth variation since paired HSI and depth data are difficult to acquire and less discussed, leading to degraded performance when encountering wide-range HSIs of non-planar scenes. To address these challenges in both data acquisition and algorithm design, we propose a novel approach that simultaneously collects both modalities and integrates depth refinement into a blind HSI deblurring model with wavelength- and depth-aware deep image prior. Specifically, we capture blurred HSI and coarse depth map with separate devices, followed by registration. Our method performs depth-guided deblurring through depth-variant multi-channel kernel estimation and soft-weight map-based layer composition, while simultaneously refining the depth. The proposed approach effectively restores fine details with fewer artifacts, showing superior performance for both simulated blurred HSIs and real captured HSIs.

Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks.However, pretraining data tends to contain misleading and even conflicting information, and it is intriguing to understand how LLMs handle these noisy data during training.In this study, we systematically analyze LLMs' learning preferences for data with conflicting knowledge.We find that pretrained LLMs establish learning preferences similar to humans, i.e., preferences towards formal texts and texts with fewer spelling errors, resulting in faster learning and more favorable treatment of knowledge in data with such features when facing conflicts.This finding is generalizable across models and languages and is more evident in larger models.An in-depth analysis reveals that LLMs tend to trust data with features that signify consistency with the majority of data, and it is possible to instill new preferences and erase old ones by manipulating the degree of consistency with the majority data.

Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining.However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory cross-lingual transfer and knowledge sharing.Previous works attempt to address this issue by explicitly injecting multilingual alignment information during or after pretraining.Thus for the early stage in pretraining, the alignment is weak for sharing information or knowledge across languages.In this paper, we propose PREALIGN, a framework that establishes multilingual alignment prior to language model pretraining.PREALIGN injects multilingual alignment by initializing the model to generate similar representations of aligned words and preserves this alignment using a code-switching strategy during pretraining.Extensive experiments in a synthetic English to English-Clone setting demonstrate that PREALIGN significantly outperforms standard multilingual joint training in language modeling, zero-shot crosslingual transfer, and cross-lingual knowledge application.Further experiments in real-world scenarios further validate PREALIGN's effectiveness across various languages and model sizes.

Jiahuan Li, Shanbo Cheng, Shujian Huang, Jiajun Chen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Abstract Large-scale pretrained language models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translation, without being explicitly trained on parallel corpora. It is intriguing how the LLMs obtain their ability to carry out translation instructions for different languages. In this paper, we present a detailed analysis by finetuning a multilingual pretrained language model, XGLM-7.5B, to perform multilingual translation following given instructions. Firstly, we show that multilingual LLMs have stronger translation abilities than previously demonstrated. For a certain language, the translation performance depends on its similarity to English and the amount of data used in the pretraining phase. Secondly, we find that LLMs’ ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages. With multilingual finetuning with translation instructions, LLMs could learn to perform the translation task well even for those language pairs unseen during the instruction tuning phase.

Quality estimation (QE) aims to assess the quality of machine translations when reference translations are unavailable. QE plays a crucial role in many real-world applications of machine translation. Because labeled QE data are usually limited in scale, recent research, such as DirectQE, pre-trains QE models with pseudo QE data and obtains remarkable performance. However, there tends to be inevitable noise in the pseudo data, hindering models from learning QE accurately. Our study shows that the noise mainly comes from the differences between pseudo and real translation outputs. To handle this problem, we propose CLQE, a denoising pre-training framework for QE based on curriculum learning. More specifically, we propose to measure the degree of noise in the pseudo QE data with some metrics based on statistical or distributional features. With the guidance of these metrics, CLQE gradually pre-trains the QE model using data from cleaner to noisier. Experiments on various benchmarks reveal that CLQE outperforms DirectQE and other strong baselines. We also show that with our framework, pre-training converges faster than directly using the pseudo data. We make our CLQE code available (https://github.com/NJUNLP/njuqe).

Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the predictor-estimator framework trains the predictor as a feature extractor, which leverages the extra parallel corpora without QE labels, achieving promising QE performance. However, we argue that there are gaps between the predictor and the estimator in both data quality and training objectives, which preclude QE models from benefiting from a large number of parallel corpora more directly. We propose a novel framework called DirectQE that provides a direct pretraining for QE tasks. In DirectQE, a generator is trained to produce pseudo data that is closer to the real QE data, and a detector is pretrained on these data with novel objectives that are akin to the QE task. Experiments on widely used benchmarks show that DirectQE outperforms existing methods, without using any pretraining models such as BERT. We also give extensive analyses showing how fixing the two gaps contributes to our improvements.

Definition generation, which aims to automatically generate dictionary definitions for words, has recently been proposed to assist the construction of dictionaries and help people understand unfamiliar texts.However, previous works hardly consider explicitly modeling the "components" of definitions, leading to under-specific generation results.In this paper, we propose ESD, namely Explicit Semantic Decomposition for definition generation, which explicitly decomposes meaning of words into semantic components, and models them with discrete latent variables for definition generation.Experimental results show that ESD achieves substantial improvements on WordNet and Oxford benchmarks over strong previous baselines.