Children's acquisition of filler-gap dependencies has been argued by some to depend on innate grammatical knowledge, while others suggest that the distributional evidence available in child-directed speech suffices.Unfortunately, the relevant input is difficult to quantify at scale with fine granularity, making this question difficult to resolve.We present a system that identifies three core filler-gap constructions in spoken English corpora -matrix whquestions, embedded wh-questions, and relative clauses -and further identifies the extraction site (i.e., subject vs. object vs. adjunct).Our approach combines constituency and dependency parsing, leveraging their complementary strengths for construction classification and extraction site identification.We validate the system on human-annotated data and find that it scores well across most categories.Applying the system to 57 English CHILDES corpora, we are able to characterize children's fillergap input and their filler-gap production trajectories over the course of development, including construction-specific frequencies and extraction-site asymmetries.The resulting finegrained labels enable future work in both acquisition and computational studies, which we demonstrate with a case study using filtered corpus training with language models.

Deep-learning methods have been widely used as an end-to-end modeling strategy of electrical energy systems because of their convenience and powerful pattern recognition capability. However, due to the “closed-box” nature, deep-learning methods have long been blamed for their poor interpretability when modeling a physical system. In this article, we introduce a novel neural network structure, Kolmogorov–Arnold network (KAN), to achieve “glass-box” modeling for electrical energy systems to enhance the interpretability. The most distinct feature of KAN lies in the learnable activation function together with the sparse training and symbolification process. Consequently, KAN can express the physical process with concise and explicit mathematical formulae while retaining the nonlinear-fitting capability of deep neural networks. Simulation results based on three electrical energy systems demonstrate the effectiveness of KAN in the aspects of interpretability, accuracy, robustness, and generalization ability.

Human feedback in generative systems is a highly active frontier of research that aims to improve the quality of generated content and align it with subjective preferences. Existing efforts predominantly focus on text-only large language models (LLMs) or text-based image generation, while cross-modal generation between audio and text remains largely unexplored. Moreover, there is currently no open-source preference dataset to support the deployment of alignment algorithms in this domain. In this work, we take audio speech translation (AST) and audio captioning (AAC) tasks as examples to explore how to enhance the performance of mainstream audio-based text generation models with limited human annotation. Specifically, we propose an novel framework named IPO that includes a model adversarial sampling concept--human annotators act as referees to determine model outcomes, using these results as pseudo-labels for the corresponding beam search hypotheses. Given these imbalance win-loss results, IPO effectively enable the two models to update interactively to win the next round of adversarial sampling. We conduct both subjective and objective evaluations to demonstrate the alignment benefits of IPO and its enhancement on model perception and generation capacities. On both AAC and AST, a few hundreds of annotations significantly enhance the weak model, and the strong model can also be encouraged to achieve new state-of-the-art results in terms of different objective metrics. Additionally, we show the extensibility of IPO by applying it to the reverse task of text-to-speech generation, improving the robustness of system on unseen reference speaker.

We present a hierarchy of natural language understanding abilities and argue for the importance of moving beyond assessments of understanding at the lexical and sentence levels to the discourse level.We propose the task of anaphora accessibility as a diagnostic for assessing discourse understanding, and to this end, present an evaluation dataset inspired by theoretical research in dynamic semantics.We evaluate human and LLM performance on our dataset and find that LLMs and humans align on some tasks and diverge on others.Such divergence can be explained by LLMs' reliance on specific lexical items during language comprehension, in contrast to human sensitivity to structural abstractions.

Zhenghao Zhou, Robert Frank, R. Thomas McCoy. 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.

Electroencephalogram (EEG) plays a crucial role in Brain-computer interface (BCI) research by recording brain electrical activity, allowing direct communication with external devices without relying on muscles or peripheral nerves. EEG signals are non-invasive and low-cost, which are commonly used in BCIs. Although existing work has achieved success in many BCI paradigms, there is still a significant challenge: how to automatically extract spectral features from raw EEG signals. To address this, we propose a novel wavelet multi-level multi-scale neural network for EEG-based BCIs, called wavelet-MMNN. Our model uses wavelet decomposition with multi-scale convolutional kernels to automatically extract abundant spectral features from the raw EEG signals. The cross-subject experiments and cross-session experiments are conducted on SSVEP Benchmark dataset, and the results indicate that the proposed model is superior to the state-of-the-art models.