Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their contexts. Recently, graph neural network has been investigated for integrating dependency syntax for the task, achieving the state-of-the-art results. However, existing methods do not consider dependency label information, which can be intuitively useful. To solve the problem, we investigate a novel relational graph attention network that integrates typed syntactic dependency information. Results on standard benchmarks show that our method can effectively leverage label information for improving targeted sentiment classification performances. Our final model significantly outperforms state-of-the-art syntax-based approaches.

The recent surge in versatile large language models (LLMs) demonstrates remarkable success across a wide range of contexts. A key factor contributing to this success is LLM alignment, in which human preference learning plays a decisive role in steering the models’ capabilities toward fulfilling human objectives. In this survey, we review the progress in human preference learning within a unified framework, aiming to provide a comprehensive perspective on established methodologies while exploring avenues to further advance LLM alignment. Specifically, we categorize human preference feedback based on data sources and formats, summarize techniques for human preference modeling and usage, and present an overview of prevailing evaluation protocols for LLM alignment. Finally, we discuss the existing challenges and identify potential directions for future research, with a particular emphasis on generalizability, transferability, and controllability.

Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao, Min Zhang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2024.

Constituency parsing is a fundamental yet unsolved challenge in natural language processing. In this paper, we examine the potential of recent large language models (LLMs) to address this challenge. We reformat constituency parsing as a sequence-to-sequence generation problem and evaluate the performance of a diverse range of LLMs under zero-shot, few-shot, and supervised fine-tuning learning paradigms. We observe that while LLMs achieve acceptable improvements, they still encounter substantial limitations, due to the absence of mechanisms to guarantee the validity and faithfulness of the generated constituent trees. Motivated by this observation, we propose two strategies to guide LLMs to generate more accurate constituent trees by learning from erroneous samples and refining outputs in a multi-agent collaboration way, respectively. The experimental results demonstrate that our methods effectively reduce the occurrence of invalid and unfaithful trees, thereby enhancing overall parsing performance and achieving promising results across different learning paradigms.

Transient stability constrained optimal power flow (TSCOPF) is increasingly important as many modern power systems nowadays have been forced to operate close to their stability limits. In this study, a non‐convex mixed integer non‐linear program (MINLP) TSCOPF model with consideration of valve‐point effects and discrete control variables is first presented, in which the energy‐based transient angle and voltage constraints are simultaneously considered as an integrated stability control process. The proposed model is general and flexible with support for any complex dynamic components, including detailed generator model and flexible AC transmission system (FACTS) devices, valve‐point effects and discrete control variables. An enhanced particle swarm optimisation with dynamic adjusted inertia weight and shrinking Gaussian distribution disturbance is then proposed to solve this challenging MINLP‐TSCOPF problem with comprehensive testing and evaluation using a benchmarking MINLP mathematical function and two representative power systems with FACTS devices.

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang. Findings of the Association for Computational Linguistics ACL 2024. 2024.