Search

Aspect Sentiment Triplet Extraction (ASTE) aims to co-extract the sentiment triplets in a given corpus. Existing approaches within the pretraining-finetuning paradigm tend to either meticulously craft complex tagging schemes and classification heads, or incorporate external semantic augmentation to enhance performance. In this study, we, for the first time, re-evaluate the redundancy in tagging schemes and the internal enhancement in pretrained representations. We propose a method to improve and utilize pretrained representations by integrating a minimalist tagging scheme and a novel token-level contrastive learning strategy. The proposed approach demonstrates comparable or superior performance compared to state-of-the-art techniques while featuring a more compact design and reduced computational overhead. Additionally, we are the first to formally evaluate GPT-4's performance in few-shot learning and Chain-of-Thought scenarios for this task. The results demonstrate that the pretraining-finetuning paradigm remains highly effective even in the era of large language models., Comment: arXiv admin note: text overlap with arXiv:2403.07342

Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair their ability to handle distribution shifts. In real-world scenarios, machine learning systems inevitably encounter both covariate shifts (e.g., changes in image styles) and semantic shifts (e.g., test-time unseen classes). This highlights the importance of enhancing out-of-distribution (OOD) generalization on covariate shifts and simultaneously detecting semantic-shifted unseen classes. Thus a critical but underexplored question arises: How to improve VL-PTMs' generalization ability to closed-set OOD data, while effectively detecting open-set unseen classes during fine-tuning? In this paper, we propose a novel objective function of OOD detection that also serves to improve OOD generalization. We show that minimizing the gradient magnitude of energy scores on training data leads to domain-consistent Hessians of classification loss, a strong indicator for OOD generalization revealed by theoretical analysis. Based on this finding, we have developed a unified fine-tuning framework that allows for concurrent optimization of both tasks. Extensive experiments have demonstrated the superiority of our method. The code is available at https://github.com/LinLLLL/CRoFT., Comment: Accepted by ICML2024

Aspect Sentiment Triplet Extraction (ASTE) is a burgeoning subtask of fine-grained sentiment analysis, aiming to extract structured sentiment triplets from unstructured textual data. Existing approaches to ASTE often complicate the task with additional structures or external data. In this research, we propose a novel tagging scheme and employ a contrastive learning approach to mitigate these challenges. The proposed approach demonstrates comparable or superior performance in comparison to state-of-the-art techniques, while featuring a more compact design and reduced computational overhead. Notably, even in the era of Large Language Models (LLMs), our method exhibits superior efficacy compared to GPT 3.5 and GPT 4 in a few-shot learning scenarios. This study also provides valuable insights for the advancement of ASTE techniques within the paradigm of large language models.

Out-of-distribution (OOD) generalization has long been a challenging problem that remains largely unsolved. Gaussian processes (GP), as popular probabilistic model classes, especially in the small data regime, presume strong OOD generalization abilities. Surprisingly, their OOD generalization abilities have been under-explored before compared with other lines of GP research. In this paper, we identify that GP is not free from the problem and propose a domain invariant learning algorithm for Gaussian processes (DIL-GP) with a min-max optimization on the likelihood. DIL-GP discovers the heterogeneity in the data and forces invariance across partitioned subsets of data. We further extend the DIL-GP to improve Bayesian optimization's adaptability on changing environments. Numerical experiments demonstrate the superiority of DIL-GP for predictions on several synthetic and real-world datasets. We further demonstrate the effectiveness of the DIL-GP Bayesian optimization method on a PID parameters tuning experiment for a quadrotor. The full version and source code are available at: https://github.com/Billzxl/DIL-GP., Comment: Accepted to The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

Spin triplet exciton formation sets limits on technologies using organic semiconductors that are confined to singlet-triplet photophysics. In contrast, excitations in the spin doublet manifold in organic radical semiconductors can show efficient luminescence. Here we explore the dynamics of the spin allowed process of intermolecular energy transfer from triplet to doublet excitons. We employ a carbene-metal-amide (CMA-CF3) as a model triplet donor host, since following photoexcitation it undergoes extremely fast intersystem crossing to set up a population of triplet excitons within 4 ps. This enables a foundational study for tracking energy transfer from triplets to a model radical semiconductor, TTM-3PCz. Over 90% of all radical luminescence originates from the triplet channel in this system under photoexcitation. We find that intermolecular triplet-to-doublet energy transfer can occur directly and rapidly, with 12% of triplet excitons transferring already on sub-ns timescales. This enhanced triplet harvesting mechanism is utilised in efficient near-infrared organic light-emitting diodes, which can be extended to other opto-electronic and -spintronic technologies by radical-based spin control in molecular semiconductors.

Organic light-emitting diodes (OLEDs) must be engineered to circumvent the efficiency limit imposed by the 3:1 ratio of triplet to singlet exciton formation following electron-hole capture. Here we show the spin nature of luminescent radicals such as TTM-3PCz allows direct energy harvesting from both singlet and triplet excitons through energy transfer, with subsequent rapid and efficient light emission from the doublet excitons. This is demonstrated with a model Thermally-Activated Delayed Fluorescence (TADF) organic semiconductor, 4CzIPN, where reverse intersystem crossing from triplets is characteristically slow (50% emission by 1 microsecond). The radical:TADF combination shows much faster emission via the doublet channel (80% emission by 100 ns) than the comparable TADF-only system, and sustains higher electroluminescent efficiency with increasing current density than a radical-only device. By unlocking energy transfer channels between singlet, triplet and doublet excitons, further technology opportunities are enabled for optoelectronics using organic radicals., Comment: 35 pages, 4 figures in main text and 11 figures in Supplementary Information

Bulk-heterojunction (BHJ) non-fullerene organic solar cells prepared from sequentially deposited donor and acceptor layers (sq-BHJ) have recently been promising to be highly efficient, environmentally friendly, and compatible with large area and roll-to-toll fabrication. However, the related photophysics at donor-acceptor interface and the vertical heterogeneity of donor-acceptor distribution, critical for exciton dissociation and device performance, are largely unexplored. Herein, steady-state and time-resolved optical and electrical techniques are employed to characterize the interfacial trap states. Correlation with the luminescent efficiency of interfacial states and its non-radiative recombination, interfacial trap states are characterized to be about 50% more populated in the sq-BHJ than as-cast BHJ (c-BHJ), which probably limits the device voltage output. Cross-sectional energy-dispersive X-ray spectroscopy and ultraviolet photoemission spectroscopy depth profiling directly vizualize the donor-acceptor vertical stratification with a precision of 1-2 nm. From the proposed "needle" model, the high exciton dissociation efficiency is rationalized. Our study highlights the promise of sequential deposition to fabricate efficient solar cells, and points towards improving the voltage output and overall device performance via eliminating interfacial trap states.