The modeling of genomic sequences presents unique challenges due to their long length and structural complexity. Traditional sequence models struggle to capture long-range dependencies and biological features inherent in DNA. In this work, we propose TrinityDNA, a novel DNA foundational model designed to address these challenges. The model integrates biologically informed components, including Groove Fusion for capturing DNA's structural features and Gated Reverse Complement (GRC) to handle the inherent symmetry of DNA sequences. Additionally, we introduce a multi-scale attention mechanism that allows the model to attend to varying levels of sequence dependencies, and an evolutionary training strategy that progressively adapts the model to both prokaryotic and eukaryotic genomes. TrinityDNA provides a more accurate and efficient approach to genomic sequence modeling, offering significant improvements in gene function prediction, regulatory mechanism discovery, and other genomics applications. Our model bridges the gap between machine learning techniques and biological insights, paving the way for more effective analysis of genomic data. Additionally, we introduced a new DNA long-sequence CDS annotation benchmark to make evaluations more comprehensive and oriented toward practical applications.

The most notable neural data-to-text approaches generate natural language from structural data relying on the surface form of the structural content, which ignores the underlying logical correlation between the input data and the target text. Moreover, identifying such logical associations and explaining them in natural language is desirable but not yet studied. In this paper, we introduce a practical data-to-text method for the logic-critical scenario, specifically for anti-money laundering applications. It involves detecting risks from input data and explaining any abnormal behaviors in natural language. The proposed method is a Logic Aware Neural Generation framework (LANG), which is a preliminary attempt to explore the integration of logic modeling and text generation. Concretely, we first convert expert rules to a logic graph. Then, the model utilizes meta path based encoder to exploit the expert knowledge. Besides, a retriever module with the encoded logic knowledge is used to bridge the gap between numeric input and target text. Finally, a rule-constrained loss is leveraged to improve the generation probability of tokens in rule recalled statements to ensure accuracy. We conduct extensive experiments on anti-money laundering data. Results show that the proposed method significantly outperforms baselines in both objective measures with relative 35% improvements in F1 score and subjective measures with 30% improvement in human preference.

Linlin Chao, Jianshan He, Taifeng Wang, Wei Chu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Human emotion is a temporally dynamic event which can be inferred from both audio and video feature sequences. In this paper we investigate the long short term memory recurrent neural network (LSTM-RNN) based encoding method for category emotion recognition in the video. LSTM-RNN is able to incorporate knowledge about how emotion evolves over long range successive frames and emotion clues from isolated frame. After encoding, each video clip can be represented by a vector for each input feature sequence. The vectors contain both frame level and sequence level emotion information. These vectors are then concatenated and fed into support vector machine (SVM) to get the final prediction result. Extensive evaluations on Emotion Challenge in the Wild (EmotiW2015) dataset show the efficiency of the proposed encoding method and competitive results are obtained. The final recognition accuracy achieves 46.38% for audio-video emotion recognition sub-challenge, where the challenge baseline is 39.33%.

Depression is a typical mood disorder, which affects people in mental and even physical problems. People who suffer depression always behave abnormal in visual behavior and the voice. In this paper, an audio visual based multimodal depression scale prediction system is proposed. Firstly, features are extracted from video and audio are fused in feature level to represent the audio visual behavior. Secondly, long short memory recurrent neural network (LSTM-RNN) is utilized to encode the dynamic temporal information of the abnormal audio visual behavior. Thirdly, emotion information is utilized by multi-task learning to boost the performance further. The proposed approach is evaluated on the Audio-Visual Emotion Challenge (AVEC2014) dataset. Experiments results show the dimensional emotion recognition helps to depression scale prediction.

The earliest research on emotion recognition starts with simulated/acted stereotypical emotional corpus, and then extends to elicited corpus. Recently, the demanding for real application forces the research shift to natural and spontaneous corpus. Previous research shows that accuracies of emotion recognition are gradual decline from simulated speech, to elicited and totally natural speech. This paper aims to investigate the effects of the common utilized spectral, prosody and voice quality features in emotion recognition with the three types of corpus, and finds out the robust feature for emotion recognition with natural speech. Emotion recognition by several common machine learning methods are carried out and thoroughly compared. Three feature selection methods are performed to find the robust features. The results on six common used corpora confirm that recognition accuracies decrease when the corpus changing from simulated to natural corpus. In addition, prosody and voice quality features are robust for emotion recognition on simulated corpus, while spectral feature is robust in elicited and natural corpus.

In real life, the affective state of human beings changes gradually and smoothly. There is a high probability that the affective state of a certain moment depends on the states of a previous period. In this study, we propose to explicitly model the temporal relationship using a Bayesian inference based two-stage classification approach. This approach could involve knowledge about the dynamics of affective states during a period, so that the inferred affective states are predicted by considering a certain amount of context. Evaluations on the Audio Sub-Challenge of the 2011 Audio/Visual Emotion Challenge show our approach obtains competitive results to those of Audio Sub-Challenge winners. The temporal context modeling method proposed in this paper is also helpful for other sequential pattern recognition problems.