In recent years, large language models (LLMs) based on the Transformer architecture have demonstrated excellent performance in code generation, but there have been fewer studies on data flow languages. This study proposes a scheme for fine-tuning large language models based on the DFCPP dataset. We demonstrate the model's ability to generate dataflow graph (DAG) topologies and achieve significant performance improvements. Experimental results show that the BLEU score of the fine-tuned model in the DFCPP code generation task reaches 0.193, which is an increase of 112.1% compared to the non-fine-tuned model (0.091). This demonstrates the effectiveness of fine-tuning techniques in domain-specific code generation.

Speech emotion recognition (SER) is a fundamental step towards fluent human-machine interaction. One challenging problem in SER is obtaining utterance-level feature representation for classification. Recent works on SER have made significant progress by using spectrogram features and introducing neural network methods, e.g., convolutional neural networks (CNNs). However the fundamental problem of CNNs is that the spatial information in spectrograms is not captured, which are basically position and relationship information of low-level features like pitch and formant frequencies. This paper presents a novel architecture based on the capsule networks (CapsNets) for SER. The proposed system can take into account the spatial relationship of speech features in spectrograms, and provide an effective pooling method for obtaining utterance global features. We also introduce a recurrent connection to CapsNets to improve the model's time sensitivity. We compare the proposed model to previous published results based on combined CNN-long short-term memory (CNN-LSTM) models on the benchmark corpus IEMOCAP over four emotions, i.e., neutral, angry, happy and sad. Experimental results show that our model achieves better results than the baseline system on weighted accuracy (WA) (72.73% vs. 68.8%) and un-weighted accuracy (UA) (59.71% vs. 59.4%), which demonstrates the effectiveness of CapsNets for SER.

The popular n-gram language model (LM) is weak for unfrequent words. Conventional approaches such as class-based LMs pre-define some sharing structures (e.g., word classes) to solve the problem. However, defining such structures requires prior knowledge, and the context sharing based on these structures is generally inaccurate. This paper presents a novel similar word model to enhance unfrequent words. In principle, we enrich the context of an unfrequent word by borrowing context information from some “similar words.” Compared to conventional class-based methods, this new approach offers a fine-grained context sharing by referring to words that best match the target word, and it is more flexible as no sharing structures need to be defined by hand. Experiments on a large-scale Chinese speech recognition task demonstrated that the similar word approach can improve performance on unfrequent words significantly, while keeping the performance on general tasks almost unchanged.

Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally underestimated by the language model (LM) due to their limited occurrences in the training data. Recently, we proposed a wordpair approach to deal with the problem, which borrows information of frequent words to enhance the probabilities of lowfrequency words. This paper presents an extension to the wordpair method by involving multiple ‘predicting words’ to produce better estimation for low-frequency words. We also employ this approach to deal with out-of-language words in the task of multi-lingual speech recognition.

MOTIVATION: Copy number abbreviation (CNA) is one type of genomic aberration that is often induced by genome instability and is associated with diseases such as cancer. Determination of the genome-wide CNA profile is an important step in identifying the underlying mutation mechanisms. Genomic data based on next-generation sequencing technology are particularly suitable for determination of high-quality CNA profile. Now is an important time to reevaluate the use of sequencing techniques for CNA analysis, especially with the rapid growth of the different targeted genome and whole-genome sequencing strategies. RESULTS: In this study, we provide a comparison of resequencing strategies, with regard to their utility, applied to the same hepatocellular carcinoma sample for copy number determination. These strategies include whole-genome, exome and restriction site-associated DNA (RAD) sequencing. The last of these strategies is a targeted sequencing technique that involves cutting the genome with a restriction enzyme and isolating the targeted sequences. Our data demonstrate that RAD sequencing is an efficient and comprehensive strategy that allows the cost-effective determination of CNAs. Further investigation of RAD sequencing data led to the finding that a precise measurement of the allele frequency would be a helpful complement to the read depth for CNA analysis for two reasons. First, knowledge of the allele frequency helps to resolve refined calculations of allele-specific copy numbers, which, in turn, identify the functionally important CNAs that are under natural selection on the parental alleles. Second, this knowledge enables deconvolution of CNA patterns in complex genomic regions.

Single nucleotide polymorphisms (SNPs) are loci on the genome where different alleles are observed in the population. It has been observed that there might be some patterns or context dependences in the sequence segments adjacent to SNPs sites. Discovering such dependences is very important for understanding possible origins of SNPs in evolution. We collected 519,767 bi-allelic SNPs of human in gene regions from HGBASE and separated them in 6 groups according to the types of alleles at the SNP loci. Bayesian network structure learning technique is applied to discovery of possible dependences in sequence segments around these sites as well as in reference sequences collected as comparison. Noticeable probabilistic correlations among some loci were detected in all the 6 SNP groups and nothing significant was found in the reference sequences. The dependence relations found with different SNP groups are different. These putative context dependences around SNP sites provide important hints for further analyzing SNP-related sequences patterns. The work also illustrates the powerfulness of the Bayesian network method as a tool for biological sequence analysis.

Recurrent combinations of events within an event sequence, known as episodes, often reveal useful information. Most of the proposed episode mining algorithms adopt an apriori-like approach that generates candidates and then calculates their support levels. Obviously, such an approach is computationally expensive. Moreover, those algorithms are capable of handling only a limited range of constraints. In this paper, we introduce two mining algorithms - episode prefix tree (EPT) and position pairs set (PPS) - based on a prefix-growth approach to overcome the above limitations. Both algorithms push constraints systematically into the mining process. Performance study shows that the proposed algorithms run considerably faster than MINEPI (Mannila and Toivonen, 1996).