Existing Large Language Models (LLMs) enforce uniform computation across all tokens. We analyze the correlation between the input-output difference of self-attention block and Feed-Forward Network (FFN) within the same transformer layer, and find that these two differential vectors are highly correlated. Thus, we propose to dynamically skip the FFN blocks based on the self-attention difference and introduce Diffential Layer Skipping (DiffSkip) to show that LLMs are inherently dynamic-depth models, capable of adjusting computational depth when generating different tokens. DiffSkip employs a lightweight router module to dynamically skip a set of FFN blocks in LLMs and only requires efficient fine-tuning while keeping the whole LLM frozen. Experimental results demonstrate that DiffSkip effectively enables dynamic FFN skipping in decoder-only language models, even in continuous token generation tasks where many layer-skipping methods struggle.

The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters. However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet data is scarce or nonexistent. In this paper, we propose a novel non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems. To this end, we first incorporate an additional encoder into the pre-trained E2E-ST model to realize text translation modeling, based on which the decoder’s output representations for text and speech translation tasks are unified by reducing the correspondent representation mismatch in available triplet training data. During domain adaptation, a k-nearest-neighbor (kNN) classifier is introduced to produce the final translation distribution using the external datastore built by the domain-specific text translation corpus, while the universal output representation is adopted to perform a similarity search. Experiments on the Europarl-ST benchmark demonstrate that when in-domain text translation data is involved only, our proposed approach significantly improves baseline by 12.82 BLEU on average in all translation directions, even outperforming the strong in-domain fine-tuning strategy.

Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.

Two challenging issues are notable in tweet clustering. Firstly, the sparse data problem is serious since no tweet can be longer than 140 characters. Secondly, synonymy and polysemy are rather common because users intend to present a unique meaning with a great number of manners in tweets. Enlightened by the recent research which indicates Wikipedia is promising in representing text, we exploit Wikipedia concepts in representing tweets with concept vectors. We address the polysemy issue with a Bayesian model, and the synonymy issue by exploiting the Wikipedia redirections. To further alleviate the sparse data problem, we further make use of three types of out-links in Wikipedia. Evaluation on a twitter dataset shows that the concept model outperforms the traditional VSM model in tweet clustering.