Loss spikes, a phenomenon in which the loss value diverges suddenly, is a fundamental issue in the pre-training of large language models. This paper supposes that the non-uniformity of the norm of the parameters is one of the causes of loss spikes. Here, in training of neural networks, the scale of the gradients is required to be kept constant throughout the layers to avoid the vanishing and exploding gradients problem. However, to meet these requirements in the Transformer model, the norm of the model parameters must be non-uniform, and thus, parameters whose norm is smaller are more sensitive to the parameter update. To address this issue, we propose a novel technique, weight scaling as reparameterization (WeSaR). WeSaR introduces a gate parameter per parameter matrix and adjusts it to the value satisfying the requirements. Because of the gate parameter, WeSaR sets the norm of the original parameters uniformly, which results in stable training. Experimental results with the Transformer decoders consisting of 130 million, 1.3 billion, and 13 billion parameters showed that WeSaR stabilizes and accelerates training and that it outperformed compared methods including popular initialization methods.

This paper presents DueT, a novel transfer learning method for vision and language models built by contrastive learning. In DueT, adapters are inserted into the image and text encoders, which have been initialized using models pre-trained on uni-modal corpora and then frozen. By training only these adapters, DueT enables efficient learning with a reduced number of trainable parameters. Moreover, unlike traditional adapters, those in DueT are equipped with a gating mechanism, enabling effective transfer and connection of knowledge acquired from pre-trained uni-modal encoders while preventing catastrophic forgetting. We report that DueT outperformed simple fine-tuning, the conventional method fixing only the image encoder and training only the text encoder, and the LoRA-based adapter method in accuracy and parameter efficiency for 0-shot image and text retrieval in both English and Japanese domains.

Argumentative dialogue is an important process where speakers discuss a specific theme for consensus building or decision making. In previous studies for generating consistent argumentative dialogue, retrieval-based methods with hand-crafted argumentation structures have been used. In this study, we propose a method to generate natural argumentative dialogues by combining an argumentation structure and language model. We trained the language model to rewrite a proposition of an argumentation structure on the basis of its information, such as keywords and stance, into the next utterance while considering its context, and we used the model to rewrite propositions in the argumentation structure. We manually evaluated the generated dialogues and found that the proposed method significantly improved the naturalness of dialogues without losing consistency of argumentation.

Social media texts, such as tweets from Twitter, contain many types of non-standard tokens, and the number of normalization approaches for handling such noisy text has been increasing. We present a method for automatically extracting pairs of a variant word and its normal form from unsegmented text on the basis of a pair-wise similarity approach. We incorporated the acquired variant-normalization pairs into Japanese morphological analysis. The experimental results show that our method can extract widely covered variants from large Twitter data and improve the recall of normalization without degrading the overall accuracy of Japanese morphological analysis.

This paper proposes a new method of constructing arbitrary class-based related word dictionaries on interactive topic models; we assume that each class is described by a topic. We propose a new semi-supervised method that uses the simplest topic model yielded by the standard EM algorithm; model calculation is very rapid. Furthermore our approach allows a dictionary to be modified interactively and the final dictionary has a hierarchical structure. This paper makes three contributions. First, it proposes a word-based semi-supervised topic model. Second, we apply the semi-supervised topic model to interactive learning; this approach is called the Interactive Topic Model. Third, we propose a score function; it extracts the related words that occupy the middle layer of the hierarchical structure. Experiments show that our method can appropriately retrieve the words belonging to an arbitrary class.