Hiun Kim

Hiun Kim, Tae Kwan Lee, Taeryun Won

Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show that MLM pre-trained models have limited readiness and transfer learning issues for fine-tuning them into Neural Bi-Encoder models. This paper studies the effect of different pre-training datasets and pre-training options on the MLM pre-trained models for retrieval fine-tuning. The study focuses on the SPLADE-style model, which uses the MLM layer also at fine-tuning time. More specifically, we experimented with Expanded-SPLADE (ESPLADE) models, a specific instance of SPLADE models, and in-house web document titles are used as datasets. Pre-training, fine-tuning, and evaluation with optional test-time pruning of sparse vectors are conducted. Our observations are three-fold: First, fine-tuned models of higher retrieval effectiveness at both unpruned and most strict pruned settings are mostly pre-trained on a general corpus, and pre-trained with a higher learning rate, showing lower MLM accuracies. Second, in the most strict pruned setting, those models show higher-level retrieval cost and a higher variance in the length of the individual postings list. Third, the repetition of the general pre-training dataset does not have much effect on retrieval effectiveness. The experimentation empirically identifies the potential limitations for aligning MLM pre-training to ESPLADE fine-tuning. Also, the experimentation provides an empirical observation that, at most strict pruned settings, the retrieval effectiveness is better maintained by the higher-level retrieval cost, showing the trade-off relationship between the two in our setting.

Taeryun Won, Tae Kwan Lee, Hiun Kim et al.

This paper presents a comprehensive comparison of BM25, SPLADE, and Expanded-SPLADE models in the context of large-scale web document retrieval. We evaluate the effectiveness and efficiency of these models on datasets spanning from tens of millions to billions of web document titles. SPLADE and Expanded-SPLADE, which utilize sparse lexical representations, demonstrate superior retrieval performance compared to BM25, especially for complex queries. However, these models incur higher computational costs. We introduce pruning strategies, including document-centric pruning and top-k query term selection, boolean query with term threshold to mitigate these costs and improve the models' efficiency without significantly sacrificing retrieval performance. The results show that Expanded-SPLADE strikes the best balance between effectiveness and efficiency, particularly when handling large datasets. Our findings offer valuable insights for deploying sparse retrieval models in large-scale search engines.

Hiun Kim, Tae Kwan Lee, Taeryun Won

Learned Sparse Retrieval (LSR) such as SPLADE has growing interest for effective semantic 1st stage matching while enjoying the efficiency of inverted indices. A recent work on learning SPLADE models with expanded vocabularies (ESPLADE) was proposed to represent queries and documents into a sparse space of custom vocabulary which have different levels of vocabularic granularity. Within this effort, however, there have not been many studies on the role of vocabulary in SPLADE models and their relationship to retrieval efficiency and effectiveness. To study this, we construct BERT models with 100K-sized output vocabularies, one initialized with the ESPLADE pretraining method and one initialized randomly. After finetune on real-world search click logs, we applied logit score-based queries and documents pruning to max size for further balancing efficiency. The experimental result in our evaluation set shows that, when pruning is applied, the two models are effective compared to the 32K-sized normal SPLADE model in the computational budget under the BM25. And the ESPLADE models are more effective than the random vocab model, while having a similar retrieval cost. The result indicates that the size and pretrained weight of output vocabularies play the role of configuring the representational specification for queries, documents, and their interactions in the retrieval engine, beyond their original meaning and purposes in NLP. These findings can provide a new room for improvement for LSR by identifying the importance of representational specification from vocabulary configuration for efficient and effective retrieval.

Hiun Kim, Jisu Jeong, Kyung-Min Kim et al.

Building a shopping product collection has been primarily a human job. With the manual efforts of craftsmanship, experts collect related but diverse products with common shopping intent that are effective when displayed together, e.g., backpacks, laptop bags, and messenger bags for freshman bag gifts. Automatically constructing a collection requires an ML system to learn a complex relationship between the customer's intent and the product's attributes. However, there have been challenging points, such as 1) long and complicated intent sentences, 2) rich and diverse product attributes, and 3) a huge semantic gap between them, making the problem difficult. In this paper, we use a pretrained language model (PLM) that leverages textual attributes of web-scale products to make intent-based product collections. Specifically, we train a BERT with triplet loss by setting an intent sentence to an anchor and corresponding products to positive examples. Also, we improve the performance of the model by search-based negative sampling and category-wise positive pair augmentation. Our model significantly outperforms the search-based baseline model for intent-based product matching in offline evaluations. Furthermore, online experimental results on our e-commerce platform show that the PLM-based method can construct collections of products with increased CTR, CVR, and order-diversity compared to expert-crafted collections.

Boseop Kim, HyoungSeok Kim, Sang-Woo Lee et al.

GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data. Here we address some remaining issues less reported by the GPT-3 paper, such as a non-English LM, the performances of different sized models, and the effect of recently introduced prompt optimization on in-context learning. To achieve this, we introduce HyperCLOVA, a Korean variant of 82B GPT-3 trained on a Korean-centric corpus of 560B tokens. Enhanced by our Korean-specific tokenization, HyperCLOVA with our training configuration shows state-of-the-art in-context zero-shot and few-shot learning performances on various downstream tasks in Korean. Also, we show the performance benefits of prompt-based learning and demonstrate how it can be integrated into the prompt engineering pipeline. Then we discuss the possibility of materializing the No Code AI paradigm by providing AI prototyping capabilities to non-experts of ML by introducing HyperCLOVA studio, an interactive prompt engineering interface. Lastly, we demonstrate the potential of our methods with three successful in-house applications.

Seungjae Jung, Young-Jin Park, Jisu Jeong et al.

Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e.g., personalized purchase prediction of shopping baskets. While most previous techniques have focused on leveraging a user's history, the study of combining it with others' histories remains untapped potential. This paper proposes Global-Local Item Embedding (GLOIE) that learns to utilize the temporal properties of sets across whole users as well as within a user by coining the names as global and local information to distinguish the two temporal patterns. GLOIE uses Variational Autoencoder (VAE) and dynamic graph-based model to capture global and local information and then applies attention to integrate resulting item embeddings. Additionally, we propose to use Tweedie output for the decoder of VAE as it can easily model zero-inflated and long-tailed distribution, which is more suitable for several real-world data distributions than Gaussian or multinomial counterparts. When evaluated on three public benchmarks, our algorithm consistently outperforms previous state-of-the-art methods in most ranking metrics.

Hiun Kim

Many variability management techniques rely on sophisticated language extension or tools to support it. While this can provide dedicated syntax and operational mechanism but it struggling practical adaptation for the cost of adapting new technology as part of development process. We present Self-composable Programming, a language-driven, composition-based variability implementation which takes an object-oriented approach to modeling and composing behaviors in software. Self-composable Programming introduces hierarchical relationship of behavior by providing concepts of abstract function, which modularise commonalities, and specific function which inherits from abstract function and be apply refinement to contain variabilities to fulfill desired functionality. Various object-oriented techniques can applicable in the refinement process including explicit method-based, and implicit traits-based refinement. In order to evaluate the potential independence of behavior from the object by applying object-orientation to function, we compare it to Aspect-oriented Programming both conceptually and empirically.