Weize Kong

Weize Kong

Weize Kong is a staff software engineer at Google DeepMind, working on retrieval augmented large language models. Before joining Google, he received his Ph.D. at University of Massachusetts Amherst in the Center for Intelligent Information Retrieval (CIIR). Prior to CIIR, he worked as an undergraduate research assistant in the Information Retrieval Group at Tsinghua University. Please see his personal homepage for a completed list of publications.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Preview abstract Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the LLMs to generate personalized text. We consider a typical scenario in which the large language model, which generates personalized output, is frozen and can only be accessed through APIs. Under this constraint, all one can do is to improve the input text (i.e., text prompts) sent to the LLM, a procedure that is usually done manually. In this paper, we propose a novel method to automatically revise prompts for personalized text generation. The proposed method takes the initial prompts generated by a state-of-the-art, multistage framework for personalized generation and rewrites a few critical components that summarize and synthesize the personal context. The prompt rewriter employs a training paradigm that chains together supervised learning (SL) and reinforcement learning (RL), where SL reduces the search space of RL and RL facilitates end-to-end training of the rewriter. Using datasets from three representative domains, we demonstrate that the rewritten prompts outperform both the original prompts and the prompts optimized via supervised learning or reinforcement learning alone. In-depth analysis of the rewritten prompts shows that they are not only human readable, but also able to guide manual revision of prompts when there is limited resource to employ reinforcement learning to train the prompt rewriter, or when it is costly to deploy an automatic prompt rewriter for inference. View details
    SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval
    Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '23), ACM(2023) (to appear)
    Preview abstract In dense retrieval, prior work has largely improved retrieval effectiveness using multi-vector dense representations, exemplified by ColBERT. In sparse retrieval, more recent work, such as SPLADE, demonstrated that one can also learn sparse lexical representations to achieve comparable effectiveness while enjoying better interpretability. In this work, we combine the strengths of both the sparse and dense representations for first-stage retrieval. Specifically, we propose SparseEmbed – a novel retrieval model that learns sparse lexical representations with contextual embeddings. Compared with SPLADE, our model leverages the contextual embeddings to improve model expressiveness. Compared with ColBERT, our sparse representations are trained end-to-end to optimize both efficiency and effectiveness. View details
    Learning Sparse Lexical Representations Over Expanded Vocabularies for Retrieval
    Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM '23)(2023)
    Preview abstract A recent line of work in first-stage Neural Information Retrieval has focused on learning sparse lexical representations instead of dense embeddings. One such work is SPLADE, which has been shown to lead to state-of-the-art results in both the in-domain and zero-shot settings, can leverage inverted indices for efficient retrieval, and offers enhanced interpretability. However, existing SPLADE models are fundamentally limited to learning a sparse representation based on the native BERT WordPiece vocabulary. In this work, we extend SPLADE to support learning sparse representations over arbitrary sets of tokens to improve flexibility and aid integration with existing retrieval systems. As an illustrative example, we focus on learning a sparse representation over a large (300k) set of unigrams. We add an unsupervised pretraining task on C4 to learn internal representations for new tokens. Our experiments show that our Expanded-SPLADE model maintains the performance of WordPiece-SPLADE on both in-domain and zero-shot retrieval while allowing for custom output vocabularies. View details
    End-to-End Query Term Weighting
    Karan Samel
    Swaraj Khadanga
    Wensong Xu
    Xingyu Wang
    Kashyap Kolipaka
    Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '23)(2023)
    Preview abstract Bag-of-words based lexical retrieval systems are still the most commonly used methods for real-world search applications. Recently deep learning methods have shown promising results to improve this retrieval performance but are expensive to run in an online fashion, non-trivial to integrate into existing production systems, and might not generalize well in out-of-domain retrieval scenarios. Instead, we build on top of lexical retrievers by proposing a Term Weighting BERT (TW-BERT) model. TW-BERT learns to predict the weight for individual n-gram (e.g., uni-grams and bi-grams) query input terms. These inferred weights and terms can be used directly by a retrieval system to perform a query search. To optimize these term weights, TW-BERT incorporates the scoring function used by the search engine, such as BM25, to score query-document pairs. Given sample query-document pairs we can compute a ranking loss over these matching scores, optimizing the learned query term weights in an end-to-end fashion. Aligning TW-BERT with search engine scorers minimizes the changes needed to integrate it into existing production applications, whereas existing deep learning based search methods would require further infrastructure optimization and hardware requirements. The learned weights can be easily utilized by standard lexical retrievers and by other retrieval techniques such as query expansion. We show that TW-BERT improves retrieval performance over strong term weighting baselines within MSMARCO and in out-of-domain retrieval on TREC datasets. View details
    Multi-Aspect Dense Retrieval
    Swaraj Khadanga
    Wensong Xu
    Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM(2022)
    Preview abstract Prior work in Dense Retrieval usually encodes queries and documents using single-vector representations (also called embeddings) and performs retrieval in the embedding space using approximate nearest neighbor search. This paradigm enables efficient semantic retrieval. However, the single-vector representations can be ineffective at capturing different aspects of the queries and documents in relevance matching, especially for some vertical domains. For example, in e-commerce search, these aspects could be category, brand and color. Given a query "white nike socks", a Dense Retrieval model may mistakenly retrieve some "white adidas socks" while missing out the intended brand. We propose to explicitly represent multiple aspects using one embedding per aspect. We introduce an aspect prediction task to teach the model to capture aspect information with particular aspect embeddings. We design a lightweight network to fuse the aspect embeddings for representing queries and documents. Our evaluation using an e-commerce dataset shows impressive improvements over strong Dense Retrieval baselines. We also discover that the proposed aspect embeddings can enhance the interpretability of Dense Retrieval models as a byproduct. View details
    Improving Cloud Storage Search with User Activity
    Proceedings of the 14th International Conference on Web Search and Data Mining (WSDM '21), ACM(2021)
    Preview abstract Cloud-based file storage platforms such as Google Drive are widely used as a means for storing, editing and sharing personal and organizational documents. In this paper, we improve search ranking quality for cloud storage platforms by utilizing user activity logs. Different from search logs, activity logs capture general document usage activity beyond search, such as opening, editing and sharing documents. We propose to automatically learn text embeddings that are effective for search ranking from activity logs. We develop a novel co-access signal, i.e., whether two documents were accessed by a user around the same time, to train deep semantic matching models that are useful for improving the search ranking quality. We confirm that activity-trained semantic matching models can improve ranking by conducting extensive offline experimentation using Google Drive search and activity logs. To the best of our knowledge, this is the first work to examine the benefits of leveraging document usage activity at large scale for cloud storage search; as such it can shed light on using such activity in scenarios where direct collection of search-specific interactions (e.g., query and click logs) may be expensive or infeasible. View details
    Natural Language Understanding with Privacy-Preserving BERT
    Proceedings of the 30th ACM International Conference on Information and Knowledge Management, ACM(2021)
    Preview abstract Privacy preservation remains a key challenge in data mining and Natural Language Understanding (NLU). Previous research shows that the input text or even text embeddings can leak private information. This concern motivates our research on effective privacy preservation approaches for pretrained Language Models (LMs). We investigate the privacy and utility implications of applying dχ-privacy, a variant of Local Differential Privacy, to BERT fine-tuning in NLU applications. More importantly, we further propose privacy-adaptive LM pretraining methods and show that our approach can boost the utility of BERT dramatically while retaining the same level of privacy protection. We also quantify the level of privacy preservation and provide guidance on privacy configuration. Our experiments and findings lay the groundwork for future explorations of privacy-preserving NLU with pretrained LMs. View details
    Learning to Cluster Documents into Workspaces Using Large Scale Activity Logs
    Mike Colagrosso
    Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’20), ACM(2020), 2416–2424
    Preview abstract Google Drive is widely used for managing personal and work-related documents in the cloud. To help users organize their documents in Google Drive, we develop a new feature to allow users to create a set of working files for ongoing easy access, called workspace. A workspace is a cluster of documents, but unlike a typical document cluster, it contains documents that are not only topically coherent, but are also useful in the ongoing user tasks. To alleviate the burden of creating workspaces manually, we automatically cluster documents into suggested workspaces. We go beyond the textual similarity-based unsupervised clustering paradigm and instead directly learn from users’ activity for document clustering. More specifically, we extract co-access signals (i.e., whether a user accessed two documents around the same time) to measure document relatedness. We then use a neural document similarity model that incorporates text, metadata, as well as co-access features. Since human labels are often difficult or expensive to collect, we extract weak labels based on co-access data at large scale for model training. Our offline and online experiments based on Google Drive show that (a) co-access features are very effective for document clustering; (b) our weakly supervised clustering achieves comparable or even better performance compared to the models trained with human labels; and (c) the weakly supervised method leads to better workspace suggestions that the users accept more often in the production system than baseline approaches. View details