Zhe Dong


SKILL: Structured Knowledge Infusion for Large Language Models
Fedor Moiseev | Zhe Dong | Enrique Alfonseca | Martin Jaggi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from text. In this work, we propose a method to infuse structured knowledge into LLMs, by directly training T5 models on factual triples of knowledge graphs (KGs). We show that models pre-trained on Wikidata KG with our method outperform the T5 baselines on FreebaseQA and WikiHop, as well as the Wikidata-answerable subset of TriviaQA and NaturalQuestions. The models pre-trained on factual triples compare competitively with the ones on natural language sentences that contain the same knowledge. Trained on a smaller size KG, WikiMovies, we saw 3x improvement of exact match score on MetaQA task. The proposed method has an advantage that no alignment between the knowledge graph and text corpus is required in curating training data. This makes our method particularly useful when working with industry-scale knowledge graphs.

Exploring Dual Encoder Architectures for Question Answering
Zhe Dong | Jianmo Ni | Dan Bikel | Enrique Alfonseca | Yuan Wang | Chen Qu | Imed Zitouni
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Dual encoders have been used for question-answering (QA) and information retrieval (IR) tasks with good results. There are two major types of dual encoders, Siamese Dual Encoders (SDE), with parameters shared across two encoders, and Asymmetric Dual Encoder (ADE), with two distinctly parameterized encoders. In this work, we explore the dual encoder architectures for QA retrieval tasks. By evaluating on MS MARCO, open domain NQ, and the MultiReQA benchmarks, we show that SDE performs significantly better than ADE. We further propose three different improved versions of ADEs. Based on the evaluation of QA retrieval tasks and direct analysis of the embeddings, we demonstrate that sharing parameters in projection layers would enable ADEs to perform competitively with SDEs.


An Double Hidden HMM and an CRF for Segmentation Tasks with Pinyin’s Finals
Huixing Jiang | Zhe Dong
CIPS-SIGHAN Joint Conference on Chinese Language Processing