Boyang Li


2023

pdf bib
Is GPT-3 a Good Data Annotator?
Bosheng Ding | Chengwei Qin | Linlin Liu | Yew Ken Chia | Boyang Li | Shafiq Joty | Lidong Bing
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Data annotation is the process of labeling data that could be used to train machine learning models. Having high quality annotation is crucial, as it allows the model to learn the relationship between the input data and the desired output. GPT-3, a large-scale language model developed by OpenAI, has demonstrated im- impressive zero- and few-shot performance on a wide range of NLP tasks. It is therefore natural to wonder whether it can be used to effectively annotate data for NLP tasks. In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks. Through this analysis, we aim to provide insight into the potential of GPT-3 as a general-purpose data annotator in NLP.

2022

pdf bib
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Anthony Meng Huat Tiong | Junnan Li | Boyang Li | Silvio Savarese | Steven C.H. Hoi
Findings of the Association for Computational Linguistics: EMNLP 2022

Visual question answering (VQA) is a hallmark of vision and language reasoningand a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA),a modular framework for zero-shot VQA.In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality,PNP-VQA requires no additional training of the PLMs.Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captions,and pass the captions to a PLM as context for question answering. Surpassing end-to-end trained baselines, PNP-VQA achieves state-of-the-art results on zero-shot VQAv2 and GQA. With 11B parameters, it outperforms the 80B-parameter Flamingo model by 8.5% on VQAv2. With 738M PLM parameters, PNP-VQA achieves an improvement of 9.1% on GQA over FewVLM with 740M PLM parameters.

pdf bib
History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
Tong Zhang | Yong Liu | Boyang Li | Zhiwei Zeng | Pengwei Wang | Yuan You | Chunyan Miao | Lizhen Cui
Findings of the Association for Computational Linguistics: EMNLP 2022

With the evolution of pre-trained language models, current open-domain dialogue systems have achieved great progress in conducting one-session conversations. In contrast, Multi-Session Conversation (MSC), which consists of multiple sessions over a long term with the same user, is under-investigated. In this paper, we propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue. HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses. Specifically, HAHT first encodes history conversation sessions hierarchically into a history memory. Then, HAHT leverages historical information to facilitate the understanding of the current conversation context by encoding the history memory together with the current context with attention-based mechanisms. Finally, to explicitly utilize historical information, HAHT uses a history-aware response generator that switches between a generic vocabulary and a history-aware vocabulary. Experimental results on a large-scale MSC dataset suggest that the proposed HAHT model consistently outperforms baseline models. Human evaluation results support that HAHT generates more human-like, context-relevant, and history-relevant responses than baseline models.

pdf bib
Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Xu Guo | Boyang Li | Han Yu
Findings of the Association for Computational Linguistics: EMNLP 2022

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are available during pretraining. We propose bOosting Prompt TunIng with doMain Adaptation (OPTIMA), which regularizes the decision boundary to be smooth around regions where source and target data distributions are similar. Extensive experiments demonstrate that OPTIMA significantly enhances the transferability and sample-efficiency of prompt tuning compared to strong baselines. Moreover, in few-shot settings, OPTIMA exceeds full-model tuning by a large margin.

pdf bib
Toward Knowledge-Enriched Conversational Recommendation Systems
Tong Zhang | Yong Liu | Boyang Li | Peixiang Zhong | Chen Zhang | Hao Wang | Chunyan Miao
Proceedings of the 4th Workshop on NLP for Conversational AI

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie. We also propose an alignment loss to further integrate KG entities into the response generation network. Experiments on the large-scale REDIAL dataset demonstrate that the proposed system consistently outperforms state-of-the-art baselines.

2021

pdf bib
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
Xu Guo | Boyang Li | Han Yu | Chunyan Miao
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while optimizing for domain-specific performance. However, these objectives may be in conflict, which can lead to optimization difficulties and sometimes diminished transfer. We propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics. The proposed method outperforms transfer learning and meta-learning baselines. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.

2018

pdf bib
Annotating High-Level Structures of Short Stories and Personal Anecdotes
Boyang Li | Beth Cardier | Tong Wang | Florian Metze
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2016

pdf bib
Multiplicative Representations for Unsupervised Semantic Role Induction
Yi Luan | Yangfeng Ji | Hannaneh Hajishirzi | Boyang Li
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)