Qifan Wang


2024

pdf bib
Minimal Distillation Schedule for Extreme Language Model Compression
Chen Zhang | Yang Yang | Qifan Wang | Jiahao Liu | Jingang Wang | Wei Wu | Dawei Song
Findings of the Association for Computational Linguistics: EACL 2024

Recent studies have revealed that language model distillation can become less effective when there is a significant capacity gap between the teacher and the student models. In order to bridge the gap, teacher assistant-based distillation has been introduced, in which the selection of the teacher assistant plays a crucial role in transferring knowledge from the teacher to the student. However, existing approaches for teacher assistant-based distillation require numerous trials to find the optimal teacher assistant.In this paper, we propose a novel approach called Minimal Distillation Schedule (MiniDisc), which enables the scheduling of an optimal teacher assistant in just one trial for extreme model compression (e.g, to 5% scale). In particular, we empirically show that the performance of the student is positively correlated with the scale-performance tradeoff of the teacher assistant. We then introduce a new 𝜆-tradeoff metric that quantifies the optimality of the teacher assistant without the need for trial distillation to the student. By employing a sandwich framework, MiniDisc can select the optimal teacher assistant with the best 𝜆-tradeoff.We extensively evaluate MiniDisc through a series of experiments on the GLUE benchmark. The results demonstrate that our approach achieved an improved efficiency compared to various state-of-the-art baselines. Furthermore, we showcase the scalability of MiniDisc by applying it to a language model with billions of parameters.

pdf bib
Ameli: Enhancing Multimodal Entity Linking with Fine-Grained Attributes
Barry Yao | Sijia Wang | Yu Chen | Qifan Wang | Minqian Liu | Zhiyang Xu | Licheng Yu | Lifu Huang
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose attribute-aware multimodal entity linking, where the input consists of a mention described with a text paragraph and images, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where each entity is also accompanied by a text description, visual images, and a collection of attributes that present the meta-information of the entity in a structured format. To facilitate this research endeavor, we construct Ameli, encompassing a new multimodal entity linking benchmark dataset that contains 16,735 mentions described in text and associated with 30,472 images, and a multimodal knowledge base that covers 34,690 entities along with 177,873 entity images and 798,216 attributes. To establish baseline performance on Ameli, we experiment with several state-of-the-art architectures for multimodal entity linking and further propose a new approach that incorporates attributes of entities into disambiguation. Experimental results and extensive qualitative analysis demonstrate that extracting and understanding the attributes of mentions from their text descriptions and visual images play a vital role in multimodal entity linking. To the best of our knowledge, we are the first to integrate attributes in the multimodal entity linking task. The programs, model checkpoints, and the dataset are publicly available at https://github.com/VT-NLP/Ameli.

2023

pdf bib
Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context
Moxin Li | Wenjie Wang | Fuli Feng | Hanwang Zhang | Qifan Wang | Tat-Seng Chua
Findings of the Association for Computational Linguistics: ACL 2023

Machine Reading Comprehension (MRC) models easily learn spurious correlations from complex contexts such as tabular data. Counterfactual training—using the factual and counterfactual data by augmentation—has become a promising solution. However, it is costly to construct faithful counterfactual examples because it is tricky to maintain the consistency and dependency of the tabular data. In this paper, we take a more efficient fashion to ask hypothetical questions like “in which year would the net profit be larger if the revenue in 2019 were $38,298?”, whose effects on the answers are equivalent to those expensive counterfactual tables. We propose a hypothetical training framework that uses paired examples with different hypothetical questions to supervise the direction of model gradient towards the counterfactual answer change. The superior generalization results on tabular MRC datasets, including a newly constructed stress test and MultiHiertt, validate our effectiveness.

pdf bib
Fusion or Defusion? Flexible Vision-and-Language Pre-Training
Rongyi Sun | Ziran Li | Yifeng Ding | Qifan Wang | Jingang Wang | Haitao Zheng | Wei Wu | Yunsen Xian
Findings of the Association for Computational Linguistics: ACL 2023

Existing approaches in the vision-and-language pre-training (VLP) paradigm mainly deploy either fusion-based encoders or dual-encoders, failing to achieve both effectiveness and efficiency in downstream multimodal tasks. In this paper, we build a flexible VLP model by incorporating cross-modal fusions into a dual-encoder architecture, where the introduced fusion modules can be easily decoupled from the dual encoder so as to switch the model to a fusion-free one. To better absorb cross-modal features from the fusion modules, we design a cross-modal knowledge transfer strategy along with other comprehensive pre-training tasks to guide the training process, which can further strengthen both the fusion-based and fusion-free representation learning. Extensive experiments conducted on various downstream vision-language tasks show that our proposed model is well-equipped with effectiveness as well as efficiency, demonstrating a superior performance compared with other strong VLP models.

pdf bib
Meta-training with Demonstration Retrieval for Efficient Few-shot Learning
Aaron Mueller | Kanika Narang | Lambert Mathias | Qifan Wang | Hamed Firooz
Findings of the Association for Computational Linguistics: ACL 2023

Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and task-agnostic manner; however, these methods alone results in models that may not have sufficient parameterization or knowledge to adapt quickly to a large variety of tasks. To overcome this issue, we propose meta-training with demonstration retrieval, where we use a dense passage retriever to retrieve semantically similar labeled demonstrations to each example for more varied supervision. By separating external knowledge from model parameters, we can use meta-training to train parameter-efficient models that generalize well on a larger variety of tasks. We construct a meta-training set from UnifiedQA and CrossFit, and propose a demonstration bank based on UnifiedQA tasks. To our knowledge, our work is the first to combine retrieval with meta-training, to use DPR models to retrieve demonstrations, and to leverage demonstrations from many tasks simultaneously, rather than randomly sampling demonstrations from the training set of the target task. Our approach outperforms a variety of targeted parameter-efficient and retrieval-augmented few-shot methods on QA, NLI, and text classification tasks (including SQuAD, QNLI, and TREC). Our approach can be meta-trained and fine-tuned quickly on a single GPU.

pdf bib
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models
Zhuocheng Gong | Jiahao Liu | Qifan Wang | Yang Yang | Jingang Wang | Wei Wu | Yunsen Xian | Dongyan Zhao | Rui Yan
Findings of the Association for Computational Linguistics: ACL 2023

While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly important problem. Quantization, which represents high-precision tensors with low-bit fix-point format, is a viable solution. However, most existing quantization methods are task-specific, requiring customized training and quantization with a large number of trainable parameters on each individual task. Inspired by the observation that the over-parameterization nature of PLMs makes it possible to freeze most of the parameters during the fine-tuning stage, in this work, we propose a novel “quantize before fine-tuning” framework, PreQuant, that differs from both quantization-aware training and post-training quantization. {pasted macro ‘OUR’} is compatible with various quantization strategies, with outlier-aware parameter-efficient fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5. We also provide an empirical investigation into the workflow of PreQuant, which sheds light on its efficacy.

pdf bib
FedPETuning: When Federated Learning Meets the Parameter-Efficient Tuning Methods of Pre-trained Language Models
Zhuo Zhang | Yuanhang Yang | Yong Dai | Qifan Wang | Yue Yu | Lizhen Qu | Zenglin Xu
Findings of the Association for Computational Linguistics: ACL 2023

With increasing concerns about data privacy, there is an increasing necessity of fine-tuning pre-trained language models (PLMs) for adapting to downstream tasks located in end-user devices or local clients without transmitting data to the central server. This urgent necessity therefore calls the research of investigating federated learning (FL) for PLMs. However, large PLMs bring the curse of prohibitive communication overhead and local model adaptation costs for the FL system. To this end, we investigate the parameter-efficient tuning (PETuning) of PLMs and develop a corresponding federated benchmark for four representative PETuning methods, dubbed FedPETuning. Specifically, FedPETuning provides the first holistic empirical study of representative PLMs tuning methods in FL, covering privacy attacks, performance comparisons, and resource-constrained analysis. Intensive experimental results have indicated that FedPETuning can efficiently defend against privacy attacks and maintains acceptable performance with reducing heavy resource consumption. The open-source code and data are available at https://github.com/SMILELab-FL/FedPETuning.

pdf bib
MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction
Li Yang | Qifan Wang | Jingang Wang | Xiaojun Quan | Fuli Feng | Yu Chen | Madian Khabsa | Sinong Wang | Zenglin Xu | Dongfang Liu
Findings of the Association for Computational Linguistics: ACL 2023

The task of product attribute value extraction is to identify values of an attribute from product information. Product attributes are important features, which help improve online shopping experience of customers, such as product search, recommendation and comparison. Most existing works only focus on extracting values for a set of known attributes with sufficient training data. However, with the emerging nature of e-commerce, new products with their unique set of new attributes are constantly generated from different retailers and merchants. Collecting a large number of annotations for every new attribute is costly and time consuming. Therefore, it is an important research problem for product attribute value extraction with limited data. In this work, we propose a novel prompt tuning approach with Mixed Prompts for few-shot Attribute Value Extraction, namely MixPAVE. Specifically, MixPAVE introduces only a small amount (< 1%) of trainable parameters, i.e., a mixture of two learnable prompts, while keeping the existing extraction model frozen. In this way, MixPAVE not only benefits from parameter-efficient training, but also avoids model overfitting on limited training examples. Experimental results on two product benchmarks demonstrate the superior performance of the proposed approach over several state-of-the-art baselines. A comprehensive set of ablation studies validate the effectiveness of the prompt design, as well as the efficiency of our approach.

pdf bib
Attack Prompt Generation for Red Teaming and Defending Large Language Models
Boyi Deng | Wenjie Wang | Fuli Feng | Yang Deng | Qifan Wang | Xiangnan He
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning. Furthermore, we propose a defense framework that fine-tunes victim LLMs through iterative interactions with the attack framework to enhance their safety against red teaming attacks. Extensive experiments on different LLMs validate the effectiveness of our proposed attack and defense frameworks. Additionally, we release a series of attack prompts datasets named SAP with varying sizes, facilitating the safety evaluation and enhancement of more LLMs.

pdf bib
PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection
Tao Yang | Tianyuan Shi | Fanqi Wan | Xiaojun Quan | Qifan Wang | Bingzhe Wu | Jiaxiang Wu
Findings of the Association for Computational Linguistics: EMNLP 2023

Recent advances in large language models (LLMs), such as ChatGPT, have showcased remarkable zero-shot performance across various NLP tasks. However, the potential of LLMs in personality detection, which involves identifying an individual’s personality from their written texts, remains largely unexplored. Drawing inspiration from Psychological Questionnaires, which are carefully designed by psychologists to evaluate individual personality traits through a series of targeted items, we argue that these items can be regarded as a collection of well-structured chain-of-thought (CoT) processes. By incorporating these processes, LLMs can enhance their capabilities to make more reasonable inferences on personality from textual input. In light of this, we propose a novel personality detection method, called PsyCoT, which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner. In particular, we employ a LLM as an AI assistant with a specialization in text analysis. We prompt the assistant to rate individual items at each turn and leverage the historical rating results to derive a conclusive personality preference. Our experiments demonstrate that PsyCoT significantly improves the performance and robustness of GPT-3.5 in personality detection, achieving an average F1 score improvement of 4.23/10.63 points on two benchmark datasets compared to the standard prompting method. Our code is available at https://github.com/TaoYang225/PsyCoT.

pdf bib
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
Jaehyung Kim | Yuning Mao | Rui Hou | Hanchao Yu | Davis Liang | Pascale Fung | Qifan Wang | Fuli Feng | Lifu Huang | Madian Khabsa
Findings of the Association for Computational Linguistics: EMNLP 2023

Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives of robustness for LMs have been studied independently, but lacking a unified consideration in multiple perspectives. In this paper, we propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST), a simple yet effective fine-tuning technique to enhance the multi-perspective robustness of LMs in a unified way. RoAST effectively incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. To be specific, RoAST introduces adversarial perturbation during fine-tuning while the model parameters are selectively updated upon their relative importance to minimize unnecessary deviation. Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.

pdf bib
Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression
Jiduan Liu | Jiahao Liu | Qifan Wang | Jingang Wang | Xunliang Cai | Dongyan Zhao | Ran Wang | Rui Yan
Findings of the Association for Computational Linguistics: EMNLP 2023

Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these models poses huge challenges for their deployment in real-world applications. While numerous model compression techniques have been proposed, most of them are not well-suited for achieving extreme model compression when there is a significant gap in model scale. In this paper, we introduce a novel compression paradigm called Retrieval-based Knowledge Transfer (RetriKT), which effectively transfers the knowledge of LLMs to extremely small-scale models (e.g., 1%). In particular, our approach extracts knowledge from LLMs to construct a knowledge store, from which the small-scale model can retrieve relevant information and leverage it for effective inference. To improve the quality of the model, soft prompt tuning and Proximal Policy Optimization (PPO) reinforcement learning techniques are employed. Extensive experiments are conducted on low-resource tasks from SuperGLUE and GLUE benchmarks. The results demonstrate that the proposed approach significantly enhances the performance of small-scale models by leveraging the knowledge from LLMs.

pdf bib
Improving Input-label Mapping with Demonstration Replay for In-context Learning
Zhuocheng Gong | Jiahao Liu | Qifan Wang | Jingang Wang | Xunliang Cai | Dongyan Zhao | Rui Yan
Findings of the Association for Computational Linguistics: EMNLP 2023

In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model’s understanding of downstream NLP tasks, without directly adjusting the model parameters. The effectiveness of ICL can be attributed to the strong language modeling capabilities of large language models (LLMs), which enable them to learn the mapping between input and labels based on in-context demonstrations. Despite achieving promising results, the causal nature of language modeling in ICL restricts the attention to be backward only, i.e., a token only attends to its previous tokens, failing to capture the full input-label information and limiting the model’s performance. In this paper, we propose a novel ICL method called Repeated Demonstration with Sliding Causal Attention, (RdSca). Specifically, we duplicate later demonstrations and concatenate them to the front, allowing the model to ‘observe’ the later information even under the causal restriction. Besides, we introduce sliding causal attention, which customizes causal attention to avoid information leakage. Experimental results show that our method significantly improves the input-label mapping in ICL demonstrations. We also conduct an in-depth analysis of how to customize the causal attention without training, which has been an unexplored area in previous research.

pdf bib
Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality
Harman Singh | Pengchuan Zhang | Qifan Wang | Mengjiao Wang | Wenhan Xiong | Jingfei Du | Yu Chen
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning. However, recent research has highlighted severe limitations of these models in their ability to perform compositional reasoning over objects, attributes, and relations. Scene graphs have emerged as an effective way to understand images compositionally. These are graph-structured semantic representations of images that contain objects, their attributes, and relations with other objects in a scene. In this work, we consider the scene graph parsed from text as a proxy for the image scene graph and propose a graph decomposition and augmentation framework along with a coarse-to-fine contrastive learning objective between images and text that aligns sentences of various complexities to the same image. We also introduce novel negative mining techniques in the scene graph space for improving attribute binding and relation understanding. Through extensive experiments, we demonstrate the effectiveness of our approach that significantly improves attribute binding, relation understanding, systematic generalization, and productivity on multiple recently proposed benchmarks (For example, improvements up to 18% for systematic generalization, 16.5% for relation understanding over a strong baseline), while achieving similar or better performance than CLIP on various general multimodal tasks.

pdf bib
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
Yuanhang Yang | Shiyi Qi | Chuanyi Liu | Qifan Wang | Cuiyun Gao | Zenglin Xu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational cost. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm TopicAns for efficient sentence pair modeling. TopicAns involves a lightweight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our TopicAnscan speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models.

pdf bib
The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models
Jingyuan Qi | Zhiyang Xu | Ying Shen | Minqian Liu | Di Jin | Qifan Wang | Lifu Huang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT heavily relies on the initial decisions, causing errors in early steps to accumulate and impact the final answers. In contrast, humans adopt recursive thinking when tackling complex reasoning problems, i.e. iteratively breaking the original problem into approachable sub-problems and aggregating their answers to resolve the original one. Inspired by the human cognitive process, we propose SOCRATIC QUESTIONING, a divide-and-conquer style algorithm that mimics the recursive thinking process. Specifically, SOCRATIC QUESTIONING leverages large language models to raise and answer sub-questions until collecting enough information to tackle the original question. Unlike CoT, SOCRATIC QUESTIONING explicitly navigates the thinking space, stimulates effective recursive thinking, and is more robust towards errors in the thinking process. Extensive experiments on several complex reasoning tasks, including MMLU, MATH, LogiQA, and visual question-answering demonstrate significant performance improvements over the state-of-the-art prompting methods, such as CoT, and Tree-of-Thought. The qualitative analysis clearly shows that the intermediate reasoning steps elicited by SOCRATIC QUESTIONING are similar to humans’ recursively thinking process of complex reasoning problems.

pdf bib
Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems
Tianyuan Shi | Liangzhi Li | Zijian Lin | Tao Yang | Xiaojun Quan | Qifan Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches generally integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases. Taking inspiration from open-domain question answering, we propose a retriever-generator architecture that harnesses a retriever to retrieve pertinent knowledge and a generator to generate system responses. Due to the lack of retriever training labels, we propose relying on feedback from the generator as pseudo-labels to train the retriever. To achieve this, we introduce a dual-feedback mechanism that generates both positive and negative feedback based on the output of the generator. Our method demonstrates superior performance in task-oriented dialogue tasks, as evidenced by experimental results on three benchmark datasets.

pdf bib
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models
Qifan Wang | Yuning Mao | Jingang Wang | Hanchao Yu | Shaoliang Nie | Sinong Wang | Fuli Feng | Lifu Huang | Xiaojun Quan | Zenglin Xu | Dongfang Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

With the continuous growth of large language models, the process of fine-tuning these models for new tasks has become increasingly parameter-intensive. Prompt tuning, a method that involves tuning a small set of soft prompts, has emerged as an effective and efficient approach for adapting large pre-trained language models. However, most existing prompt tuning approaches only introduce prompts at the input layer, limiting their performance and leaving large rooms for improvement. In this work, we propose a novel Attention Prompt tuning method, namely APrompt, for efficient adaptation of pre-trained language models. We first demonstrate that existing prompt tuning can be considered as a special case of attention prompt tuning. We then formally introduce APrompt, which incorporates query, key, and value prompts into the attention layer to guide the attention computation during fine-tuning. Experimental results on the SuperGLUE benchmark consistently demonstrate that our proposed approach outperforms state-of-the-art baselines and full fine-tuning method with pre-trained models at different scales. In addition, a comprehensive set of ablation studies validate the effectiveness of the prompt design, as well as the efficiency of our approach.

pdf bib
COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation
Nan Wang | Qifan Wang | Yi-Chia Wang | Maziar Sanjabi | Jingzhou Liu | Hamed Firooz | Hongning Wang | Shaoliang Nie
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

As language models become increasingly integrated into our digital lives, Personalized Text Generation (PTG) has emerged as a pivotal component with a wide range of applications. However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different levels of linguistic quality with users’ protected attributes. The model can inherit the bias and perpetuate inequality in generating text w.r.t. users’ protected attributes, leading to unfair treatment when serving users. In this work, we investigate fairness of PTG in the context of personalized explanation generation for recommendations. We first discuss the biases in generated explanations and their fairness implications. To promote fairness, we introduce a general framework to achieve measure-specific counterfactual fairness in explanation generation. Extensive experiments and human evaluations demonstrate the effectiveness of our method.

pdf bib
MUSTIE: Multimodal Structural Transformer for Web Information Extraction
Qifan Wang | Jingang Wang | Xiaojun Quan | Fuli Feng | Zenglin Xu | Shaoliang Nie | Sinong Wang | Madian Khabsa | Hamed Firooz | Dongfang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The task of web information extraction is to extract target fields of an object from web pages, such as extracting the name, genre and actor from a movie page. Recent sequential modeling approaches have achieved state-of-the-art results on web information extraction. However, most of these methods only focus on extracting information from textual sources while ignoring the rich information from other modalities such as image and web layout. In this work, we propose a novel MUltimodal Structural Transformer (MUST) that incorporates multiple modalities for web information extraction. Concretely, we develop a structural encoder that jointly encodes the multimodal information based on the HTML structure of the web layout, where high-level DOM nodes, and low-level text and image tokens are introduced to represent the entire page. Structural attention patterns are designed to learn effective cross-modal embeddings for all DOM nodes and low-level tokens. An extensive set of experiments are conducted on WebSRC and Common Crawl benchmarks. Experimental results demonstrate the superior performance of MUST over several state-of-the-art baselines.

pdf bib
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales
Brihi Joshi | Ziyi Liu | Sahana Ramnath | Aaron Chan | Zhewei Tong | Shaoliang Nie | Qifan Wang | Yejin Choi | Xiang Ren
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Among the remarkable emergent capabilities of large language models (LMs) is free-text rationalization; beyond certain scale, large LMs are capable of generating seemingly useful rationalizations, which in turn, can dramatically enhance their performances on leaderboards. This phenomenon raises a question: can machine generated rationales also be useful for humans, especially when lay humans try to answer questions based on those machine rationales? We observe that human utility of existing rationales is far from satisfactory and expensive to estimate with human studies. Existing metrics like task performance of the LM generating the rationales or similarity between generated and gold rationales are not good indicators of their human utility. While we observe that certain properties of rationales like conciseness and novelty are correlated with their human utility, estimating them without human involvement is challenging. We show that, by estimating a rationale’s helpfulness in answering similar unseen instances, we can measure its human utility to a better extent. We also translate this finding into an automated score, Gen-U, that we propose, which can help improve LMs’ ability to generate rationales with better human utility, while maintaining most of its task performance. Lastly, we release all code and collected data with this project.

pdf bib
AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression
Siyue Wu | Hongzhan Chen | Xiaojun Quan | Qifan Wang | Rui Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Knowledge distillation has attracted a great deal of interest recently to compress large language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the teacher’s behavior while ignoring the reasoning behind it. Second, these methods usually focus on the transfer of sophisticated model-specific knowledge but overlook data-specific knowledge. In this paper, we present a novel attribution-driven knowledge distillation approach, which explores the token-level rationale behind the teacher model based on Integrated Gradients (IG) and transfers attribution knowledge to the student model. To enhance the knowledge transfer of model reasoning and generalization, we further explore multi-view attribution distillation on all potential decisions of the teacher. Comprehensive experiments are conducted with BERT on the GLUE benchmark. The experimental results demonstrate the superior performance of our approach to several state-of-the-art methods.

pdf bib
Disentangled Phonetic Representation for Chinese Spelling Correction
Zihong Liang | Xiaojun Quan | Qifan Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese texts. Although efforts have been made to introduce phonetic information (Hanyu Pinyin) in this task, they typically merge phonetic representations with character representations, which tends to weaken the representation effect of normal texts. In this work, we propose to disentangle the two types of features to allow for direct interaction between textual and phonetic information. To learn useful phonetic representations, we introduce a pinyin-to-character objective to ask the model to predict the correct characters based solely on phonetic information, where a separation mask is imposed to disable attention from phonetic input to text. To avoid overfitting the phonetics, we further design a self-distillation module to ensure that semantic information plays a major role in the prediction. Extensive experiments on three CSC benchmarks demonstrate the superiority of our method in using phonetic information.

pdf bib
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank
Jiduan Liu | Jiahao Liu | Qifan Wang | Jingang Wang | Wei Wu | Yunsen Xian | Dongyan Zhao | Kai Chen | Rui Yan
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Unsupervised sentence representation learning is one of the fundamental problems in natural language processing with various downstream applications. Recently, contrastive learning has been widely adopted which derives high-quality sentence representations by pulling similar semantics closer and pushing dissimilar ones away. However, these methods fail to capture the fine-grained ranking information among the sentences, where each sentence is only treated as either positive or negative. In many real-world scenarios, one needs to distinguish and rank the sentences based on their similarities to a query sentence, e.g., very relevant, moderate relevant, less relevant, irrelevant, etc. In this paper, we propose a novel approach, RankCSE, for unsupervised sentence representation learning, which incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework. In particular, we learn semantically discriminative sentence representations by simultaneously ensuring ranking consistency between two representations with different dropout masks, and distilling listwise ranking knowledge from the teacher. An extensive set of experiments are conducted on both semantic textual similarity (STS) and transfer (TR) tasks. Experimental results demonstrate the superior performance of our approach over several state-of-the-art baselines.

2022

pdf bib
SMARTAVE: Structured Multimodal Transformer for Product Attribute Value Extraction
Qifan Wang | Li Yang | Jingang Wang | Jitin Krishnan | Bo Dai | Sinong Wang | Zenglin Xu | Madian Khabsa | Hao Ma
Findings of the Association for Computational Linguistics: EMNLP 2022

Automatic product attribute value extraction refers to the task of identifying values of an attribute from the product information. Product attributes are essential in improving online shopping experience for customers. Most existing methods focus on extracting attribute values from product title and description. However, in many real-world applications, a product is usually represented by multiple modalities beyond title and description, such as product specifications, text and visual information from the product image, etc. In this paper, we propose SMARTAVE, a Structure Mltimodal trAnsformeR for producT Attribute Value Extraction, which jointly encodes the structured product information from multiple modalities. Specifically, in SMARTAVE encoder, we introduce hyper-tokens to represent the modality-level information, and local-tokens to represent the original text and visual inputs. Structured attention patterns are designed among the hyper-tokens and local-tokens for learning effective product representation. The attribute values are then extracted based on the learned embeddings. We conduct extensive experiments on two multimodal product datasets. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods. Ablation studies validate the effectiveness of the structured attentions in modeling the multimodal product information.

pdf bib
Autoregressive Entity Generation for End-to-End Task-Oriented Dialog
Guanhuan Huang | Xiaojun Quan | Qifan Wang
Proceedings of the 29th International Conference on Computational Linguistics

Task-oriented dialog (TOD) systems are often required to interact with an external knowledge base (KB) to retrieve necessary entity (e.g., restaurants) information to support their response generation. Most current end-to-end TOD systems either retrieve the KB information explicitly or embed it into model parameters for implicit access. While the first approach demands scanning the KB at each turn of response generation, which is inefficient when the KB scales up, the second approach shows higher flexibility and efficiency. In either approach, the response shall contain attributes of the same entity, however the systems may generate a response with conflicting entities. To address this, we propose to generate the entity autoregressively before leveraging it to guide the response generation in an end-to-end system. To ensure entity consistency, we impose a trie constraint on the decoding of an entity. We also introduce a logit concatenation strategy to facilitate gradient backpropagation for end-to-end training. Experiments on MultiWOZ 2.1 single and CAMREST show that our system can generate more high-quality and entity-consistent responses in an end-to-end manner.

pdf bib
CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations
Borun Chen | Hongyin Tang | Jiahao Bu | Kai Zhang | Jingang Wang | Qifan Wang | Hai-Tao Zheng | Wei Wu | Liqian Yu
Proceedings of the 29th International Conference on Computational Linguistics

Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language representation. However, most current models use Chinese characters as inputs and are not able to encode semantic information contained in Chinese words. While recent pre-trained models incorporate both words and characters simultaneously, they usually suffer from deficient semantic interactions and fail to capture the semantic relation between words and characters. To address the above issues, we propose a simple yet effective PLM CLOWER, which adopts the Contrastive Learning Over Word and charactER representations. In particular, CLOWER implicitly encodes the coarse-grained information (i.e., words) into the fine-grained representations (i.e., characters) through contrastive learning on multi-grained information. CLOWER is of great value in realistic scenarios since it can be easily incorporated into any existing fine-grained based PLMs without modifying the production pipelines. Extensive experiments conducted on a range of downstream tasks demonstrate the superior performance of CLOWER over several state-of-the-art baselines.

pdf bib
Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation
Qifan Wang | Li Yang | Xiaojun Quan | Fuli Feng | Dongfang Liu | Zenglin Xu | Sinong Wang | Hao Ma
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Automatic question generation (AQG) is the task of generating a question from a given passage and an answer. Most existing AQG methods aim at encoding the passage and the answer to generate the question. However, limited work has focused on modeling the correlation between the target answer and the generated question. Moreover, unseen or rare word generation has not been studied in previous works. In this paper, we propose a novel approach which incorporates question generation with its dual problem, question answering, into a unified primal-dual framework. Specifically, the question generation component consists of an encoder that jointly encodes the answer with the passage, and a decoder that produces the question. The question answering component then re-asks the generated question on the passage to ensure that the target answer is obtained. We further introduce a knowledge distillation module to improve the model generalization ability. We conduct an extensive set of experiments on SQuAD and HotpotQA benchmarks. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

pdf bib
VIRT: Improving Representation-based Text Matching via Virtual Interaction
Dan Li | Yang Yang | Hongyin Tang | Jiahao Liu | Qifan Wang | Jingang Wang | Tong Xu | Wei Wu | Enhong Chen
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Text matching is a fundamental research problem in natural language understanding. Interaction-based approaches treat the text pair as a single sequence and encode it through cross encoders, while representation-based models encode the text pair independently with siamese or dual encoders. Interaction-based models require dense computations and thus are impractical in real-world applications. Representation-based models have become the mainstream paradigm for efficient text matching. However, these models suffer from severe performance degradation due to the lack of interactions between the pair of texts. To remedy this, we propose a Virtual InteRacTion mechanism (VIRT) for improving representation-based text matching while maintaining its efficiency. In particular, we introduce an interactive knowledge distillation module that is only applied during training. It enables deep interaction between texts by effectively transferring knowledge from the interaction-based model. A light interaction strategy is designed to fully leverage the learned interactive knowledge. Experimental results on six text matching benchmarks demonstrate the superior performance of our method over several state-of-the-art representation-based models. We further show that VIRT can be integrated into existing methods as plugins to lift their performances.

pdf bib
Federated Model Decomposition with Private Vocabulary for Text Classification
Zhuo Zhang | Xiangjing Hu | Lizhen Qu | Qifan Wang | Zenglin Xu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

With the necessity of privacy protection, it becomes increasingly vital to train deep neural models in a federated learning manner for natural language processing (NLP) tasks. However, recent studies show eavesdroppers (i.e., dishonest servers) can still reconstruct the private input in federated learning (FL). Such a data reconstruction attack relies on the mappings between vocabulary and associated word embedding in NLP tasks, which are unfortunately less studied in current FL methods. In this paper, we propose a fedrated model decomposition method that protects the privacy of vocabularies, shorted as FEDEVOCAB. In FEDEVOCAB, each participant keeps the local embedding layer in the local device and detaches the local embedding parameters from federated aggregation. However, it is challenging to train an accurate NLP model when the private mappings are unknown and vary across participants in a cross-device FL setting. To address this problem, we further propose an adaptive updating technique to improve the performance of local models. Experimental results show that FEDEVOCAB maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods.

pdf bib
XPrompt: Exploring the Extreme of Prompt Tuning
Fang Ma | Chen Zhang | Lei Ren | Jingang Wang | Qifan Wang | Wei Wu | Xiaojun Quan | Dawei Song
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Prompt tuning learns soft prompts to condition the frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of fine-tuning as the model scale increases, there is still a large performance gap between prompt tuning and fine-tuning for models of moderate and small scales (typically less than 11B parameters). In this paper, we empirically show that the trained prompt tokens can have a negative impact on a downstream task and thus degrade its performance. To bridge the gap, we propose a novel Prompt tuning model with an eXtremely small scale (XPrompt) under the regime of lottery tickets hypothesis. Specifically, XPrompt eliminates the negative prompt tokens at different granularity levels through a hierarchical structured pruning, yielding a more parameter-efficient prompt yet with a competitive performance. Comprehensive experiments are carried out on the SuperGLUE tasks, and the results indicate that XPrompt is able to close the performance gap at smaller model scales.

2020

pdf bib
ETC: Encoding Long and Structured Inputs in Transformers
Joshua Ainslie | Santiago Ontanon | Chris Alberti | Vaclav Cvicek | Zachary Fisher | Philip Pham | Anirudh Ravula | Sumit Sanghai | Qifan Wang | Li Yang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, “Extended Transformer Construction” (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a “Contrastive Predictive Coding” (CPC) pre-training objective allows ETC to encode structured inputs. We achieve state-of-the-art results on four natural language datasets requiring long and/or structured inputs.