arXiv subjects

Haiqin Yang

Publications and source records attributed to Haiqin Yang.

36 records · Page 2Linked to original sources

arXiv2021

RefBERT: Compressing BERT by Referencing to Pre-computed Representations

Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of parameters and suffer from high computation and latency in real-world applications. It is desirable to reduce the computation overhead of the models for fast training and inference while keeping the model performance in downstream applications. Several lines of work utilize knowledge distillation to compress the teacher model to a smaller student model. However, they usually discard the teacher's knowledge when in inference. Differently, in this paper, we propose RefBERT to leverage the knowledge learned from the teacher, i.e., facilitating the pre-computed BERT representation on the reference sample and compressing BERT into a smaller student model. To guarantee our proposal, we provide theoretical justification on the loss function and the usage of reference samples. Significantly, the theoretical result shows that including the pre-computed teacher's representations on the reference samples indeed increases the mutual information in learning the student model. Finally, we conduct the empirical evaluation and show that our RefBERT can beat the vanilla TinyBERT over 8.1\% and achieves more than 94\% of the performance of $\BERTBASE$ on the GLUE benchmark. Meanwhile, RefBERT is 7.4x smaller and 9.5x faster on inference than BERT$_{\rm BASE}$.

cs.CL↗

arXiv2021

MagicPai at SemEval-2021 Task 7: Method for Detecting and Rating Humor Based on Multi-Task Adversarial Training

This paper describes MagicPai's system for SemEval 2021 Task 7, HaHackathon: Detecting and Rating Humor and Offense. This task aims to detect whether the text is humorous and how humorous it is. There are four subtasks in the competition. In this paper, we mainly present our solution, a multi-task learning model based on adversarial examples, for task 1a and 1b. More specifically, we first vectorize the cleaned dataset and add the perturbation to obtain more robust embedding representations. We then correct the loss via the confidence level. Finally, we perform interactive joint learning on multiple tasks to capture the relationship between whether the text is humorous and how humorous it is. The final result shows the effectiveness of our system.

cs.AI↗

arXiv2021

Sattiy at SemEval-2021 Task 9: An Ensemble Solution for Statement Verification and Evidence Finding with Tables

Question answering from semi-structured tables can be seen as a semantic parsing task and is significant and practical for pushing the boundary of natural language understanding. Existing research mainly focuses on understanding contents from unstructured evidence, e.g., news, natural language sentences, and documents. The task of verification from structured evidence, such as tables, charts, and databases, is still less explored. This paper describes sattiy team's system in SemEval-2021 task 9: Statement Verification and Evidence Finding with Tables (SEM-TAB-FACT). This competition aims to verify statements and to find evidence from tables for scientific articles and to promote the proper interpretation of the surrounding article. In this paper, we exploited ensemble models of pre-trained language models over tables, TaPas and TaBERT, for Task A and adjust the result based on some rules extracted for Task B. Finally, in the leaderboard, we attain the F1 scores of 0.8496 and 0.7732 in Task A for the 2-way and 3-way evaluation, respectively, and the F1 score of 0.4856 in Task B.

cs.AI↗

arXiv2021

PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation

This paper presents the PALI team's winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In the implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain first place in all four cross-lingual tasks.

cs.AI↗

arXiv2021

Progressive Open-Domain Response Generation with Multiple Controllable Attributes

It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems. However, existing methods can generate responses with only one controllable attribute or lack a flexible way to generate them with multiple controllable attributes. In this paper, we propose a Progressively trained Hierarchical Encoder-Decoder (PHED) to tackle this task. More specifically, PHED deploys Conditional Variational AutoEncoder (CVAE) on Transformer to include one aspect of attributes at one stage. A vital characteristic of the CVAE is to separate the latent variables at each stage into two types: a global variable capturing the common semantic features and a specific variable absorbing the attribute information at that stage. PHED then couples the CVAE latent variables with the Transformer encoder and is trained by minimizing a newly derived ELBO and controlled losses to produce the next stage's input and produce responses as required. Finally, we conduct extensive evaluations to show that PHED significantly outperforms the state-of-the-art neural generation models and produces more diverse responses as expected.

cs.CL↗

arXiv2021

Emotion Dynamics Modeling via BERT

Emotion dynamics modeling is a significant task in emotion recognition in conversation. It aims to predict conversational emotions when building empathetic dialogue systems. Existing studies mainly develop models based on Recurrent Neural Networks (RNNs). They cannot benefit from the power of the recently-developed pre-training strategies for better token representation learning in conversations. More seriously, it is hard to distinguish the dependency of interlocutors and the emotional influence among interlocutors by simply assembling the features on top of RNNs. In this paper, we develop a series of BERT-based models to specifically capture the inter-interlocutor and intra-interlocutor dependencies of the conversational emotion dynamics. Concretely, we first substitute BERT for RNNs to enrich the token representations. Then, a Flat-structured BERT (F-BERT) is applied to link up utterances in a conversation directly, and a Hierarchically-structured BERT (H-BERT) is employed to distinguish the interlocutors when linking up utterances. More importantly, a Spatial-Temporal-structured BERT, namely ST-BERT, is proposed to further determine the emotional influence among interlocutors. Finally, we conduct extensive experiments on two popular emotion recognition in conversation benchmark datasets and demonstrate that our proposed models can attain around 5\% and 10\% improvement over the state-of-the-art baselines, respectively.

cs.AI↗

arXiv2021

KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph

Entity synonyms discovery is crucial for entity-leveraging applications. However, existing studies suffer from several critical issues: (1) the input mentions may be out-of-vocabulary (OOV) and may come from a different semantic space of the entities; (2) the connection between mentions and entities may be hidden and cannot be established by surface matching; and (3) some entities rarely appear due to the long-tail effect. To tackle these challenges, we facilitate knowledge graphs and propose a novel entity synonyms discovery framework, named \emph{KGSynNet}. Specifically, we pre-train subword embeddings for mentions and entities using a large-scale domain-specific corpus while learning the knowledge embeddings of entities via a joint TransC-TransE model. More importantly, to obtain a comprehensive representation of entities, we employ a specifically designed \emph{fusion gate} to adaptively absorb the entities' knowledge information into their semantic features. We conduct extensive experiments to demonstrate the effectiveness of our \emph{KGSynNet} in leveraging the knowledge graph. The experimental results show that the \emph{KGSynNet} improves the state-of-the-art methods by 14.7\% in terms of hits@3 in the offline evaluation and outperforms the BERT model by 8.3\% in the positive feedback rate of an online A/B test on the entity linking module of a question answering system.

cs.AI↗

arXiv2021

Automatic Intent-Slot Induction for Dialogue Systems

Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema and asking many domain experts to annotate the corresponding utterances, upon which neural models are trained. This procedure brings the challenges of information sharing hindering, out-of-schema, or data sparsity in open-domain dialogue systems. To tackle these challenges, we explore a new task of {\em automatic intent-slot induction} and propose a novel domain-independent tool. That is, we design a coarse-to-fine three-step procedure including Role-labeling, Concept-mining, And Pattern-mining (RCAP): (1) role-labeling: extracting keyphrases from users' utterances and classifying them into a quadruple of coarsely-defined intent-roles via sequence labeling; (2) concept-mining: clustering the extracted intent-role mentions and naming them into abstract fine-grained concepts; (3) pattern-mining: applying the Apriori algorithm to mine intent-role patterns and automatically inferring the intent-slot using these coarse-grained intent-role labels and fine-grained concepts. Empirical evaluations on both real-world in-domain and out-of-domain datasets show that: (1) our RCAP can generate satisfactory SLU schema and outperforms the state-of-the-art supervised learning method; (2) our RCAP can be directly applied to out-of-domain datasets and gain at least 76\% improvement of F1-score on intent detection and 41\% improvement of F1-score on slot filling; (3) our RCAP exhibits its power in generic intent-slot extractions with less manual effort, which opens pathways for schema induction on new domains and unseen intent-slot discovery for generalizable dialogue systems.

cs.AI↗

arXiv2020

Block-term Tensor Neural Networks

Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily adapted to neural network models, such as CNNs and RNNs. In particular, the inputs and the outputs in BT-layers are reshaped into low-dimensional high-order tensors with a similar or improved representation power. Sufficient experiments have demonstrated that BT-layers in CNNs and RNNs can achieve a very large compression ratio on the number of parameters while preserving or improving the representation power of the original DNNs.

cs.LG↗

arXiv2020

Making Online Sketching Hashing Even Faster

Data-dependent hashing methods have demonstrated good performance in various machine learning applications to learn a low-dimensional representation from the original data. However, they still suffer from several obstacles: First, most of existing hashing methods are trained in a batch mode, yielding inefficiency for training streaming data. Second, the computational cost and the memory consumption increase extraordinarily in the big data setting, which perplexes the training procedure. Third, the lack of labeled data hinders the improvement of the model performance. To address these difficulties, we utilize online sketching hashing (OSH) and present a FasteR Online Sketching Hashing (FROSH) algorithm to sketch the data in a more compact form via an independent transformation. We provide theoretical justification to guarantee that our proposed FROSH consumes less time and achieves a comparable sketching precision under the same memory cost of OSH. We also extend FROSH to its distributed implementation, namely DFROSH, to further reduce the training time cost of FROSH while deriving the theoretical bound of the sketching precision. Finally, we conduct extensive experiments on both synthetic and real datasets to demonstrate the attractive merits of FROSH and DFROSH.

cs.LG↗

arXiv2020

Effective Data-aware Covariance Estimator from Compressed Data

Estimating covariance matrix from massive high-dimensional and distributed data is significant for various real-world applications. In this paper, we propose a data-aware weighted sampling based covariance matrix estimator, namely DACE, which can provide an unbiased covariance matrix estimation and attain more accurate estimation under the same compression ratio. Moreover, we extend our proposed DACE to tackle multiclass classification problems with theoretical justification and conduct extensive experiments on both synthetic and real-world datasets to demonstrate the superior performance of our DACE.

cs.LG↗

arXiv2020

Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion

Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings. This paper describes our submitted solution, Hierarchical Context Enhanced Dialogue System (HCEDS), for this task. The main motivation of our system is to comprehensively explore the potential of hierarchical context for sufficiently understanding complex dialogues. More specifically, we apply BERT to capture token-level information and employ the attention mechanism to capture sentence-level information. The results listed in the leaderboard show that our system achieves first place in automatic evaluation and the second place in human evaluation.

cs.AI↗

arXiv2019

BERT Meets Chinese Word Segmentation

Chinese word segmentation (CWS) is a fundamental task for Chinese language understanding. Recently, neural network-based models have attained superior performance in solving the in-domain CWS task. Last year, Bidirectional Encoder Representation from Transformers (BERT), a new language representation model, has been proposed as a backbone model for many natural language tasks and redefined the corresponding performance. The excellent performance of BERT motivates us to apply it to solve the CWS task. By conducting intensive experiments in the benchmark datasets from the second International Chinese Word Segmentation Bake-off, we obtain several keen observations. BERT can slightly improve the performance even when the datasets contain the issue of labeling inconsistency. When applying sufficiently learned features, Softmax, a simpler classifier, can attain the same performance as that of a more complicated classifier, e.g., Conditional Random Field (CRF). The performance of BERT usually increases as the model size increases. The features extracted by BERT can be also applied as good candidates for other neural network models.

cs.CL↗

arXiv2019

HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition

In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured. We therefore propose a hierarchical Gated Recurrent Unit (HiGRU) framework with a lower-level GRU to model the word-level inputs and an upper-level GRU to capture the contexts of utterance-level embeddings. Moreover, we promote the framework to two variants, HiGRU with individual features fusion (HiGRU-f) and HiGRU with self-attention and features fusion (HiGRU-sf), so that the word/utterance-level individual inputs and the long-range contextual information can be sufficiently utilized. Experiments on three dialogue emotion datasets, IEMOCAP, Friends, and EmotionPush demonstrate that our proposed HiGRU models attain at least 8.7%, 7.5%, 6.0% improvement over the state-of-the-art methods on each dataset, respectively. Particularly, by utilizing only the textual feature in IEMOCAP, our HiGRU models gain at least 3.8% improvement over the state-of-the-art conversational memory network (CMN) with the trimodal features of text, video, and audio.

cs.CL↗

arXiv2017

BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition

Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its deployment to situations with light computing resources. Researchers resort to the redundancy in the weights of DNNs and attempt to find how fewer parameters can be chosen while preserving the accuracy at the same time. Although several promising results have been shown along this research line, most existing methods either fail to significantly compress a well-trained deep network or require a heavy fine-tuning process for the compressed network to regain the original performance. In this paper, we propose the \textit{Block Term} networks (BT-nets) in which the commonly used fully-connected layers (FC-layers) are replaced with block term layers (BT-layers). In BT-layers, the inputs and the outputs are reshaped into two low-dimensional high-order tensors, then block-term decomposition is applied as tensor operators to connect them. We conduct extensive experiments on benchmark datasets to demonstrate that BT-layers can achieve a very large compression ratio on the number of parameters while preserving the representation power of the original FC-layers as much as possible. Specifically, we can get a higher performance while requiring fewer parameters compared with the tensor train method.

stat.ML↗

arXiv2016

A deep learning approach for predicting the quality of online health expert question-answering services

Currently, a growing number of health consumers are asking health-related questions online, at any time and from anywhere, which effectively lowers the cost of health care. The most common approach is using online health expert question-answering (HQA) services, as health consumers are more willing to trust answers from professional physicians. However, these answers can be of varying quality depending on circumstance. In addition, as the available HQA services grow, how to predict the answer quality of HQA services via machine learning becomes increasingly important and challenging. In an HQA service, answers are normally short texts, which are severely affected by the data sparsity problem. Furthermore, HQA services lack community features such as best answer and user votes. Therefore, the wisdom of the crowd is not available to rate answer quality. To address these problems, in this paper, the prediction of HQA answer quality is defined as a classification task. First, based on the characteristics of HQA services and feedback from medical experts, a standard for HQA service answer quality evaluation is defined. Next, based on the characteristics of HQA services, several novel non-textual features are proposed, including surface linguistic features and social features. Finally, a deep belief network (DBN)-based HQA answer quality prediction framework is proposed to predict the quality of answers by learning the high-level hidden semantic representation from the physicians' answers. Our results prove that the proposed framework overcomes the problem of overly sparse textual features in short text answers and effectively identifies high-quality answers.

cs.IR↗

arXiv2016

Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee

In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning. Recently, various non-oblivious randomized reduction methods have been developed and deployed for solving many numerical problems such as matrix product approximation, low-rank matrix approximation, etc. However, they are less explored for the machine learning tasks, e.g., classification. More seriously, the theoretical analysis of excess risk bounds for risk minimization, an important measure of generalization performance, has not been established for non-oblivious randomized reduction methods. It therefore remains an open problem what is the benefit of using them over previous oblivious random projection based approaches. To tackle these challenges, we propose an algorithmic framework for employing non-oblivious randomized reduction method for general empirical risk minimizing in machine learning tasks, where the original high-dimensional features are projected onto a random subspace that is derived from the data with a small matrix approximation error. We then derive the first excess risk bound for the proposed non-oblivious randomized reduction approach without requiring strong assumptions on the training data. The established excess risk bound exhibits that the proposed approach provides much better generalization performance and it also sheds more insights about different randomized reduction approaches. Finally, we conduct extensive experiments on both synthetic and real-world benchmark datasets, whose dimension scales to $O(10^7)$, to demonstrate the efficacy of our proposed approach.

cs.LG↗

arXiv2012

Response Aware Model-Based Collaborative Filtering

Previous work on recommender systems mainly focus on fitting the ratings provided by users. However, the response patterns, i.e., some items are rated while others not, are generally ignored. We argue that failing to observe such response patterns can lead to biased parameter estimation and sub-optimal model performance. Although several pieces of work have tried to model users' response patterns, they miss the effectiveness and interpretability of the successful matrix factorization collaborative filtering approaches. To bridge the gap, in this paper, we unify explicit response models and PMF to establish the Response Aware Probabilistic Matrix Factorization (RAPMF) framework. We show that RAPMF subsumes PMF as a special case. Empirically we demonstrate the merits of RAPMF from various aspects.

cs.LG↗