Search Results for author:
Found 250 papers, 94 papers with code
Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation
Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence.
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing
In the coarse labeling stage, the joint model outputs a bracketed tree, in which each node corresponds to one of four labels (i. e., phrase, subphrase, word, subword).
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)
“数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时, 很少有工作严格对比不同标注方法, 以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队, 以依存句法数据标注为案例, 实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法, 得到了一些初步的结论。”
RST Discourse Parsing with Second-Stage EDU-Level Pre-training
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i. e. element discourse unit (EDU). To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP). We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective, leading a 2. 1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
Prediction Difference Regularization against Perturbation for Neural Machine Translation
Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years.
HW-TSC at SemEval-2022 Task 3: A Unified Approach Fine-tuned on Multilingual Pretrained Model for PreTENS
In order to verify whether our model could also perform better in subtask 2 (the regression subtask), the ranking score is transformed into classification labels by an up-sampling strategy.
HW-TSC at SemEval-2022 Task 7: Ensemble Model Based on Pretrained Models for Identifying Plausible Clarifications
This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases.
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
HW-TSC’s Participation in the WMT 2021 News Translation Shared Task
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing
Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains.
Stacked AMR Parsing with Silver Data
In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin.
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation
In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT.
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection
Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA).
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
This paper describes in detail the construction process and data statistics of DuSQL.
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation
The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track.
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity.
Synchronous Refinement for Neural Machine Translation
Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner.
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis
This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities.
Speaker-Aware Discourse Parsing on Multi-Party Dialogues
It is believed that speaker interactions are helpful for this task.
Ranked #2 on
Discourse Parsing
on STAC
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
To address this issue, we for the first time apply a dynamic matching network on the shared-private model for semi-supervised cross-domain dependency parsing.
KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues.
OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks
The experimental results demonstrate our approach's effectiveness and efficiency in verifying DNNs' robustness against various occlusions, and its ability to generate counterexamples when these DNNs are not robust.
SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation
In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.
Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
However, these methods fail to build connections between candidates and thus cannot model the inter-dependent relation during retrieval.
P-Transformer: Towards Better Document-to-Document Neural Machine Translation
To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.
QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks
Experimental results on QNNs with different quantization bits confirm the effectiveness and efficiency of our approach, e. g., two orders of magnitude faster and able to solve more verification tasks in the same time limit than the state-of-the-art methods.
ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation
In this paper, we propose a novel transfer learning method for NMT, namely ConsistTL, which can continuously transfer knowledge from the parent model during the training of the child model.
Improving Simultaneous Machine Translation with Monolingual Data
Preliminary experiments on En-Zh and En-Ja news domain corpora demonstrate that monolingual data can significantly improve translation quality (e. g., +3. 15 BLEU on En-Zh).
Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling
Existing research generally treats Chinese character as a minimum unit for representation.
Ranked #1 on
Machine Translation
on WMT2017 Chinese-English
BBReach: Tight and Scalable Black-Box Reachability Analysis of Deep Reinforcement Learning Systems
In this paper we propose a novel, tight and scalable reachability analysis approach for DRL systems.
DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation
We observe that existing approaches only rely on overestimated domains, while the corresponding tight approximation may not necessarily be tight on its actual domain.
WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation
Keyphrase generation aims to automatically generate short phrases summarizing an input document.
Third-Party Aligner for Neural Word Alignments
Word alignment is to find translationally equivalent words between source and target sentences.
Revisiting Grammatical Error Correction Evaluation and Beyond
Pretraining-based (PT-based) automatic evaluation metrics (e. g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e. g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods.
Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
Chinese word segmentation (CWS) models have achieved very high performance when the training data is sufficient and in-domain.
Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
Existing methods mainly perform continual training to mitigate such a misalignment.
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
We apply BABERT for feature induction of Chinese sequence labeling tasks.
Ranked #1 on
Chinese Word Segmentation
on MSRA
Chinese Named Entity Recognition
Chinese Word Segmentation
+2
Extending Phrase Grounding with Pronouns in Visual Dialogues
First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions.
SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser
Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences.
Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones.
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios.
SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks.
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes
First, we propose a unified policy abstraction theory, containing three types of policy abstraction associated to policy features at different levels.
SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset
As the first session-level Chinese dataset, CHASE contains two separate parts, i. e., 2, 003 sessions manually constructed from scratch (CHASE-C), and 3, 456 sessions translated from English SParC (CHASE-T).
Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks
Considerable efforts have been devoted to finding the so-called tighter approximations to obtain more precise verification results.
Brain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System
We explore the effectiveness of BTA for satisfaction modeling in two popular information access scenarios, i. e., search and recommendation.
Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval
By making the REM and DAMs disentangled, DDR enables a flexible training paradigm in which REM is trained with supervision once and DAMs are trained with unsupervised data.
Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network
Normalizing flow models have been used successfully for generative image super-resolution (SR) by approximating complex distribution of natural images to simple tractable distribution in latent space through Invertible Neural Networks (INN).
Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr.
Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation
To solve this problem, we present a plug-in Hierarchical Tree Structure-aware (HTS) method, which not only learns the relationship of FSL and pretext tasks, but more importantly, can adaptively select and aggregate feature representations generated by pretext tasks to maximize the performance of FSL tasks.
Towards Representation Alignment and Uniformity in Collaborative Filtering
Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance.
Adversarial Self-Attention for Language Understanding
Deep neural models (e. g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness.
A Federated Reinforcement Learning Method with Quantization for Cooperative Edge Caching in Fog Radio Access Networks
In this paper, cooperative edge caching problem is studied in fog radio access networks (F-RANs).
Medical Dialogue Response Generation with Pivotal Information Recalling
To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i. e., knowledge-aware dialogue graph encoder and recall-enhanced generator.
A Survey on the Fairness of Recommender Systems
First, we summarize fairness definitions in the recommendation and provide several views to classify fairness issues.
Neural Network Verification with Proof Production
In this work, we present a novel mechanism for enhancing Simplex-based DNN verifiers with proof production capabilities: the generation of an easy-to-check witness of unsatisfiability, which attests to the absence of errors.
MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset
1) Based on a frame-free annotation methodology, we avoid writing complex frames for new predicates.
Graph Convolutional Network Based Semi-Supervised Learning on Multi-Speaker Meeting Data
In this work, we present a GCN-based approach for semi-supervised learning.
Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models
For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation.
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually.
MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction
This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7, 063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources.
Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations
Recent works of opinion expression identification (OEI) rely heavily on the quality and scale of the manually-constructed training corpus, which could be extremely difficult to satisfy.
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, auto-regressive (AR) generation.
BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation
Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks.
ConvSearch: A Open-Domain Conversational Search Behavior Dataset
25 search agents and 51 users are recruited for the field study that lasts about 45 days.
A Survey on Dropout Methods and Experimental Verification in Recommendation
Among various methods of coping with overfitting, dropout is one of the representative ways.
Image-text Retrieval: A Survey on Recent Research and Development
On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective.
Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging
In recent years, large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks.
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
Inspired by this, we design a new architecture, {\it ODE Transformer}, which is analogous to the Runge-Kutta method that is well motivated in ODE.
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence.
Ranked #3 on
Aspect-Based Sentiment Analysis
on SemEval 2014 Task 4 Sub Task 2
(using extra training data)
Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation
Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner.
Recommendation Unlearning
From the perspective of utility, if a system's utility is damaged by some bad data, the system needs to forget these data to regain utility.
A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition
Then, we employ a label sequence decoder to output the predicted labels in a top-down manner, where the predicted higher-level labels are directly used to guide the label prediction at the current level.
Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18.
Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation
An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the combination of raw data and distilled data.
Diformer: Directional Transformer for Neural Machine Translation
In this paper, we aim to close the gap by preserving the original objective of AR and NAR under a unified framework.
Learning Semantic-Aligned Feature Representation for Text-based Person Search
In this paper, we propose a semantic-aligned embedding method for text-based person search, in which the feature alignment across modalities is achieved by automatically learning the semantic-aligned visual features and textual features.
C$^2$-Rec: An Effective Consistency Constraint for Sequential Recommendation
Sequential recommendation methods play an important role in real-world recommender systems.
Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph
Most previous studies of document-level event extraction mainly focus on building argument chains in an autoregressive way, which achieves a certain success but is inefficient in both training and inference.
Ranked #3 on
Document-level Event Extraction
on ChFinAnn
GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method
GreenPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans.
Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing
Moreover, we propose a simple constrained Viterbi procedure to ensure the legality of the output graph according to the constraints of the SRL structure.
Interpreting Dense Retrieval as Mixture of Topics
Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success.
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security.
Web Search via an Efficient and Effective Brain-Machine Interface
While search technologies have evolved to be robust and ubiquitous, the fundamental interaction paradigm has remained relatively stable for decades.
Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community.
Ranked #1 on
Semantic Role Labeling
on OntoNotes
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space.
Stochastic Variance Reduced Ensemble Adversarial Attack
Black-box adversarial attack has attracted much attention for its practical use in deep learning applications, and it is very challenging as there is no access to the architecture and weights of the target model.
Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations
Starting from the resurgence of deep learning, language models (LMs) have never been so popular.
DM-CT: Consistency Training with Data and Model Perturbation
The common approach of consistency training is performed on the data-level, which typically utilizes the data augmentation strategy (or adversarial training) to make the predictions from the augmented input and the original input to be consistent, so that the model is more robust and attains better generalization ability.
GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds
It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale benchmark -- the Stanford 3D Indoor Segmentation (S3DIS) dataset.
Why Don't You Click: Neural Correlates of Non-Click Behaviors in Web Search
Inspired by these findings, we conduct supervised learning tasks to estimate the usefulness of non-click results with brain signals and conventional information (i. e., content and context factors).
Physics-informed Neural Network for Nonlinear Dynamics in Fiber Optics
A physics-informed neural network (PINN) that combines deep learning with physics is studied to solve the nonlinear Schr\"odinger equation for learning nonlinear dynamics in fiber optics.
The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
Towards a Better Understanding Human Reading Comprehension with Brain Signals
In this paper, we carefully design a lab-based user study to investigate brain activities during reading comprehension.
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size.
Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training
To this end, we propose two pre-training tasks.
XLPT-AMR: Cross-Lingual Pre-Training via Multi-Task Learning for Zero-Shot AMR Parsing and Text Generation
We hope that knowledge gained while learning for English AMR parsing and text generation can be transferred to the counterparts of other languages.
A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues
Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
Ranked #3 on
Discourse Parsing
on STAC
Exploiting Rich Syntax for Better Knowledge Base Question Answering
Previous works for encoding questions mainly focus on the word sequences, but seldom consider the information from syntactic trees. In this paper, we propose an approach to learn syntax-based representations for KBQA.
R-Drop: Regularized Dropout for Neural Networks
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #4 on
Machine Translation
on WMT2014 English-French
Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning
Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural networks.
A Large-Scale Rich Context Query and Recommendation Dataset in Online Knowledge-Sharing
To the best of our knowledge, this is the largest real-world interaction dataset for personalized recommendation.
Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation
A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary.
Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction
Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and is typically through learning linear projections to align monolingual word representation spaces.
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents
Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.
An In-depth Study on Internal Structure of Chinese Words
Several previous works on syntactic parsing propose to annotate shallow word-internal structures for better utilizing character-level information.
Optimizing Dense Retrieval Model Training with Hard Negatives
ADORE replaces the widely-adopted static hard negative sampling method with a dynamic one to directly optimize the ranking performance.
Not All Attention Is All You Need
Beyond the success story of pre-trained language models (PrLMs) in recent natural language processing, they are susceptible to over-fitting due to unusual large model size.
Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network (PHMN).
R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work.
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries.
Cortical Surface Shape Analysis Based on Alexandrov Polyhedra
Shape analysis has been playing an important role in early diagnosis and prognosis of neurodegenerative diseases such as Alzheimer's diseases (AD).
Code Summarization with Structure-induced Transformer
Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of programmer developing.
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents.
Ranked #1 on
Key information extraction
on SROIE
THUIR@COLIEE-2020: Leveraging Semantic Understanding and Exact Matching for Legal Case Retrieval and Entailment
We participated in the two case law tasks, i. e., the legal case retrieval task and the legal case entailment task.
Multi-grained Chinese Word Segmentation with Weakly Labeled Data
Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1. 12 and 5. 97 on NEWS and BAIKE data in F1.
Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations
The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training data when there is only a small-scale out-domain labeled data.
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition
We tackle implicit discourse relation recognition.
Improving Relation Extraction with Relational Paraphrase Sentences
In this paper, we propose an alternative approach to improve RE systems via enriching diverse expressions by relational paraphrase sentences.
Semantic Role Labeling with Heterogeneous Syntactic Knowledge
Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention.
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue
As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information.
Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction
The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different.
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
Concretely, we design a novel interpretation scheme whereby the loss of mis-predicted frequent and sparse answers of the same question type is distinctly exhibited during the late training phase.
Token Drop mechanism for Neural Machine Translation
Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs.
Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.
Tight Lower Complexity Bounds for Strongly Convex Finite-Sum Optimization
Finite-sum optimization plays an important role in the area of machine learning, and hence has triggered a surge of interest in recent years.
Improving AMR Parsing with Sequence-to-Sequence Pre-training
In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance.
Ranked #11 on
AMR Parsing
on LDC2017T10
(using extra training data)
A new dataset of dog breed images and a benchmark for fine-grained classification
It is currently the largest dataset for fine-grained classification of dogs, including130 dog breeds and 70, 428 real-world images.
Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition
However, these approaches only augment the representations of samples with available semantics while ignoring the query set, which loses the potential for the improvement and may lead to a shift between the modalities combination and the pure-visual representation.
Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)
An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work.
Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation
The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture.
Neural Logic Reasoning
Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs.
Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels
The key insight of our approach is that the robustness verification problem of DNNs can be solved by verifying sub-problems of DNNs, one per target label.
Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation
Recently, the leading performance of human pose estimation is dominated by heatmap based methods.
Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary.
Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks
The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.
Jointly Non-Sampling Learning for Knowledge Graph Enhanced Recommendation
However, existing KG enhanced recommendation methods have largely focused on exploring advanced neural network architectures to better investigate the structural information of KG.
Aspect Sentiment Classification with Document-level Sentiment Preference Modeling
This justifies the importance of the document-level sentiment preference information to ASC and the effectiveness of our approach capturing such information.
RepBERT: Contextualized Text Embeddings for First-Stage Retrieval
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized embeddings.
Eicient Non-Sampling Factorization Machines for Optimal Context-Aware Recommendation
Factorization Machines (FM) with negative sampling is a popular solution for context-aware recommendation.
Efficient Second-Order TreeCRF for Neural Dependency Parsing
Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data.
Ranked #1 on
Dependency Parsing
on CoNLL-2009
Fully-Corrective Gradient Boosting with Squared Hinge: Fast Learning Rates and Early Stopping
Boosting is a well-known method for improving the accuracy of weak learners in machine learning.
Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?
In the pre deep learning era, part-of-speech tags have been considered as indispensable ingredients for feature engineering in dependency parsing.
PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
Stochastic Item Descent Method for Large Scale Equal Circle Packing Problem
Inspired by its success in deep learning, we apply the idea of SGD with batch selection of samples to a classic optimization problem in decision version.
AE-OT-GAN: Training GANs from data specific latent distribution
Though generative adversarial networks (GANs) areprominent models to generate realistic and crisp images, they often encounter the mode collapse problems and arehard to train, which comes from approximating the intrinsicdiscontinuous distribution transform map with continuousDNNs.