Search Results for author:
Found 37 papers, 14 papers with code
基于多任务学习的生成式阅读理解(Generative Reading Comprehension via Multi-task Learning)
生成式阅读理解是机器阅读理解领域一项新颖且极具挑战性的研究。与主流的抽取式阅读理解相比, 生成式阅读理解模型不再局限于从段落中抽取答案, 而是能结合问题和段落生成自然和完整的表述作为答案。然而, 现有的生成式阅读理解模型缺乏对答案在段落中的边界信息以及对问题类型信息的理解。为解决上述问题, 本文提出一种基于多任务学习的生成式阅读理解模型。该模型在训练阶段将答案生成任务作为主任务, 答案抽取和问题分类任务作为辅助任务进行多任务学习, 同时学习和优化模型编码层参数;在测试阶段加载模型编码层进行解码生成答案。实验结果表明, 答案抽取模型和问题分类模型能够有效提升生成式阅读理解模型的性能。
Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation
The former aims to adapt to characteristics of low-resource languages during encoding, while the latter adapts to translation experiences learned from high-resource languages.
Capturing Conversational Interaction for Question Answering via Global History Reasoning
Conversational Question Answering (ConvQA) is required to answer the current question, conditioned on the observable paragraph-level context and conversation history.
Winnowing Knowledge for Multi-choice Question Answering
However, the current reasoning models suffer from the noises in the retrieved knowledge.
Feature-level Incongruence Reduction for Multimodal Translation
Besides of linguistic features in captions, MNMT allows visual(image) features to be used.
CVAE-based Re-anchoring for Implicit Discourse Relation Classification
Training implicit discourse relation classifiers suffers from data sparsity.
Unregulated Chinese-to-English Data Expansion Does NOT Work for Neural Event Detection
The survey of translations suggests that the mistakenly-aligned triggers in the expanded data negatively influences the retraining process.
UniVision: A Unified Framework for Vision-Centric 3D Perception
The past few years have witnessed the rapid development of vision-centric 3D perception in autonomous driving.
HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting
Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating.
UFO: Unified Fact Obtaining for Commonsense Question Answering
UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question.
CopyNE: Better Contextual ASR by Copying Named Entities
However, traditional token-level ASR models have struggled with accurately transcribing entities due to the problem of homophonic and near-homophonic tokens.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension
The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts.
KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering
Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60. 91% at the primary canonical metric Inc@3.
Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e. g., Pseudo-LiDAR methods.
Ranked #1 on
Monocular 3D Object Detection
on KITTI Cyclist Hard
(using extra training data)
Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation
We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation.
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models.
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.
DuReader\_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements.
Single-photon imaging over 200 km
Long-range active imaging has widespread applications in remote sensing and target recognition.
NUT-RC: Noisy User-generated Text-oriented Reading Comprehension
Most existing RC models are developed on formal datasets such as news articles and Wikipedia documents, which severely limit their performances when directly applied to the noisy and informal texts in social media.
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition
We tackle implicit discourse relation recognition.
Argumentation Mining on Essays at Multi Scales
Recent research mainly models the task as a sequence tagging problem and deal with all the argumentation components at word level.
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification
We tackle implicit discourse relation classification, a task of automatically determining semantic relationships between arguments.
Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction
The current aspect extraction methods suffer from boundary errors.
Ranked #2 on
Aspect Extraction
on SemEval 2015 Task 12
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements.
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner.
Negative Focus Detection via Contextual Attention Mechanism
For the sake of understanding a negated statement, it is critical to precisely detect the negative focus in context.
Using active learning to expand training data for implicit discourse relation recognition
We tackle discourse-level relation recognition, a problem of determining semantic relations between text spans.
Adversarial Feature Adaptation for Cross-lingual Relation Classification
In this paper, we come up with a feature adaptation approach for cross-lingual relation classification, which employs a generative adversarial network (GAN) to transfer feature representations from one language with rich annotated data to another language with scarce annotated data.
Incorporating Image Matching Into Knowledge Acquisition for Event-Oriented Relation Recognition
In particular, we incorporate image processing into the acquisition of similar event instances, including the utilization of images for visually representing event scenes, and the use of the neural network based image matching for approximate calculation between events.
Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection
Due to the ability of encoding and mapping semantic information into a high-dimensional latent feature space, neural networks have been successfully used for detecting events to a certain extent.
Image-Image Search for Comparable Corpora Construction
We present a novel method of comparable corpora construction.
