Search Results for author:
Found 109 papers, 32 papers with code
OPERA: Operation-Pivoted Discrete Reasoning over Text
To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.
基于实体信息增强及多粒度融合的多文档摘要(Multi-Document Summarization Based on Entity Information Enhancement and Multi-Granularity Fusion)
“神经网络模型的快速发展使得多文档摘要可以获得人类可读的流畅的摘要, 对大规模的数据进行预训练可以更好的从自然语言文本中捕捉更丰富的语义信息, 并更好的作用于下游任务。目前很多的多文档摘要的工作也应用了预训练模型(如BERT)并取得了一定的效果, 但是这些预训练模型不能更好的从文本中捕获事实性知识, 没有考虑到多文档文本的结构化的实体-关系信息, 本文提出了基于实体信息增强和多粒度融合的多文档摘要模型MGNIE, 将实体关系信息融入预训练模型ERNIE中, 增强知识事实以获得多层语义信息, 解决摘要生成的事实一致性问题。进而从多种粒度进行多文档层次结构的融合建模, 以词信息、实体信息以及句子信息捕捉长文本信息摘要生成所需的关键信息点。本文设计的模型, 在国际标准评测数据集MultiNews上对比强基线模型效果和竞争力获得较大提升。”
On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning
Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to newly specified few-shot tasks with potentially unseen intent categories.
Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction
Despite their progress in high-resource language settings, unsupervised bilingual lexicon induction (UBLI) models often fail on corpora with low-resource distant language pairs due to insufficient initialization.
Jointly Learning Guidance Induction and Faithful Summary Generation via Conditional Variational Autoencoders
Abstractive summarization can generate high quality results with the development of the neural network.
CAN-GRU: a Hierarchical Model for Emotion Recognition in Dialogue
In the first layer, in order to extract textual features of utterances, we propose a convolutional self-attention network(CAN).
Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring
Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT).
Cross-Domain Bilingual Lexicon Induction via Pretrained Language Models
Bilingual Lexicon Induction (BLI) is generally based on common domain data to obtain monolingual word embedding, and by aligning the monolingual word embeddings to obtain the cross-lingual embeddings which are used to get the word translation pairs.
Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
Surprisingly, experiments applying the advanced speculative decoding method EAGLE-2 to various quantized models reveal that the memory benefits from 4-bit weight quantization are diminished by the computational load from speculative decoding.
Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory
The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concerns about their ability to accurately reflect authentic model capabilities.
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs).
Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
The o1-Like LLMs are transforming AI by simulating human cognitive processes, but their performance in multilingual machine translation (MMT) remains underexplored.
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities
In this paper, we propose DuplexMamba, a Mamba-based end-to-end multimodal duplex model for speech-to-text conversation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation
Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.
LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks.
Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM
This vulnerability poses significant risks to the real-world applications.
PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment
Reinforcement Learning from Human Feedback (RLHF) has been proven to be an effective method for preference alignment of large language models (LLMs) and is widely used in the post-training process of LLMs.
LLM-based Translation Inference with Iterative Bilingual Understanding
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance.
Dynamic Planning for LLM-based Graphical User Interface Automation
However, a key challenge lies in devising effective plans to guide action prediction in GUI tasks, though planning have been widely recognized as effective for decomposing complex tasks into a series of steps.
Mitigating the Bias of Large Language Model Evaluation
Recently, there has been a trend of evaluating the Large Language Model (LLM) quality in the flavor of LLM-as-a-Judge, namely leveraging another LLM to evaluate the current output quality.
Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
Different from the traditional translation tasks, classical Chinese poetry translation requires both adequacy and fluency in translating culturally and historically significant content and linguistic poetic elegance.
A Survey on Human Preference Learning for Large Language Models
In this survey, we review the progress in exploring human preference learning for LLMs from a preference-centered perspective, covering the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs.
STAR: Scale-wise Text-to-image generation via Auto-Regressive representations
We present STAR, a text-to-image model that employs scale-wise auto-regressive paradigm.
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation.
DesignProbe: A Graphic Design Benchmark for Multimodal Large Language Models
This complexity makes the comprehension of graphic design challenging, for it needs the capability to both recognize the design elements and understand the design.
Dual Instruction Tuning with Large Language Models for Mathematical Reasoning
To alleviate this problem, we propose a dual instruction tuning strategy to meticulously model mathematical reasoning from both forward and reverse directions.
Self-Evaluation of Large Language Model based on Glass-box Features
The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods.
An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4
Alternatively, other works have fine-tuned judge models based on open-source LLMs as the evaluator.
Decomposed Meta-Learning for Few-Shot Sequence Labeling
With the detected mention spans, we further leverage the MAML-enhanced span-level prototypical network for few-shot type classification.
Ranked #1 on
Slot Filling
on SNIPS
(F1 (1-shot) avg metric)
LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
In fact, the output of LoRA (product of LoRA parameter and hidden state), directly impacts the final results.
Spot the Error: Non-autoregressive Graphic Layout Generation with Wireframe Locator
Furthermore, based on our observation that pixel space is more sensitive in capturing spatial patterns of graphic layouts (e. g., overlap, alignment), we propose a learning-based locator to detect erroneous tokens which takes the wireframe image rendered from the generated layout sequence as input.
StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models
The ability to fine-tune generative models for text-to-image generation tasks is crucial, particularly facing the complexity involved in accurately interpreting and visualizing textual inputs.
HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge
To alleviate these challenges, we propose a self-iterative framework for multi-hop program generation (HopPG) over heterogeneous knowledge, which leverages the previous execution results to retrieve supporting facts and generate subsequent programs hop by hop.
Learning and Evaluating Human Preferences for Conversational Head Generation
In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions.
Interactive Conversational Head Generation
Based on ViCo and ViCo-X, we define three novel tasks targeting the interaction modeling during the face-to-face conversation: 1) responsive listening head generation making listeners respond actively to the speaker with non-verbal signals, 2) expressive talking head generation guiding speakers to be aware of listeners' behaviors, and 3) conversational head generation to integrate the talking/listening ability in one interlocutor.
Visual-Aware Text-to-Speech
Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction.
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition
Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes well to a target language by leveraging labeled data in a given source language.
Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making.
MuGER$^2$: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering
To preserve the advantage and eliminate the disadvantage of different granularity evidence, we propose MuGER$^2$, a Multi-Granularity Evidence Retrieval and Reasoning approach.
UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation
Question answering requiring discrete reasoning, e. g., arithmetic computing, comparison, and counting, over knowledge is a challenging task.
OPERA:Operation-Pivoted Discrete Reasoning over Text
To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.
Document-Level Relation Extraction with Sentences Importance Estimation and Focusing
Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences.
Ranked #5 on
Dialog Relation Extraction
on DialogRE
(F1c (v1) metric)
Dialog Relation Extraction
Document-level Relation Extraction
+2
Decomposed Meta-Learning for Few-Shot Named Entity Recognition
Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples.
Ranked #6 on
Few-shot NER
on Few-NERD (INTER)
CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection
Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data.
Responsive Listening Head Generation: A Benchmark Dataset and Baseline
Automatically synthesizing listening behavior that actively responds to a talking head, is critical to applications such as digital human, virtual agents and social robots.
A Neural Conversation Generation Model via Equivalent Shared Memory Investigation
Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation.
EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension
Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text.
Issues with Entailment-based Zero-shot Text Classification
The general format of natural language inference (NLI) makes it tempting to be used for zero-shot text classification by casting any target label into a sentence of hypothesis and verifying whether or not it could be entailed by the input, aiming at generic classification applicable on any specified label space.
HITMI\&T at SemEval-2021 Task 5: Integrating Transformer and CRF for Toxic Spans Detection
This paper introduces our system at SemEval-2021 Task 5: Toxic Spans Detection.
Discriminative Reasoning for Document-level Relation Extraction
Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i. e., pattern recognition, logical reasoning, coreference reasoning, etc.)
Ranked #24 on
Relation Extraction
on DocRED
Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Induction
Embeddings of two languages are made to match with each other by rotating and scaling.
Gumbel-Attention for Multi-modal Machine Translation
Multi-modal machine translation (MMT) improves translation quality by introducing visual information.
Ranked #5 on
Multimodal Machine Translation
on Multi30K
Demystifying Learning of Unsupervised Neural Machine Translation
Unsupervised Neural Machine Translation or UNMT has received great attention in recent years.
Document-Level Relation Extraction with Reconstruction
In document-level relation extraction (DocRE), graph structure is generally used to encode relation information in the input document to classify the relation category between each entity pair, and has greatly advanced the DocRE task over the past several years.
Ranked #35 on
Relation Extraction
on DocRED
CN-HIT-MI.T at SemEval-2020 Task 8: Memotion Analysis Based on BERT
Internet memes emotion recognition is focused by many researchers.
Robust Machine Reading Comprehension by Learning Soft labels
Neural models have achieved great success on the task of machine reading comprehension (MRC), which are typically trained on hard labels.
Cross Copy Network for Dialogue Generation
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e. g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation.
AI-lead Court Debate Case Investigation
The multi-role judicial debate composed of the plaintiff, defendant, and judge is an important part of the judicial trial.
Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training
This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations.
Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.
End-to-End Speech Translation with Adversarial Training
End-to-End speech translation usually leverages audio-to-text parallel data to train an available speech translation model which has shown impressive results on various speech translation tasks.
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the non-discrimination distribution to the discrimination distribution.
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs.
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.
Understanding Learning Dynamics for Neural Machine Translation
Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process.
Detecting and Understanding Generalization Barriers for Neural Machine Translation
Generalization to unseen instances is our eternal pursuit for all data-driven models.
Look-into-Object: Self-supervised Structure Modeling for Object Recognition
Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category.
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training
Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community.
Modeling Future Cost for Neural Machine Translation
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.
Multimodal Matching Transformer for Live Commenting
In this work, we aim to improve the relevance between live comments and videos by modeling the cross-modal interactions among different modalities.
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization
Many Data Augmentation (DA) methods have been proposed for neural machine translation.
Mitigating Annotation Artifacts in Natural Language Inference Datasets to Improve Cross-dataset Generalization Ability
This irregularity makes the evaluation results over-estimated and affects models' generalization ability.
Duality Regularization for Unsupervised Bilingual Lexicon Induction
Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation.
Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation
However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.
Sentence-Level Agreement for Neural Machine Translation
The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation
In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.
Understanding and Improving Hidden Representations for Neural Machine Translation
Multilayer architectures are currently the gold standard for large-scale neural machine translation.
Improving Neural Machine Translation with Neural Syntactic Distance
The explicit use of syntactic information has been proved useful for neural machine translation (NMT).
CN-HIT-MI.T at SemEval-2019 Task 6: Offensive Language Identification Based on BiLSTM with Double Attention
Our macro-averaged F1-score in sub-task A is 0. 768, ranking 28/103.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.
Deep Attention Neural Tensor Network for Visual Question Answering
First, we model one of the pairwise interaction (e. g., image and question) by bilinear features, which is further encoded with the third dimension (e. g., answer) to be a triplet by bilinear tensor product.
Neural Document Summarization by Jointly Learning to Score and Select Sentences
In this paper, we present a novel end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences.
Ranked #10 on
Extractive Text Summarization
on CNN / Daily Mail
Forest-Based Neural Machine Translation
Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors.
Table-to-Text: Describing Table Region with Natural Language
The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table.
Syntax-Directed Attention for Neural Machine Translation
In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction.
Context-Aware Smoothing for Neural Machine Translation
In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information.
Neural Machine Translation with Source Dependency Representation
Source dependency information has been successfully introduced into statistical machine translation.
Automatic Dataset Augmentation
Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years.
Constraint-Based Question Answering with Knowledge Graph
WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent knowledge-based question answering (KBQA) work.
A Distribution-based Model to Learn Bilingual Word Embeddings
We introduce a distribution based model to learn bilingual word embeddings from monolingual data.
Building A Case-based Semantic English-Chinese Parallel Treebank
This Treebank is a part of a semantic corpus building project, which aims to build a semantic bilingual corpus annotated with syntactic, semantic cases and word senses.
Augmenting Phrase Table by Employing Lexicons for Pivot-based SMT
Pivot language is employed as a way to solve the data sparseness problem in machine translation, especially when the data for a particular language pair does not exist.
Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries.
