Search Results for author:
Found 85 papers, 56 papers with code
NJU’s submission to the WMT20 QE Shared Task
This paper describes our system of the sentence-level and word-level Quality Estimation Shared Task of WMT20.
Towards Multi-label Unknown Intent Detection
In this paper, we propose a more desirable task, multi-label unknown intent detection, to detect whether the utterance contains the unknown intent, in which each utterance may contain multiple intents.
Learning from Adjective-Noun Pairs: A Knowledge-enhanced Framework for Target-Oriented Multimodal Sentiment Classification
Target-oriented multimodal sentiment classification (TMSC) is a new subtask of aspect-based sentiment analysis, which aims to determine the sentiment polarity of the opinion target mentioned in a (sentence, image) pair.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation
In this work, we propose a novel BiTIIMT system, Bilingual Text-Infilling for Interactive Neural Machine Translation.
Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification
However, the simple extension of meta-learning approaches to multi-label classification is sub-optimal for LMTC tasks due to long-tailed label distribution and coexisting of few- and zero-shot scenarios.
PATS: Process-Level Adaptive Thinking Mode Switching
Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty.
Internal Bias in Reasoning Models leads to Overthinking
Through further interpretability experiments, we find that this behavior is largely driven by the model's excessive attention to the input section, which amplifies the influence of internal bias on its decision-making process.
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks.
Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data
The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing challenges like data scarcity for low-resource languages and catastrophic forgetting.
Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From
The ability of cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment of large language models (LLMs), where the model extracts context information in one language based on requests in another language.
FamilyTool: A Multi-hop Personalized Tool Use Benchmark
To bridge this gap, we introduce FamilyTool, a novel benchmark grounded in a family-based knowledge graph (KG) that simulates personalized, multi-hop tool use scenarios.
A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mapping
Finally, this approach is applied during the testing phase, rapidly adapting to domain variations through meta-training tasks on support sets, consequently enhancing the model's capability to transfer domain knowledge effectively.
R-PRM: Reasoning-Driven Process Reward Modeling
Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning.
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
Image captioning has been a longstanding challenge in vision-language research.
Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task.
Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning
The focus of research into modelling long context has been on how to model position and there has been little investigation into other important aspects of language modelling such as instruction tuning.
Extend Adversarial Policy Against Neural Machine Translation via Unknown Token
Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness.
Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark
This paper addresses the issue of entity bias in relation extraction tasks, where models tend to rely on entity mentions rather than context.
Enhancing Mathematical Reasoning in LLMs with Background Operators
For each mathematical problem, we develop a Prolog solution that includes problem-specific predicates and intermediate predicates derived from these background operators, ensuring that each solution adheres to the defined operator set.
Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
We find that pretrained LLMs establish learning preferences similar to humans, i. e., preferences towards formal texts and texts with fewer spelling errors, resulting in faster learning and more favorable treatment of knowledge in data with such features when facing conflicts.
MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing
Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages.
Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
Extensive experiments on 12 mainstream MLLMs, such as GPT-4V and Gemini-Pro Vision, demonstrate that these models exhibit significant hallucinations on Hallu-PI, which is not observed in unperturbed scenarios.
PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment
In this paper, we propose PreAlign, a framework that establishes multilingual alignment prior to language model pretraining.
Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping
Decoding by contrasting layers (DoLa), is designed to improve the generation quality of large language models (LLMs) by contrasting the prediction probabilities between an early exit output (amateur logits) and the final output (expert logits).
Large Language Models are Limited in Out-of-Context Knowledge Reasoning
Using this dataset, we evaluated several LLMs and discovered that their proficiency in this aspect is limited, regardless of whether the knowledge is trained in a separate or adjacent training settings.
Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners
Recently, Large Language Models (LLMs) have shown impressive language capabilities.
Why Not Transform Chat Large Language Models to Non-English?
For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.
The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
Bridging the significant gap between large language model's English and non-English performance presents a great challenge.
Improved Paraphrase Generation via Controllable Latent Diffusion
Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel.
Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly
In this paper, we propose CLiKA, a systematic framework to assess the cross-lingual knowledge alignment of LLMs in the Performance, Consistency and Conductivity levels, and explored the effect of multilingual pretraining and instruction tuning on the degree of alignment.
MixRED: A Mix-lingual Relation Extraction Dataset
Relation extraction is a critical task in the field of natural language processing with numerous real-world applications.
MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT), yet they suffer from high computational cost and latency.
Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models
Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension.
EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving
This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving.
Cobra Effect in Reference-Free Image Captioning Metrics
If a certain metric has flaws, it will be exploited by the model and reflected in the generated sentences.
Question Translation Training for Better Multilingual Reasoning
A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training.
Multi-Candidate Speculative Decoding
One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model.
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
To enhance reasoning abilities in non-dominant languages, we propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO), aiming to align the reasoning processes in other languages with the dominant language.
Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation
This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task.
A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies.
Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models
For answering the factual questions, which is more challenging, the average error rate of all evaluated LLMs is 36. 1%.
Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention
Recent large language models (LLMs) have revealed strong abilities to understand natural language.
IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems
We present IMTLab, an open-source end-to-end interactive machine translation (IMT) system platform that enables researchers to quickly build IMT systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
Towards Better Chain-of-Thought Prompting Strategies: A Survey
Chain-of-Thought (CoT), a step-wise and coherent reasoning chain, shows its impressive strength when used as a prompting strategy for large language models (LLM).
Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task
We generate pseudo MQM data using parallel data from the WMT translation task.
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task.
Extrapolating Large Language Models to Non-English by Aligning Languages
We start from targeting individual languages by performing cross-lingual instruction-tuning (CoIT) on LLaMA, i. e. tuning it with translation task data and cross-lingual general task data to obtain cross-lingual models (x-LLaMAs), and formulate underlying scaling laws to investigate the advantages of using scalable translation data.
Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation
Next, we propose an Expression Alignment (EA) mechanism for audio and text.
Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Experiments on our proposed datasets demonstrate that popular VLMs underperform in the food domain compared with their performance in the general domain.
ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora
Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns.
BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training
In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems.
INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation
We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parameters.
Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions
Secondly, we find that LLMs' ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages.
AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time.
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT).
kNN-BOX: A Unified Framework for Nearest Neighbor Generation
Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT).
CoP: Factual Inconsistency Detection by Controlling the Preference
To separate the preference for factual consistency, we propose an unsupervised framework named CoP by controlling the preference of the generation model with the help of prompt.
What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation
kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus.
Structure-Unified M-Tree Coding Solver for MathWord Problem
As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years.
Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings
In this paper, we consider a novel research problem: music-to-text synaesthesia.
What Makes for Automatic Reconstruction of Pulmonary Segments
The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing.
A Numerical Reasoning Question Answering System with Fine-grained Retriever and the Ensemble of Multiple Generators for FinQA
Here, we propose a numerical reasoning question answering system to answer numerical reasoning questions among financial text and table data sources, consisting of a retriever module, a generator module, and an ensemble module.
Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities
By enforcing the entities' embeddings close to their associated prototypes' embeddings, our approach can effectively encourage the global semantic similarities of entities -- that can be far away in the KG -- connected by the same relation.
Analyzing the Intensity of Complaints on Social Media
Furthermore, we conduct a comprehensive linguistic analysis around complaints, including the connections between complaints and sentiment, and a cross-lingual comparison for complaints expressions used by Chinese and English speakers.
$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
To address this challenge, we propose a novel query embedding model, namely Cone Embeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation.
Non-Parametric Online Learning from Human Feedback for Neural Machine Translation
We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected translations are used to improve the neural machine translation (NMT) system.
Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.
When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation
Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems.
Energy-based Unknown Intent Detection with Data Manipulation
Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.
Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021
To address this challenge, we propose a framework that integrates three components -- a basic model ComplEx-CMRC, a rule miner AMIE 3, and an inference model to predict missing links.
Adaptive Nearest Neighbor Machine Translation
On four benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively filter out the noises in retrieval results and significantly outperforms the vanilla kNN-MT model.
DirectQE: Direct Pretraining for Machine Translation Quality Estimation
However, we argue that there are gaps between the predictor and the estimator in both data quality and training objectives, which preclude QE models from benefiting from a large number of parallel corpora more directly.
Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
Thus REDER enables reversible machine translation by simply flipping the input and output ends.
Non-Autoregressive Translation by Learning Target Categorical Codes
Non-autoregressive Transformer is a promising text generation model.
Ranked #7 on
Machine Translation
on WMT2014 German-English
Dual Side Deep Context-aware Modulation for Social Recommendation
Specifically, we first proposed a novel graph neural network to model the social relation and collaborative relation, and on top of high-order relations, a dual side deep context-aware modulation is introduced to capture the friends' information and item attraction.
Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
TACT is inspired by the observation that the semantic correlation between two relations is highly correlated to their topological structure in knowledge graphs.
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios.
Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification
In this paper, we propose a novel joint model, Opinion Transmission Network (OTN), to exploit the potential bridge between ALSC and AOWE to achieve the goal of facilitating them simultaneously.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis
To facilitate the research of ABSA, NLPCC 2020 Shared Task 2 releases a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Rethinking Document-level Neural Machine Translation
This paper does not aim at introducing a novel model for document-level neural machine translation.
MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response
Furthermore, we experiment the proposed method on an in-house, retrospective dataset of real-world non-small cell lung cancer patients under anti-PD-1 immunotherapy.
Ranked #1 on
Text-To-Speech Synthesis
on 20000 utterances
(using extra training data)
PNAT: Non-autoregressive Transformer by Position Learning
However, position modeling of output words is an essential problem in non-autoregressive text generation.
