Search Results for author:
Found 86 papers, 31 papers with code
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs).
An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing
Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET).
On the Relationship between Neural Machine Translation and Word Alignment
We find that although NMT models are difficult to capture word alignment for CFT words but these words do not sacrifice translation quality significantly, which provides an explanation why NMT is more successful for translation yet worse for word alignment compared to statistical machine translation.
Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing
In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance.
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.
Fine-grained Entity Typing without Knowledge Base
Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision.
DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance
To alleviate memory burden during inference of large language models (LLMs), numerous studies have focused on compressing the KV cache by exploring aspects such as attention sparsity.
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
In a systematic way, we investigate a widely asked question: Do LLMs really understand what they say?, which relates to the more familiar term Stochastic Parrot.
Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task
While LLMs have exhibited strong performance on various NLP tasks, it is noteworthy that most of these tasks rely on utilizing the vast amount of knowledge encoded in LLMs' parameters, rather than solving new problems without prior knowledge.
Large Language Models Can Self-Improve in Long-context Reasoning
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning.
Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning.
A Survey on the Honesty of Large Language Models
Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge.
TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
In this paper, we analyze the core mechanisms of previous predominant adversarial attack methods, revealing that 1) the distributions of importance score differ markedly among victim models, restricting the transferability; 2) the sequential attack processes induces substantial time overheads.
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i. e., the candidate target word is treated as a label).
Rethinking Targeted Adversarial Attacks For Neural Machine Translation
To this end, this paper presents a new setting for NMT targeted adversarial attacks that could lead to reliable attacking results.
On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications.
On the Hallucination in Simultaneous Machine Translation
It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information.
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
However, the performance of LLMs on standard knowledge and reasoning benchmarks tends to suffer from deterioration at the latter stage of the SFT process, echoing the phenomenon of alignment tax.
Cross-lingual Contextualized Phrase Retrieval
In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs).
When Graph Data Meets Multimodal: A New Paradigm for Graph Understanding and Reasoning
Graph data is ubiquitous in the physical world, and it has always been a challenge to efficiently model graph structures using a unified paradigm for the understanding and reasoning on various graphs.
Context Consistency between Training and Testing in Simultaneous Machine Translation
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context.
Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks
In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks.
Rethinking Word-Level Auto-Completion in Computer-Aided Translation
Word-Level Auto-Completion (WLAC) plays a crucial role in Computer-Assisted Translation.
DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation.
Towards General Error Diagnosis via Behavioral Testing in Machine Translation
Behavioral testing offers a crucial means of diagnosing linguistic errors and assessing capabilities of NLP models.
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.
TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild
We release our dataset, model, and demo to foster future research in the area of multimodal instruction following.
Ranked #230 on
Visual Question Answering
on MM-Vet
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
Rethinking Translation Memory Augmented Neural Machine Translation
The finding demonstrates that TM-augmented NMT is good at the ability of fitting data (i. e., lower bias) but is more sensitive to the fluctuations in the training data (i. e., higher variance), which provides an explanation to a recently reported contradictory phenomenon on the same translation task: TM-augmented NMT substantially advances vanilla NMT under the high-resource scenario whereas it fails under the low-resource scenario.
Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model
Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks.
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments.
Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer
Nearest Neighbor Machine Translation ($k$NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval.
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption.
Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance
Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than static word embeddings.
Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory
In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round.
Ranked #1 on
Text Summarization
on X-Sum
Federated Nearest Neighbor Machine Translation
To protect user privacy and meet legal regulations, federated learning (FL) is attracting significant attention.
Neural Machine Translation with Contrastive Translation Memories
Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios.
Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications.
Discourse-Aware Graph Networks for Textual Logical Reasoning
In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
Current practices in metric evaluation focus on one single dataset, e. g., Newstest dataset in each year's WMT Metrics Shared Task.
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
Efficient Sub-structured Knowledge Distillation
Specifically, we transfer the knowledge from a teacher model to its student model by locally matching their predictions on all sub-structures, instead of the whole output space.
On the Evaluation Metrics for Paraphrase Generation
In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance than their reference-based counterparts.
A Survey on Retrieval-Augmented Text Generation
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models.
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions.
Rethinking Negative Sampling for Handling Missing Entity Annotations
Negative sampling is highly effective in handling missing annotations for named entity recognition (NER).
Engage the Public: Poll Question Generation for Social Media Posts
This paper presents a novel task to generate poll questions for social media posts.
Ranked #3 on
Answer Generation
on WeiboPolls
Fast and Accurate Neural Machine Translation with Translation Memory
It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks.
TexSmart: A System for Enhanced Natural Language Understanding
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation
In this paper, we propose the task of general word-level autocompletion (GWLAN) from a real-world CAT scenario, and construct the first public benchmark to facilitate research in this topic.
TranSmart: A Practical Interactive Machine Translation System
Automatic machine translation is super efficient to produce translations yet their quality is not guaranteed.
Neural Machine Translation with Monolingual Translation Memory
Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal.
Assessing Dialogue Systems with Distribution Distances
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
Neural Sequence Segmentation as Determining the Leftmost Segments
Prior methods to text segmentation are mostly at token level.
Demystifying Learning of Unsupervised Neural Machine Translation
Unsupervised Neural Machine Translation or UNMT has received great attention in recent years.
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Segmenting Natural Language Sentences via Lexical Unit Analysis
In this work, we present Lexical Unit Analysis (LUA), a framework for general sequence segmentation tasks.
Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition
Experiments on synthetic datasets and real-world datasets show that our model is robust to unlabeled entity problem and surpasses prior baselines.
Touch Editing: A Flexible One-Time Interaction Approach for Translation
We propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting.
On the Branching Bias of Syntax Extracted from Pre-trained Language Models
Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing.
Evaluating Explanation Methods for Neural Machine Translation
Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods.
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.
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization
Many Data Augmentation (DA) methods have been proposed for neural machine translation.
Regularized Context Gates on Transformer for Machine Translation
This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer.
Neural Machine Translation with Noisy Lexical Constraints
Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints.
On the Word Alignment from Neural Machine Translation
Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models.
Understanding and Improving Hidden Representations for Neural Machine Translation
Multilayer architectures are currently the gold standard for large-scale neural machine translation.
Target Foresight Based Attention for Neural Machine Translation
In neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it does not make use of any information of this target foresight word at all.
Automatic Article Commenting: the Task and Dataset
Comments of online articles provide extended views and improve user engagement.
Neural Machine Translation with Source Dependency Representation
Source dependency information has been successfully introduced into statistical machine translation.
Instance Weighting for Neural Machine Translation Domain Adaptation
Instance weighting has been widely applied to phrase-based machine translation domain adaptation.
Neural Machine Translation with Supervised Attention
The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words.
