Search Results for author:
Found 288 papers, 119 papers with code
TenTrans Large-Scale Multilingual Machine Translation System for WMT21
This paper describes TenTrans large-scale multilingual machine translation system for WMT 2021.
End-to-End Chinese Speaker Identification
End-to-end SI systems, on the other hand, are not limited by individual modules, but suffer from insufficient training data from the existing small-scale datasets.
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution
Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity.
From Polarity to Intensity: Mining Morality from Semantic Space
It only needs moral polarity labels, which are more robust and easier to acquire.
Instance-adaptive training with noise-robust losses against noisy labels
In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data.
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
面向人工智能伦理计算的中文道德词典构建方法研究(Construction of a Chinese Moral Dictionary for Artificial Intelligence Ethical Computing)
道德词典资源的建设是人工智能伦理计算的一个研究重点。由于道德行为复杂多样, 现有的英文道德词典分类体系并不完善, 而中文方面目前尚未有相关的词典资源, 理论体系和构建方法仍待探究。针对以上问题, 该文提出了面向人工智能伦理计算的中文道德词典构建任务, 设计了四类标签和四种类型, 得到包含25, 012个词的中文道德词典资源。实验结果表明, 该词典资源不仅能够使机器学会道德知识, 判断词的道德标签和类型, 而且能够为句子级别的道德文本分析提供数据支持。
结合深度学习和语言难度特征的句子可读性计算方法(The method of calculating sentence readability combined with deep learning and language difficulty characteristics)
本文提出了可读性语料库构建的改进方法, 基于该方法, 构建了规模更大的汉语句子可读性语料库。该语料库在句子绝对难度评估任务上的准确率达到0. 7869, 相对前人工作提升了0. 15以上, 证明了改进方法的有效性。将深度学习方法应用于汉语可读性评估, 探究了不同深度学习方法自动捕获难度特征的能力, 并进仛步探究了向深度学习特征中融入不同层面的语难度特征对模型整体性能的影响。实验结果显示, 不同深度学习模型的难度特征捕获能力不尽相同, 语言难度特征可以不同程度地提高深度学习模型的难度表征能力。
Lifelong Learning of Large Language Model based Agents: A Roadmap
This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents.
Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT
The pre-trained BERT model extracts semantic features from a raw Chinese character sequence and the NN based classifier predicts the polyphonic character's pronunciation according to BERT output.
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference.
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
In this work, we provide a thorough investigation of gist-based context compression methods to improve long-context processing in large language models.
Teaching LLMs to Refine with Tools
We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs.
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
In this work, we provide a detailed analysis of this issue and identify that unusually high attention entropy can be a key factor.
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
To gain deeper insights into this trend, we study over 1500 quantized LLM checkpoints of various sizes and at different training levels (undertrained or fully trained) in a controlled setting, deriving scaling laws for understanding the relationship between QiD and factors such as the number of training tokens, model size and bit width.
Federated Incremental Named Entity Recognition
In a more realistic scenario, local clients receive new entity types continuously, while new local clients collecting novel data may irregularly join the global FNER training.
Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
Additionally, through moral debates, we investigate the firmness of these models to their moral choices.
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
In this paper, we introduce an open-source framework designed to facilitate the development of multimodal web agent that can autonomously conduct real-world exploration and improve itself.
LoGU: Long-form Generation with Uncertainty Expressions
To tackle these challenges, we propose a refinement-based data collection framework and a two-stage training pipeline.
Atomic Calibration of LLMs in Long-Form Generations
Existing research on LLM calibration has primarily focused on short-form tasks, providing a single confidence score at the response level (macro calibration).
Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers
Traditional transformer models often allocate a fixed amount of computational resources to every input token, leading to inefficient and unnecessary computation.
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses.
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel.
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
In this paper, we propose DOTS, an approach enabling LLMs to reason dynamically via optimal reasoning trajectory search, tailored to the specific characteristics of each question and the inherent capability of the task-solving LLM.
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with code repositories.
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
In this paper, we study a new task of navigating to diverse target objects in a large number of scene types.
DeFine: Enhancing LLM Decision-Making with Factor Profiles and Analogical Reasoning
In this paper, we introduce DeFine, a new framework that constructs probabilistic factor profiles from complex scenarios.
Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks
Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs.
Restorative Speech Enhancement: A Progressive Approach Using SE and Codec Modules
In challenging environments with significant noise and reverberation, traditional speech enhancement (SE) methods often lead to over-suppressed speech, creating artifacts during listening and harming downstream tasks performance.
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited.
Video-to-Audio Generation with Fine-grained Temporal Semantics
With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e. g., Sora).
Preference Alignment Improves Language Model-Based TTS
Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts.
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
Latent diffusion models have shown promising results in text-to-audio (T2A) generation tasks, yet previous models have encountered difficulties in generation quality, computational cost, diffusion sampling, and data preparation.
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
Cognitive Kernel adopts a model-centric design.
Towards Diverse and Efficient Audio Captioning via Diffusion Models
We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning.
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?
To bridge this gap, we introduce DSBench, a comprehensive benchmark designed to evaluate data science agents with realistic tasks.
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot textbased speech editing and text-to-speech synthesis.
Neural Ambisonic Encoding For Multi-Speaker Scenarios Using A Circular Microphone Array
Spatial audio formats like Ambisonics are playback device layout-agnostic and well-suited for applications such as teleconferencing and virtual reality.
Comparing Discrete and Continuous Space LLMs for Speech Recognition
This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and unsupervised for both discrete and continuous types.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Advancing Multi-talker ASR Performance with Large Language Models
Recognizing overlapping speech from multiple speakers in conversational scenarios is one of the most challenging problem for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding.
DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems
In this paper, we introduce DocBench, a new benchmark designed to evaluate LLM-based document reading systems.
Video-to-Audio Generation with Hidden Alignment
In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques.
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO).
LiteSearch: Efficacious Tree Search for LLM
Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.
Scaling Synthetic Data Creation with 1,000,000,000 Personas
We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.
Abstraction-of-Thought Makes Language Models Better Reasoners
Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning.
When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives
Finally, the effectiveness of reasoning is influenced by narrative complexity, information density, and domain-specific terms, highlighting the challenges in analytical reasoning tasks.
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks.
Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment
In the field of multi-channel, multi-speaker Automatic Speech Recognition (ASR), the task of discerning and accurately transcribing a target speaker's speech within background noise remains a formidable challenge.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs.
MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
We evaluate the performance of various SOTA LLMs on the MathChat benchmark, and we observe that while these models excel in single turn question answering, they significantly underperform in more complex scenarios that require sustained reasoning and dialogue understanding.
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning.
Ranked #1 on
GSM8K
on GSM8K
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure.
Polarity Calibration for Opinion Summarization
To address this issue and make the summarizer express both sides of opinions, we introduce the concept of polarity calibration, which aims to align the polarity of output summary with that of input text.
Conceptual and Unbiased Reasoning in Language Models
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition.
Self-Consistency Boosts Calibration for Math Reasoning
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms. WoW) for evaluating multi-source dialogue knowledge selection and response generation.
Can Large Language Models do Analytical Reasoning?
Our analytical reasoning embodies the tasks of letting large language models count how many points each team scores in a quarter in the NBA and NFL games.
Collaborative decoding of critical tokens for boosting factuality of large language models
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model.
Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models
For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance.
Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns.
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems.
SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs
In this paper, we introduce four novel tasks centered around sports data analytics to evaluate the numerical reasoning and information fusion capabilities of LLMs.
SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization
Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations.
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.
MM-LLMs: Recent Advances in MultiModal Large Language Models
In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies.
Inconsistent dialogue responses and how to recover from them
One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem.
InFoBench: Evaluating Instruction Following Ability in Large Language Models
This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions.
Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention
This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of large volumes of information.
CLOMO: Counterfactual Logical Modification with Large Language Models
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs).
Deep Audio Zooming: Beamwidth-Controllable Neural Beamformer
Audio zooming, a signal processing technique, enables selective focusing and enhancement of sound signals from a specified region, attenuating others.
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
Recognizing the need for a comprehensive evaluation of LMM chart understanding, we also propose a MultiModal Chart Benchmark (\textbf{MMC-Benchmark}), a comprehensive human-annotated benchmark with nine distinct tasks evaluating reasoning capabilities over charts.
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
In response to these challenges, we introduces Chain-of-Noting (CoN), a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios.
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning
In this paper, we take a closer look at the self-verification abilities of LLMs in the context of logical reasoning, focusing on their ability to identify logical fallacies accurately.
TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs
We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and in-depth manner.
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios
Automatic speech recognition (ASR) on multi-talker recordings is challenging.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
UniX-Encoder: A Universal $X$-Channel Speech Encoder for Ad-Hoc Microphone Array Speech Processing
2) Multi-Task Capability: Beyond the single-task focus of previous systems, UniX-Encoder acts as a robust upstream model, adeptly extracting features for diverse tasks including ASR and speaker recognition.
On the Dimensionality of Sentence Embeddings
Therefore, we propose a two-step training method for sentence representation learning models, wherein the encoder and the pooler are optimized separately to mitigate the overall performance loss in low-dimension scenarios.
Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation
Multimodal machine translation (MMT) simultaneously takes the source sentence and a relevant image as input for translation.
uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs.
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on intrinsic changes.
The Trickle-down Impact of Reward (In-)consistency on RLHF
We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM.
Neural Network Augmented Kalman Filter for Robust Acoustic Howling Suppression
Acoustic howling suppression (AHS) is a critical challenge in audio communication systems.
Advancing Acoustic Howling Suppression through Recursive Training of Neural Networks
In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process.
Proposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark
Existing propositions often rely on logical constants for classification.
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge.
Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing.
LASER: LLM Agent with State-Space Exploration for Web Navigation
We evaluate our proposed LLM Agent with State-Space ExploRation (LASER) on both the WebShop task and amazon. com.
Unsupervised Multi-document Summarization with Holistic Inference
SRI balances the importance and diversity of a subset of sentences from the source documents and can be calculated in unsupervised and adaptive manners.
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) performance in new domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Bayes Risk Transducer: Transducer with Controllable Alignment Prediction
While the vanilla transducer does not have a prior preference for any of the valid paths, this work intends to enforce the preferred paths and achieve controllable alignment prediction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
We investigate how to elicit compositional generalization capabilities in large language models (LLMs).
Ranked #34 on
Math Word Problem Solving
on MATH
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Our approach uniquely considers the various annotation formats as different "views" and leverages them in training the model.
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Specifically, the detection technique achieves a recall of ~88% and the mitigation technique successfully mitigates 57. 6% of the correctly detected hallucinations.
Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Various applications of voice synthesis have been developed independently despite the fact that they generate "voice" as output in common.
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations
It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space.
PIVOINE: Instruction Tuning for Open-world Information Extraction
In particular, we construct INSTRUCTOPENWIKI, a substantial instruction tuning dataset for Open-world IE enriched with a comprehensive corpus, extensive annotations, and diverse instructions.
Open-Domain Event Graph Induction for Mitigating Framing Bias
However, none of the existing methods have explicitly addressed the issue of framing bias that is inherent in news articles.
Faithful Question Answering with Monte-Carlo Planning
In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps.
Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression
During offline training, a pre-processed signal obtained from the Kalman filter and an ideal microphone signal generated via teacher-forced training strategy are used to train the deep neural network (DNN).
Deep Learning for Joint Acoustic Echo and Acoustic Howling Suppression in Hybrid Meetings
In particular, the interplay between acoustic echo and acoustic howling in a hybrid meeting makes the joint suppression of them difficult.
Deep AHS: A Deep Learning Approach to Acoustic Howling Suppression
In this paper, we formulate acoustic howling suppression (AHS) as a supervised learning problem and propose a deep learning approach, called Deep AHS, to address it.
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation.
Friend-training: Learning from Models of Different but Related Tasks
Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes.
Neural Target Speech Extraction: An Overview
Humans can listen to a target speaker even in challenging acoustic conditions that have noise, reverberation, and interfering speakers.
NeuralKalman: A Learnable Kalman Filter for Acoustic Echo Cancellation
The robustness of the Kalman filter to double talk and its rapid convergence make it a popular approach for addressing acoustic echo cancellation (AEC) challenges.
OASum: Large-Scale Open Domain Aspect-based Summarization
Specifically, zero/few-shot and fine-tuning results show that the model pre-trained on our corpus demonstrates a strong aspect or query-focused generation ability compared with the backbone model.
TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR
Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse.
ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion
However, there has been limited research on the zero-shot KBC settings, where we need to deal with unseen entities and relations that emerge in a constantly growing knowledge base.
Deep Neural Mel-Subband Beamformer for In-car Speech Separation
While current deep learning (DL)-based beamforming techniques have been proved effective in speech separation, they are often designed to process narrow-band (NB) frequencies independently which results in higher computational costs and inference times, making them unsuitable for real-world use.
Efficient Zero-shot Event Extraction with Context-Definition Alignment
We argue that using the static embedding of the event type name might not be enough because a single word could be ambiguous, and we need a sentence to define the type semantics accurately.
Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing
Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors.
Toward Unifying Text Segmentation and Long Document Summarization
The problem is only exacerbated by a lack of segmentation in transcripts of audio/video recordings.
Ranked #6 on
Text Summarization
on Pubmed
Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
In this paper, we develop a novel semi-parametric language model architecture, Knowledge-in-Context (KiC), which empowers a parametric text-to-text language model with a knowledge-rich external memory.
Ranked #5 on
Question Answering
on StoryCloze
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
To this end, we propose a comprehensive logical reasoning explanation form.
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence.
Salience Allocation as Guidance for Abstractive Summarization
Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.
Ranked #7 on
Abstractive Text Summarization
on CNN / Daily Mail
Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination
Large-scale pretrained language models have made significant advances in solving downstream language understanding tasks.
Ranked #2 on
Visual Commonsense Tests
on ViComTe-color
Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks
Besides predicting the target sequence, a side product of CTC is to predict the alignment, which is the most probable input-long sequence that specifies a hard aligning relationship between the input and target units.
Cross-Lingual Speaker Identification Using Distant Supervision
Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks.
Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks
Notably, our proposed $\text{Zemi}_\text{LARGE}$ outperforms T0-3B by 16% on all seven evaluation tasks while being 3. 9x smaller in model size.
C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
On the basis of the pretrained CSSL model, we further propose to employ a negative sample free SSL objective (i. e., DINO) to fine-tune the speaker embedding network.
Diffsound: Discrete Diffusion Model for Text-to-sound Generation
In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder (VQ-VAE), a decoder, and a vocoder.
Ranked #15 on
Audio Generation
on AudioCaps
(FD metric)
Hierarchical Context Tagging for Utterance Rewriting
HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context.
Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability.
Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE
We leverage recent advancements in self-supervised speech representation learning as well as speech synthesis front-end techniques for system development.
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level and shows superior performance on both monolingual and multilingual ASR tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back.
Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
In our experiment on the VCTK dataset, we demonstrate that content embeddings derived from the conditional DSVAE overcome the randomness and achieve a much better phoneme classification accuracy, a stabilized vocalization and a better zero-shot VC performance compared with the competitive DSVAE baseline.
Distant finetuning with discourse relations for stance classification
Approaches for the stance classification task, an important task for understanding argumentation in debates and detecting fake news, have been relying on models which deal with individual debate topics.