Search Results for author: Yikang Shen

Found 43 papers, 15 papers with code

Unsupervised Dependency Graph Network

1 code implementation ACL 2022 Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie zhou, Aaron Courville

We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task.

Language Modelling Masked Language Modeling +2

Phrase-aware Unsupervised Constituency Parsing

no code implementations ACL 2022 Xiaotao Gu, Yikang Shen, Jiaming Shen, Jingbo Shang, Jiawei Han

Recent studies have achieved inspiring success in unsupervised grammar induction using masked language modeling (MLM) as the proxy task.

Constituency Parsing Language Modelling +1

CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding

no code implementations6 Nov 2023 Junyan Li, Delin Chen, Yining Hong, Zhenfang Chen, Peihao Chen, Yikang Shen, Chuang Gan

A communication token is generated by the LLM following a visual entity or a relation, to inform the detection network to propose regions that are relevant to the sentence generated so far.

CoLA Question Answering +4

Autonomous Tree-search Ability of Large Language Models

no code implementations14 Oct 2023 Zheyu Zhang, Zhuorui Ye, Yikang Shen, Chuang Gan

This approach yield a greater improvement compared to the ones fine-tuned on CoT data.

Decision Making

The Consensus Game: Language Model Generation via Equilibrium Search

no code implementations13 Oct 2023 Athul Paul Jacob, Yikang Shen, Gabriele Farina, Jacob Andreas

When applied to question answering and other text generation tasks, language models (LMs) may be queried generatively (by sampling answers from their output distribution) or discriminatively (by using them to score or rank a set of candidate outputs).

Language Modelling Question Answering +2

Sparse Universal Transformer

no code implementations11 Oct 2023 Shawn Tan, Yikang Shen, Zhenfang Chen, Aaron Courville, Chuang Gan

The Universal Transformer (UT) is a variant of the Transformer that shares parameters across its layers.

TextPSG: Panoptic Scene Graph Generation from Textual Descriptions

no code implementations ICCV 2023 Chengyang Zhao, Yikang Shen, Zhenfang Chen, Mingyu Ding, Chuang Gan

To tackle this problem, we propose a new framework TextPSG consisting of four modules, i. e., a region grouper, an entity grounder, a segment merger, and a label generator, with several novel techniques.

Graph Generation Panoptic Scene Graph Generation +1

GraphText: Graph Reasoning in Text Space

no code implementations2 Oct 2023 Jianan Zhao, Le Zhuo, Yikang Shen, Meng Qu, Kai Liu, Michael Bronstein, Zhaocheng Zhu, Jian Tang

Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language.

Text Generation

Aligning Large Multimodal Models with Factually Augmented RLHF

no code implementations25 Sep 2023 Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liang-Yan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context.

Image Captioning Language Modelling

ModuleFormer: Modularity Emerges from Mixture-of-Experts

1 code implementation7 Jun 2023 Yikang Shen, Zheyu Zhang, Tianyou Cao, Shawn Tan, Zhenfang Chen, Chuang Gan

In our experiment, we found that the modular architecture enables three important abilities for large pre-trained language models: 1) Efficiency, since ModuleFormer only activates a subset of its modules for each input token, thus it could achieve the same performance as dense LLMs with more than two times throughput; 2) Extendability, ModuleFormer is more immune to catastrophic forgetting than dense LLMs and can be easily extended with new modules to learn new knowledge that is not included in the training data; 3) Specialisation, finetuning ModuleFormer could specialize a subset of modules to the finetuning task and the task-unrelated modules could be easily pruned for a lightweight deployment.

Language Modelling

Hyper-Decision Transformer for Efficient Online Policy Adaptation

no code implementations17 Apr 2023 Mengdi Xu, Yuchen Lu, Yikang Shen, Shun Zhang, Ding Zhao, Chuang Gan

To address this challenge, we propose a new framework, called Hyper-Decision Transformer (HDT), that can generalize to novel tasks from a handful of demonstrations in a data- and parameter-efficient manner.

Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention

1 code implementation CVPR 2023 Mingyu Ding, Yikang Shen, Lijie Fan, Zhenfang Chen, Zitian Chen, Ping Luo, Joshua B. Tenenbaum, Chuang Gan

When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them.

Planning with Large Language Models for Code Generation

no code implementations9 Mar 2023 Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, Chuang Gan

Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process.

Code Generation Language Modelling +1

Transformer-Patcher: One Mistake worth One Neuron

1 code implementation24 Jan 2023 Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie zhou, Wenge Rong, Zhang Xiong

Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME).

Model Editing

Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners

no code implementations15 Dec 2022 Zitian Chen, Yikang Shen, Mingyu Ding, Zhenfang Chen, Hengshuang Zhao, Erik Learned-Miller, Chuang Gan

To address the MTL challenge, we propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad').

Multi-Task Learning

Mixture of Attention Heads: Selecting Attention Heads Per Token

1 code implementation11 Oct 2022 Xiaofeng Zhang, Yikang Shen, Zeyu Huang, Jie zhou, Wenge Rong, Zhang Xiong

This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.

Language Modelling Machine Translation +1

Syntactic Inductive Biases for Deep Learning Methods

no code implementations8 Jun 2022 Yikang Shen

We propose two families of inductive biases, one for constituency structure and another one for dependency structure.

Inductive Bias

Self-Instantiated Recurrent Units with Dynamic Soft Recursion

no code implementations NeurIPS 2021 Aston Zhang, Yi Tay, Yikang Shen, Alvin Chan Guo Wei, Shuai Zhang

On the other hand, the extent of the Self-IRU recursion is controlled by gates whose values are between 0 and 1 and may vary across the temporal dimension of sequences, enabling dynamic soft recursion depth at each time step.

Inductive Bias

Inducing Reusable Skills From Demonstrations with Option-Controller Network

no code implementations29 Sep 2021 Siyuan Zhou, Yikang Shen, Yuchen Lu, Aaron Courville, Joshua B. Tenenbaum, Chuang Gan

With the isolation of information and the synchronous calling mechanism, we can impose a division of works between the controller and options in an end-to-end training regime.

Learning Task Decomposition with Ordered Memory Policy Network

no code implementations19 Mar 2021 Yuchen Lu, Yikang Shen, Siyuan Zhou, Aaron Courville, Joshua B. Tenenbaum, Chuang Gan

The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstruc-tured demonstration.

Inductive Bias

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

2 code implementations ACL 2021 Yikang Shen, Yi Tay, Che Zheng, Dara Bahri, Donald Metzler, Aaron Courville

There are two major classes of natural language grammar -- the dependency grammar that models one-to-one correspondences between words and the constituency grammar that models the assembly of one or several corresponded words.

Constituency Parsing Language Modelling +2

Long Range Arena: A Benchmark for Efficient Transformers

5 code implementations8 Nov 2020 Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler

In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models.

Benchmarking Long-range modeling

Ordered Memory

1 code implementation NeurIPS 2019 Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

Inspired by Ordered Neurons (Shen et al., 2018), we introduce a new attention-based mechanism and use its cumulative probability to control the writing and erasing operation of the memory.


Investigating Biases in Textual Entailment Datasets

no code implementations23 Jun 2019 Shawn Tan, Yikang Shen, Chin-wei Huang, Aaron Courville

The ability to understand logical relationships between sentences is an important task in language understanding.

BIG-bench Machine Learning Natural Language Inference +2

BanditSum: Extractive Summarization as a Contextual Bandit

1 code implementation EMNLP 2018 Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung

In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.

Extractive Summarization Extractive Text Summarization

Generating Contradictory, Neutral, and Entailing Sentences

no code implementations7 Mar 2018 Yikang Shen, Shawn Tan, Chin-wei Huang, Aaron Courville

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP).

Natural Language Inference RTE

Neural Language Modeling by Jointly Learning Syntax and Lexicon

1 code implementation ICLR 2018 Yikang Shen, Zhouhan Lin, Chin-wei Huang, Aaron Courville

In this paper, We propose a novel neural language model, called the Parsing-Reading-Predict Networks (PRPN), that can simultaneously induce the syntactic structure from unannotated sentences and leverage the inferred structure to learn a better language model.

Constituency Grammar Induction Language Modelling

Self-organized Hierarchical Softmax

no code implementations26 Jul 2017 Yikang Shen, Shawn Tan, Chrisopher Pal, Aaron Courville

We propose a new self-organizing hierarchical softmax formulation for neural-network-based language models over large vocabularies.

Language Modelling Sentence Compression

Word Embedding based Correlation Model for Question/Answer Matching

no code implementations15 Nov 2015 Yikang Shen, Wenge Rong, Nan Jiang, Baolin Peng, Jie Tang, Zhang Xiong

With the development of community based question answering (Q&A) services, a large scale of Q&A archives have been accumulated and are an important information and knowledge resource on the web.

Question Answering Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.