Search Results for author:
Found 44 papers, 25 papers with code
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
We study the problem of learning to reason in large scale knowledge graphs (KGs).
Ranked #1 on
Link Prediction
on NELL-995
(Mean AP metric)
Variational Knowledge Graph Reasoning
Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community.
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices---We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task.
Model-based Reinforcement Learning
reinforcement-learning
+4
Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents
We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs.
One-Shot Relational Learning for Knowledge Graphs
Knowledge graphs (KGs) are the key components of various natural language processing applications.
SafeRoute: Learning to Navigate Streets Safely in an Urban Environment
We propose SafeRoute, a novel solution to the problem of navigating cities and avoiding street harassment and crime.
Sentence Embedding Alignment for Lifelong Relation Extraction
We formulate such a challenging problem as lifelong relation extraction and investigate memory-efficient incremental learning methods without catastrophically forgetting knowledge learned from previous tasks.
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing
Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance.
Ranked #3 on
Entity Typing
on Ontonotes v5 (English)
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets.
Self-Supervised Learning for Contextualized Extractive Summarization
Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level.
TWEETQA: A Social Media Focused Question Answering Dataset
With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective-ness of many applications that rely on real-time knowledge.
Meta Reasoning over Knowledge Graphs
The ability to reason over learned knowledge is an innate ability for humans and humans can easily master new reasoning rules with only a few demonstrations.
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
Many tasks in natural language processing can be viewed as multi-label classification problems.
Neural Correction Model for Open-Domain Named Entity Recognition
In this work, to address the low precision and recall problems, we first utilize DBpedia as the source of distant supervision to annotate abstracts from Wikipedia and design a neural correction model trained with a human-annotated NER dataset, DocRED, to correct the false entity labels.
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering
To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (\emph{i. e.}, the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model.
Do Multi-hop Readers Dream of Reasoning Chains?
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i. e. the ability to reason with information collected from multiple passages to derive the answer.
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
Models trained with our new objective yield significant improvements on the fact completion task.
Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games
We propose the new problem of learning to recover reasoning chains from weakly supervised signals, i. e., the question-answer pairs.
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
3) a hybrid model that combines heterogeneous information to find the answer.
Ranked #4 on
Question Answering
on HybridQA
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering
In this work, we propose a simple and resource-efficient method to pretrain the paragraph encoder.
Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER.
Ranked #14 on
Question Answering
on HotpotQA
Unsupervised Multi-hop Question Answering by Question Generation
Obtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Zero-shot Fact Verification by Claim Generation
However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive.
Open-Domain Question-Answering for COVID-19 and Other Emergent Domains
In this work, we present such a system for the emergent domain of COVID-19.
Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation
Our experiments show that there is a trade-off between understanding tasks and generation tasks while using the same model, and a feasible way to improve both tasks is to use more data.
Boosted Dense Retriever
DrBoost is trained in stages: each component model is learned sequentially and specialized by focusing only on retrieval mistakes made by the current ensemble.
Simple Local Attentions Remain Competitive for Long-Context Tasks
Many NLP tasks require processing long contexts beyond the length limit of pretrained models.
SCROLLS: Standardized CompaRison Over Long Language Sequences
NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild.
Ranked #8 on
Long-range modeling
on SCROLLS
Adapting Pretrained Text-to-Text Models for Long Text Sequences
We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs.
Ranked #1 on
Text Summarization
on QMSum
Bridging the Training-Inference Gap for Dense Phrase Retrieval
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search.
CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding
Whether heuristic or learned, these methods ignore instance-level visual attributes of objects, and as a result may produce visually less coherent scenes.
3DGen: Triplane Latent Diffusion for Textured Mesh Generation
We take another step along this direction, combining these developments in a two-step pipeline consisting of 1) a triplane VAE which can learn latent representations of textured meshes and 2) a conditional diffusion model which generates the triplane features.
VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation
We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn fundamental vision-language concepts, and then adapted to video data in an intermediate video-text pre-training stage to learn video-specific skills such as spatio-temporal reasoning.
Multi-Head State Space Model for Speech Recognition
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches.
Ranked #8 on
Speech Recognition
on LibriSpeech test-clean
Text-guided 3D Human Generation from 2D Collections
To address this \texttt{T3H} task, we propose Compositional Cross-modal Human (CCH).
Ranked #1 on
Text-to-3D-Human Generation
on SHHQ
Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality
Along with this, we propose novel negative mining techniques in the scene graph space for improving attribute binding and relation understanding.
Ranked #1 on
Image Retrieval
on CREPE (Compositional REPresentation Evaluation)
(Recall@1 (HN-Comp, UC) metric)
Prompting Large Language Models with Speech Recognition Abilities
Furthermore, we perform ablation studies to investigate whether the LLM can be completely frozen during training to maintain its original capabilities, scaling up the audio encoder, and increasing the audio encoder striding to generate fewer embeddings.
Abstractive Text Summarization
Automatic Speech Recognition
+3
Code Llama: Open Foundation Models for Code
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.
Ranked #26 on
Code Generation
on MBPP
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their applications in real-world tasks involving long contexts such as encoding scientific articles, code repositories, or long dialogues.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
To our knowledge, only one method has been proposed to learn a sequence of mixed tasks.
The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task
The study explores the effectiveness of the Chain-of-Thought approach, known for its proficiency in language tasks by breaking them down into sub-tasks and intermediate steps, in improving vision-language tasks that demand sophisticated perception and reasoning.
Ranked #1 on
Visual Reasoning
on Winoground
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
This paper introduces Scene-LLM, a 3D-visual-language model that enhances embodied agents' abilities in interactive 3D indoor environments by integrating the reasoning strengths of Large Language Models (LLMs).
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform Transformers in pretraining efficiency and downstream task accuracy.
