Search Results for author:
Found 27 papers, 15 papers with code
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience.
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).
RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores, but are challenging to build.
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
Few-shot learning for open domain multi-hop question answering typically relies on the incontext learning capability of large language models (LLMs).
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.
Hierarchical Video-Moment Retrieval and Step-Captioning
Our hierarchical benchmark consists of video retrieval, moment retrieval, and two novel moment segmentation and step captioning tasks.
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
We hence propose a new DA approach with diverse queries and sources of supervision to progressively train a generalizable DR. As a result, DRAGON, our dense retriever trained with diverse augmentation, is the first BERT-base-sized DR to achieve state-of-the-art effectiveness in both supervised and zero-shot evaluations and even competes with models using more complex late interaction (ColBERTv2 and SPLADE++).
Nonparametric Masked Language Modeling
Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases.
CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
In this paper, we unify different multi-vector retrieval models from a token routing viewpoint and propose conditional token interaction via dynamic lexical routing, namely CITADEL, for efficient and effective multi-vector retrieval.
Task-aware Retrieval with Instructions
We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries.
A Study on the Efficiency and Generalization of Light Hybrid Retrievers
Driven by this question, we leverage an indexing-efficient dense retriever (i. e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost.
Simple Local Attentions Remain Competitive for Long-Context Tasks
Many NLP tasks require processing long contexts beyond the length limit of pretrained models.
CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training
Consequently, we propose a novel QA dataset based on the Common Crawl project in this paper.
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data.
Ranked #2 on
Passage Retrieval
on EntityQuestions
Domain-matched Pre-training Tasks for Dense Retrieval
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks.
Ranked #2 on
Passage Retrieval
on Natural Questions
(using extra training data)
Muppet: Massive Multi-task Representations with Pre-Finetuning
We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning.
Ranked #3 on
Text Summarization
on GigaWord
(using extra training data)
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
Learning Better Structured Representations Using Low-rank Adaptive Label Smoothing
Training with soft targets instead of hard targets has been shown to improve performance and calibration of deep neural networks.
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases.
Ranked #1 on
Open-Domain Question Answering
on WebQuestions
(using extra training data)
Knowledge Base Question Answering
Open-Domain Question Answering
Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing
Task-oriented semantic parsing is a critical component of virtual assistants, which is responsible for understanding the user's intents (set reminder, play music, etc.).
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on
Cross-Lingual NER
on CoNLL Dutch
Zero-Resource Multilingual Model Transfer: Learning What to Share
In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.
Unsupervised Multilingual Word Embeddings
Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space.
Multinomial Adversarial Networks for Multi-Domain Text Classification
Many text classification tasks are known to be highly domain-dependent.
Combining Global Models for Parsing Universal Dependencies
We describe our entry, C2L2, to the CoNLL 2017 shared task on parsing Universal Dependencies from raw text.
Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists.
