Hannaneh Hajishirzi

research

∙ 08/10/2022

Patching open-vocabulary models by interpolating weights

Open-vocabulary models like CLIP achieve high accuracy across many image...

Gabriel Ilharco, et al. ∙

research

∙ 07/02/2022

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

In an information-seeking conversation, a user converses with an agent t...

Zeqiu Wu, et al. ∙

research

∙ 05/24/2022

Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

This work introduces ATTEMPT (Attentional Mixture of Prompt Tuning), a n...

Akari Asai, et al. ∙

research

∙ 02/25/2022

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

Large language models (LMs) are able to in-context learn – perform a new...

Sewon Min, et al. ∙

research

∙ 02/23/2022

UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training

We present UnifiedQA-v2, a QA model built with the same process as Unifi...

Daniel Khashabi, et al. ∙

research

∙ 02/22/2022

Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

Question answering (QA) over real-world knowledge bases (KBs) is challen...

Rajarshi Das, et al. ∙

research

∙ 12/16/2021

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

Retrieval-augmented generation models have shown state-of-the-art perfor...

Akari Asai, et al. ∙

research

∙ 12/02/2021

LongChecker: Improving scientific claim verification by modeling full-abstract context

We introduce the LongChecker system for scientific claim verification. G...

David Wadden, et al. ∙

research

∙ 12/01/2021

Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text

Communicating with humans is challenging for AIs because it requires a s...

Christopher Clark, et al. ∙

research

∙ 10/29/2021

MetaICL: Learning to Learn In Context

We introduce MetaICL (Meta-training for In-Context Learning), a new meta...

Sewon Min, et al. ∙

research

∙ 09/16/2021

Reframing Instructional Prompts to GPTk's Language

How can model designers turn task instructions into effective prompts fo...

Swaroop Mishra, et al. ∙

research

∙ 09/10/2021

DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

Identifying relevant knowledge to be used in conversational systems that...

Zeqiu Wu, et al. ∙

research

∙ 09/04/2021

Robust fine-tuning of zero-shot models

Large pre-trained models such as CLIP offer consistent accuracy across a...

Mitchell Wortsman, et al. ∙

research

∙ 08/09/2021

Noisy Channel Language Model Prompting for Few-Shot Text Classification

We introduce a noisy channel approach for language model prompting in fe...

Sewon Min, et al. ∙

research

∙ 07/26/2021

One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

We present CORA, a Cross-lingual Open-Retrieval Answer Generation model ...

Akari Asai, et al. ∙

research

∙ 07/05/2021

FaVIQ: FAct Verification from Information-seeking Questions

Despite significant interest in developing general purpose fact checking...

Jungsoo Park, et al. ∙

research

∙ 06/17/2021

Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study

Biomedical knowledge graphs (KGs) hold rich information on entities such...

Rahul Nadkarni, et al. ∙

research

∙ 06/12/2021

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

Many commonsense reasoning NLP tasks involve choosing between one or mor...

Bhargavi Paranjape, et al. ∙

research

∙ 06/02/2021

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

Most state-of-the-art open-domain question answering systems use a neura...

Ikuya Yamada, et al. ∙

research

∙ 04/18/2021

Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language Instructions

Can we enable NLP models to appropriately respond to instructional promp...

Swaroop Mishra, et al. ∙

research

∙ 04/18/2021

GooAQ: Open Question Answering with Diverse Answer Types

While day-to-day questions come with a variety of answer types, the curr...

Daniel Khashabi, et al. ∙

research

∙ 04/17/2021

Joint Passage Ranking for Diverse Multi-Answer Retrieval

We study multi-answer retrieval, an under-explored problem that requires...

Sewon Min, et al. ∙

research

∙ 03/24/2021

NaturalProofs: Mathematical Theorem Proving in Natural Language

Understanding and creating mathematics using natural mathematical langua...

Sean Welleck, et al. ∙

research

∙ 01/01/2021

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

We review the EfficientQA competition from NeurIPS 2020. The competition...

Sewon Min, et al. ∙

research

∙ 11/13/2020

IIRC: A Dataset of Incomplete Information Reading Comprehension Questions

Humans often have to read multiple documents to address their informatio...

James Ferguson, et al. ∙

research

∙ 10/22/2020

XOR QA: Cross-lingual Open-Retrieval Question Answering

Multilingual question answering tasks typically assume answers exist in ...

Akari Asai, et al. ∙

research

∙ 10/12/2020

MedICaT: A Dataset of Medical Images, Captions, and Textual References

Understanding the relationship between figures and text is key to scient...

Sanjay Subramanian, et al. ∙

research

∙ 10/08/2020

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers

The urgency of mitigating COVID-19 has spawned a large and diverse body ...

Aida Amini, et al. ∙

research

∙ 09/23/2020

X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

Mirroring the success of masked language models, vision-and-language cou...

Jaemin Cho, et al. ∙

research

∙ 09/19/2020

Extracting Summary Knowledge Graphs from Long Documents

Knowledge graphs capture entities and relations from long documents and ...

Zeqiu Wu, et al. ∙

research

∙ 08/03/2020

DeLighT: Very Deep and Light-weight Transformer

We introduce a very deep and light-weight transformer, DeLighT, that del...

Sachin Mehta, et al. ∙

research

∙ 07/25/2020

HATNet: An End-to-End Holistic Attention Network for Diagnosis of Breast Biopsy Images

Training end-to-end networks for classifying gigapixel size histopatholo...

Sachin Mehta, et al. ∙

research

∙ 05/02/2020

UnifiedQA: Crossing Format Boundaries With a Single QA System

Question answering (QA) tasks have been posed using a variety of formats...

Daniel Khashabi, et al. ∙

research

∙ 05/01/2020

An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction

Decisions of complex language understanding models can be rationalized b...

Bhargavi Paranjape, et al. ∙

research

∙ 05/01/2020

Probing Text Models for Common Ground with Visual Representations

Vision, as a central component of human perception, plays a fundamental ...

Gabriel Ilharco, et al. ∙

research

∙ 05/01/2020

A Controllable Model of Grounded Response Generation

Current end-to-end neural conversation models inherently lack the flexib...

Zeqiu Wu, et al. ∙

research

∙ 05/01/2020

SciREX: A Challenge Dataset for Document-Level Information Extraction

Extracting information from full documents is an important problem in ma...

Sarthak Jain, et al. ∙

research

∙ 04/30/2020

Fact or Fiction: Verifying Scientific Claims

We introduce the task of scientific fact-checking. Given a corpus of sci...

David Wadden, et al. ∙

research

∙ 04/22/2020

AmbigQA: Answering Ambiguous Open-domain Questions

Ambiguity is inherent to open-domain question answering; especially when...

Sewon Min, et al. ∙

research

∙ 04/21/2020

Logic-Guided Data Augmentation and Regularization for Consistent Question Answering

Many natural language questions require qualitative, quantitative or log...

Akari Asai, et al. ∙

research

∙ 03/31/2020

Procedural Reading Comprehension with Attribute-Aware Context Flow

Procedural texts often describe processes (e.g., photosynthesis and cook...

Aida Amini, et al. ∙

research

∙ 02/15/2020

Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

Fine-tuning pretrained contextual word embedding models to supervised do...

Jesse Dodge, et al. ∙

research

∙ 11/27/2019

DeFINE: DEep Factorized INput Word Embeddings for Neural Sequence Modeling

For sequence models with large word-level vocabularies, a majority of ne...

Sachin Mehta, et al. ∙

research

∙ 11/24/2019

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Answering questions that require multi-hop reasoning at web-scale necess...

Akari Asai, et al. ∙

research

∙ 11/10/2019

Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

This paper presents a general approach for open-domain question answerin...

Sewon Min, et al. ∙

research

∙ 11/07/2019

Contextualized Sparse Representation with Rectified N-Gram Attention for Open-Domain Question Answering

A sparse representation is known to be an effective means to encode prec...

Jinhyuk Lee, et al. ∙

research

∙ 09/25/2019

Question Answering is a Format; When is it Useful?

Recent years have seen a dramatic expansion of tasks and datasets posed ...

Matt Gardner, et al. ∙

research

∙ 09/11/2019

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Many question answering (QA) tasks only provide weak supervision for how...

Sewon Min, et al. ∙

research

∙ 09/08/2019

Entity. Relation, and Event Extraction with Contextualized Span Representations

We examine the capabilities of a unified, multi-task framework for three...

David Wadden, et al. ∙

research

∙ 09/04/2019

Mixture Content Selection for Diverse Sequence Generation

Generating diverse sequences is important in many NLP applications such ...

Jaemin Cho, et al. ∙

Hannaneh Hajishirzi

Featured Co-authors