428 citations · 1k across the 21 of their papers we have counts for
25 papers
Efficient End-to-End Visual Document Understanding with Rationale Distillation
Wang Zhu, Alekh Agarwal, Mandar Joshi +3
Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), ca…
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Peter Shaw, Mandar Joshi, James Cohan +6
Much of the previous work towards digital agents for graphical user interfaces (GUIs) has relied on text-based representations (derived from HTML or other structured data sources),…
QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations
Chaitanya Malaviya, Peter Shaw, Ming-Wei Chang +2
Formulating selective information needs results in queries that implicitly specify set operations, such as intersection, union, and difference. For instance, one might search for "…
Anchor Prediction: Automatic Refinement of Internet Links
Nelson F. Liu, Kenton Lee, Kristina Toutanova
Internet links enable users to deepen their understanding of a topic by providing convenient access to related information. However, the majority of links are unanchored -- they li…
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Hexiang Hu, Yi Luan, Yang Chen +5
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmar…
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
Kenton Lee, Mandar Joshi, Iulia Turc +7
Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to th…
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing
Linlu Qiu, Peter Shaw, Panupong Pasupat +5
Despite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work…
Entity-Centric Query Refinement
David Wadden, Nikita Gupta, Kenton Lee +1
We introduce the task of entity-centric query refinement. Given an input query whose answer is a (potentially large) collection of entities, the task output is a small set of query…
Improving Compositional Generalization with Latent Structure and Data Augmentation
Linlu Qiu, Peter Shaw, Panupong Pasupat +4
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has…
Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer
Iulia Turc, Kenton Lee, Jacob Eisenstein +2
Despite their success, large pre-trained multilingual models have not completely alleviated the need for labeled data, which is cumbersome to collect for all target languages. Zero…
Joint Passage Ranking for Diverse Multi-Answer Retrieval
Sewon Min, Kenton Lee, Ming-Wei Chang +2
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint model…
Representations for Question Answering from Documents with Tables and Text
Vicky Zayats, Kristina Toutanova, Mari Ostendorf
Tables in Web documents are pervasive and can be directly used to answer many of the queries searched on the Web, motivating their integration in question answering. Very often inf…
Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?
Peter Shaw, Ming-Wei Chang, Panupong Pasupat +1
Sequence-to-sequence models excel at handling natural language variation, but have been shown to struggle with out-of-distribution compositional generalization. This has motivated…
Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
Hao Cheng, Ming-Wei Chang, Kenton Lee +1
We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previous…
Sparse, Dense, and Attentional Representations for Text Retrieval
Yi Luan, Jacob Eisenstein, Kristina Toutanova +1
Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the c…
Contextualized Representations Using Textual Encyclopedic Knowledge
Mandar Joshi, Kenton Lee, Yi Luan +1
We present a method to represent input texts by contextualizing them jointly with dynamically retrieved textual encyclopedic background knowledge from multiple documents. We apply…
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
Iulia Turc, Ming-Wei Chang, Kenton Lee +1
Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervise…
Latent Retrieval for Weakly Supervised Open Domain Question Answering
Kenton Lee, Ming-Wei Chang, Kristina Toutanova
Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evi…
Zero-Shot Entity Linking by Reading Entity Descriptions
Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee +3
We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly speci…
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
Christopher Clark, Kenton Lee, Ming-Wei Chang +3
In this paper we study yes/no questions that are naturally occurring --- meaning that they are generated in unprompted and unconstrained settings. We build a reading comprehension…
Language Model Pre-training for Hierarchical Document Representations
Ming-Wei Chang, Kristina Toutanova, Kenton Lee +1
Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentati…
Improving Span-based Question Answering Systems with Coarsely Labeled Data
Hao Cheng, Ming-Wei Chang, Kenton Lee +3
We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely…
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee +1
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models…
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
Nanyun Peng, Hoifung Poon, Chris Quirk +2
Past work in relation extraction has focused on binary relations in single sentences. Recent NLP inroads in high-value domains have sparked interest in the more general setting of…