Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

Michael HassidHao PengDaniel RotemRoy Schwartz
2022
EMNLP Findings

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this… 

In-Context Learning for Few-Shot Dialogue State Tracking

Yushi HuChia-Hsuan LeeTianbao XieMari Ostendorf
2022
EMNLP Findings

Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, zero and few shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an… 

Unsupervised Learning of Hierarchical Conversation Structure

Bo-Ru LuYushi HuHao ChengMari Ostendorf
2022
EMNLP Findings

Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure,… 

Knowledge Transfer from Answer Ranking to Answer Generation

Matteo GabburoRik Koncel-KedziorskiSiddhant GargAlessandro Moschitti
2022
EMNLP

Recent studies show that Question Answering (QA) based on Answer Sentence Selection (AS2) can be improved by generating an improved answer from the top-k ranked answer sentences (termed GenQA). This… 

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

Luca Di LielloSiddhant GargLuca SoldainiAlessandro Moschitti
2022
EMNLP

An important task for designing QA systems is answer sentence selection (AS2): select-ing the sentence containing (or constituting) the answer to a question from a set of re-trieved relevant… 

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems

Yoshitomo MatsubaraLuca SoldainiEric LindAlessandro Moschitti
2022
Findings of EMNLP

Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but their high computational costs prevent their use in many real-world applications. In this pa-per, we explore… 

Abstract Visual Reasoning with Tangram Shapes

Anya JiNoriyuki KojimaN. RushYoav Artzi
2022
EMNLP

We introduce KiloGram, a resource for studying abstract visual reasoning in humans and machines. Drawing on the history of tangram puzzles as stimuli in cognitive science, we build a richly… 

CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation

Abhilasha RavichanderMatt GardnerAna Marasović
2022
EMNLP

The full power of human language-based communication cannot be realized without negation. All human languages have some form of negation. Despite this, negation remains a challenging phenomenon for… 

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Pan LuSwaroop MishraTony XiaA. Kalyan
2022
NeurIPS 2022

When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box… 

ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

Matt DeitkeEli VanderBiltAlvaro HerrastiRoozbeh Mottaghi
2022
NeurIPS

Massive datasets and high-capacity models have driven many recent advancements in computer vision and natural language understanding. This work presents a platform to enable similar success stories…