23 citations · 124 across the 30 of their papers we have counts for
39 papers
Modeling Complex Event Scenarios via Simple Entity-focused Questions
Mahnaz Koupaee, Greg Durrett, Nathanael Chambers +1
Event scenarios are often complex and involve multiple event sequences connected through different entity participants. Exploring such complex scenarios requires an ability to bran…
POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex Events
Sai Vallurupalli, Sayontan Ghosh, Katrin Erk +2
Knowledge about outcomes is critical for complex event understanding but is hard to acquire. We show that by pre-identifying a participant in a complex event, crowd workers are abl…
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering…
BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples
Mohaddeseh Bastan, Mihai Surdeanu, Niranjan Balasubramanian
Natural language inference (NLI) is critical for complex decision-making in biomedical domain. One key question, for example, is whether a given biomedical mechanism is supported b…
Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation
Sayontan Ghosh, Tanvi Aggarwal, Minh Hoai +1
Anticipating future actions in a video is useful for many autonomous and assistive technologies. Most prior action anticipation work treat this as a vision modality problem, where…
Efficient Methods for Natural Language Processing: A Survey
Marcos Treviso, Ji-Ung Lee, Tianchu Ji +19
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance mea…
PASTA: A Dataset for Modeling Participant States in Narratives
Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen +3
The events in a narrative are understood as a coherent whole via the underlying states of their participants. Often, these participant states are not explicitly mentioned, instead…
Human Language Modeling
Nikita Soni, Matthew Matero, Niranjan Balasubramanian +1
Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM),…
SuMe: A Dataset Towards Summarizing Biomedical Mechanisms
Mohaddeseh Bastan, Nishant Shankar, Mihai Surdeanu +1
Can language models read biomedical texts and explain the biomedical mechanisms discussed? In this work we introduce a biomedical mechanism summarization task. Biomedical studies o…
Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fa…
MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection
Matthew Matero, Nikita Soni, Niranjan Balasubramanian +1
Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens. Ho…
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension
Naoya Inoue, Harsh Trivedi, Steven Sinha +2
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-…
MuSiQue: Multihop Questions via Single-hop Question Composition
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by…
Toward Diverse Precondition Generation
Heeyoung Kwon, Nathanael Chambers, Niranjan Balasubramanian
Language understanding must identify the logical connections between events in a discourse, but core events are often unstated due to their commonsense nature. This paper fills in…
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers
Tianchu Ji, Shraddhan Jain, Michael Ferdman +3
How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transfor…
IrEne: Interpretable Energy Prediction for Transformers
Qingqing Cao, Yash Kumar Lal, Harsh Trivedi +2
Existing software-based energy measurements of NLP models are not accurate because they do not consider the complex interactions between energy consumption and model execution. We…
TellMeWhy: A Dataset for Answering Why-Questions in Narratives
Yash Kumar Lal, Nathanael Chambers, Raymond Mooney +1
Answering questions about why characters perform certain actions is central to understanding and reasoning about narratives. Despite recent progress in QA, it is not clear if exist…
Bew: Towards Answering Business-Entity-Related Web Questions
Qingqing Cao, Oriana Riva, Aruna Balasubramanian +1
We present BewQA, a system specifically designed to answer a class of questions that we call Bew questions. Bew questions are related to businesses/services such as restaurants, ho…
Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents
Amanpreet Singh, Niranjan Balasubramanian
A major challenge in fine-tuning deep learning models for automatic summarization is the need for large domain specific datasets. One of the barriers to curating such data from res…
Author's Sentiment Prediction
Mohaddeseh Bastan, Mahnaz Koupaee, Youngseo Son +2
We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles. The dataset also includes paragra…
LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System
Ishita Doshi, Dhritiman Das, Ashish Bhutani +3
Nearest neighbor search (NNS) has a wide range of applications in information retrieval, computer vision, machine learning, databases, and other areas. Existing state-of-the-art al…
Modeling Preconditions in Text with a Crowd-sourced Dataset
Heeyoung Kwon, Mahnaz Koupaee, Pratyush Singh +5
Preconditions provide a form of logical connection between events that explains why some events occur together and information that is complementary to the more widely studied rela…
Towards Accurate and Reliable Energy Measurement of NLP Models
Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian
Accurate and reliable measurement of energy consumption is critical for making well-informed design choices when choosing and training large scale NLP models. In this work, we show…
Modeling Label Semantics for Predicting Emotional Reactions
Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan +2
Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes…