23 citations · 124 across the 30 of their papers we have counts for
10 papers · 1 filter
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…
DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
Qingqing Cao, Harsh Trivedi, Aruna Balasubramanian +1
Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It…
Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
Has there been real progress in multi-hop question-answering? Models often exploit dataset artifacts to produce correct answers, without connecting information across multiple supp…
Generating Narrative Text in a Switching Dynamical System
Noah Weber, Leena Shekhar, Heeyoung Kwon +2
Early work on narrative modeling used explicit plans and goals to generate stories, but the language generation itself was restricted and inflexible. Modern methods use language mo…