Search Results for author: Niranjan Balasubramanian

Found 54 papers, 28 papers with code

IrEne-viz: Visualizing Energy Consumption of Transformer Models

1 code implementation EMNLP (ACL) 2021 Yash Kumar Lal, Reetu Singh, Harsh Trivedi, Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian

IrEne is an energy prediction system that accurately predicts the interpretable inference energy consumption of a wide range of Transformer-based NLP models.

SpecNFS: A Challenge Dataset Towards Extracting Formal Models from Natural Language Specifications

1 code implementation LREC 2022 Sayontan Ghosh, Amanpreet Singh, Alex Merenstein, Wei Su, Scott A. Smolka, Erez Zadok, Niranjan Balasubramanian

Evaluations show that even when using a state-of-the-art language model, there is significant room for improvement, with the best models achieving an F1 score of only 60. 5 and 33. 3 in the named-entity-recognition and dependency-link-prediction sub-tasks, respectively.

Dependency Parsing Domain Adaptation +7

Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?

no code implementations23 Jan 2024 Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz, Dirk Hovy

We compare pre-training models with human context via 1) group attributes, 2) individual users, and 3) a combined approach on 5 user- and document-level tasks.

Age Estimation Language Modelling

Large Human Language Models: A Need and the Challenges

no code implementations9 Nov 2023 Nikita Soni, H. Andrew Schwartz, João Sedoc, Niranjan Balasubramanian

As research in human-centered NLP advances, there is a growing recognition of the importance of incorporating human and social factors into NLP models.

Modeling Complex Event Scenarios via Simple Entity-focused Questions

1 code implementation14 Feb 2023 Mahnaz Koupaee, Greg Durrett, Nathanael Chambers, Niranjan Balasubramanian

Event scenarios are often complex and involve multiple event sequences connected through different entity participants.

Language Modelling

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

1 code implementation20 Dec 2022 Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

While using the question to retrieve relevant text from an external knowledge source helps LLMs, we observe that this one-step retrieve-and-read approach is insufficient for multi-step QA.

Hallucination Question Answering +1

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

1 code implementation26 Oct 2022 Mohaddeseh Bastan, Mihai Surdeanu, Niranjan Balasubramanian

We introduce a novel semi-supervised procedure that bootstraps an NLI dataset from existing biomedical dataset that pairs mechanisms with experimental evidence in abstracts.

Decision Making Natural Language Inference

PASTA: A Dataset for Modeling Participant States in Narratives

no code implementations31 Jul 2022 Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen, Francis Ferraro, Nathanael Chambers, Niranjan Balasubramanian

This dataset contains inferable participant states; a counterfactual perturbation to each state; and the changes to the story that would be necessary if the counterfactual were true.

Benchmarking Common Sense Reasoning +1

Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts

1 code implementation25 May 2022 Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion.

Question Answering

SuMe: A Dataset Towards Summarizing Biomedical Mechanisms

2 code implementations ACL ARR November 2021 Mohaddeseh Bastan, Nishant Shankar, Mihai Surdeanu, Niranjan Balasubramanian

We leverage this structure and create a summarization task, where the input is a collection of sentences and the main entities in an abstract, and the output includes the relationship and a sentence that summarizes the mechanism.


Human Language Modeling

1 code implementation Findings (ACL) 2022 Nikita Soni, Matthew Matero, Niranjan Balasubramanian, H. Andrew Schwartz

Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently.

Age Estimation Language Modelling +3

MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection

1 code implementation Findings (EMNLP) 2021 Matthew Matero, Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz

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.

Attribute Language Modelling +2

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

1 code implementation EMNLP 2021 Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui

Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system.

2k Multi-Hop Reading Comprehension

MuSiQue: Multihop Questions via Single-hop Question Composition

2 code implementations2 Aug 2021 Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts.

Multi-hop Question Answering Question Answering

TellMeWhy: A Dataset for Answering Why-Questions in Narratives

1 code implementation Findings (ACL) 2021 Yash Kumar Lal, Nathanael Chambers, Raymond Mooney, Niranjan Balasubramanian

They are especially worse on questions whose answers are external to the narrative, thus providing a challenge for future QA and narrative understanding research.

IrEne: Interpretable Energy Prediction for Transformers

1 code implementation ACL 2021 Qingqing Cao, Yash Kumar Lal, Harsh Trivedi, Aruna Balasubramanian, Niranjan Balasubramanian

We present IrEne, an interpretable and extensible energy prediction system that accurately predicts the inference energy consumption of a wide range of Transformer-based NLP models.

Bew: Towards Answering Business-Entity-Related Web Questions

no code implementations10 Dec 2020 Qingqing Cao, Oriana Riva, Aruna Balasubramanian, Niranjan Balasubramanian

We present a practical approach, called BewQA, that can answer Bew queries by mining a template of the business-related webpages and using the template to guide the search.

Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents

1 code implementation15 Nov 2020 Amanpreet Singh, Niranjan Balasubramanian

The dataset introduces a new challenge for summarization in the business domain, requiring highly abstractive and more concise summaries as compared to other existing datasets.

Author's Sentiment Prediction

1 code implementation COLING 2020 Mohaddeseh Bastan, Mahnaz Koupaee, Youngseo Son, Richard Sicoli, Niranjan Balasubramanian

We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles.

Sentiment Analysis

LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System

no code implementations19 Oct 2020 Ishita Doshi, Dhritiman Das, Ashish Bhutani, Rajeev Kumar, Rushi Bhatt, Niranjan Balasubramanian

Nearest neighbor search (NNS) has a wide range of applications in information retrieval, computer vision, machine learning, databases, and other areas.

Information Retrieval Playing the Game of 2048 +1

Towards Accurate and Reliable Energy Measurement of NLP Models

1 code implementation EMNLP (sustainlp) 2020 Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian

In this work, we show that existing software-based energy measurements are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption.

Question Answering

Modeling Label Semantics for Predicting Emotional Reactions

1 code implementation ACL 2020 Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan, Niranjan Balasubramanian, Nathanael Chambers

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 to predict.

Emotion Classification Multi-Label Classification

Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

1 code implementation EMNLP 2020 Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

For a recent large-scale model (XLNet), we show that only 18 points out of its answer F1 score of 72 on HotpotQA are obtained through multifact reasoning, roughly the same as that of a simpler RNN baseline.

Multi-hop Question Answering Question Answering +1

Generating Narrative Text in a Switching Dynamical System

1 code implementation CONLL 2020 Noah Weber, Leena Shekhar, Heeyoung Kwon, Niranjan Balasubramanian, Nathanael Chambers

A SLDS is a dynamical system in which the latent dynamics of the system (i. e. how the state vector transforms over time) is controlled by top-level discrete switching variables.

Text Generation

Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning

no code implementations19 Nov 2019 Yingru Liu, Xuewen Yang, Dongliang Xie, Xin Wang, Li Shen, Hao-Zhi Huang, Niranjan Balasubramanian

In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL.

Multi-Task Learning

Latent Part-of-Speech Sequences for Neural Machine Translation

no code implementations IJCNLP 2019 Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian

In this work, we introduce a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics, while allowing for effective and efficient inference over the latent space.

Decoder Machine Translation +2

PoMo: Generating Entity-Specific Post-Modifiers in Context

no code implementations NAACL 2019 Jun Seok Kang, Robert L. Logan IV, Zewei Chu, Yang Chen, Dheeru Dua, Kevin Gimpel, Sameer Singh, Niranjan Balasubramanian

Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity.


Hierarchical Quantized Representations for Script Generation

1 code implementation EMNLP 2018 Noah Weber, Leena Shekhar, Niranjan Balasubramanian, Nathanael Chambers

This permits the decoder to softly decide what portions of the latent hierarchy to condition on by attending over the value embeddings for a given setting.

Decoder Language Modelling +1

Residualized Factor Adaptation for Community Social Media Prediction Tasks

no code implementations EMNLP 2018 Mohammadzaman Zamani, H. Andrew Schwartz, Veronica E. Lynn, Salvatore Giorgi, Niranjan Balasubramanian

Predictive models over social media language have shown promise in capturing community outcomes, but approaches thus far largely neglect the socio-demographic context (e. g. age, education rates, race) of the community from which the language originates.

Fake Sentence Detection as a Training Task for Sentence Encoding

no code implementations ICLR 2019 Viresh Ranjan, Heeyoung Kwon, Niranjan Balasubramanian, Minh Hoai

We automatically generate fake sentences by corrupting original sentences from a source collection and train the encoders to produce representations that are effective at detecting fake sentences.

Binary Classification Language Modelling +1

The Fine Line between Linguistic Generalization and Failure in Seq2Seq-Attention Models

2 code implementations WS 2018 Noah Weber, Leena Shekhar, Niranjan Balasubramanian

Seq2Seq based neural architectures have become the go-to architecture to apply to sequence to sequence language tasks.

Event Representations with Tensor-based Compositions

1 code implementation21 Nov 2017 Noah Weber, Niranjan Balasubramanian, Nathanael Chambers

Robust and flexible event representations are important to many core areas in language understanding.

Human Centered NLP with User-Factor Adaptation

no code implementations EMNLP 2017 Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian, H. Andrew Schwartz

We pose the general task of user-factor adaptation {--} adapting supervised learning models to real-valued user factors inferred from a background of their language, reflecting the idea that a piece of text should be understood within the context of the user that wrote it.

Document Classification Domain Adaptation +5

Cannot find the paper you are looking for? You can Submit a new open access paper.