Search Results for author: Shubham Agarwal

Found 21 papers, 9 papers with code

The ReproGen Shared Task on Reproducibility of Human Evaluations in NLG: Overview and Results

no code implementations INLG (ACL) 2021 Anya Belz, Anastasia Shimorina, Shubham Agarwal, Ehud Reiter

The NLP field has recently seen a substantial increase in work related to reproducibility of results, and more generally in recognition of the importance of having shared definitions and practices relating to evaluation.

Real-Time Weather Image Classification with SVM

1 code implementation1 Sep 2024 Eden Ship, Eitan Spivak, Shubham Agarwal, Raz Birman, Ofer Hadar

Accurate classification of weather conditions in images is essential for enhancing the performance of object detection and classification models under varying weather conditions.

Autonomous Vehicles Classification +4

KaPQA: Knowledge-Augmented Product Question-Answering

no code implementations22 Jul 2024 Swetha Eppalapally, Daksh Dangi, Chaithra Bhat, Ankita Gupta, Ruiyi Zhang, Shubham Agarwal, Karishma Bagga, Seunghyun Yoon, Nedim Lipka, Ryan A. Rossi, Franck Dernoncourt

Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs).

Question Answering RAG +1

LongLaMP: A Benchmark for Personalized Long-form Text Generation

no code implementations27 Jun 2024 Ishita Kumar, Snigdha Viswanathan, Sushrita Yerra, Alireza Salemi, Ryan A. Rossi, Franck Dernoncourt, Hanieh Deilamsalehy, Xiang Chen, Ruiyi Zhang, Shubham Agarwal, Nedim Lipka, Chien Van Nguyen, Thien Huu Nguyen, Hamed Zamani

In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark.

Language Modelling Text Generation

LitLLM: A Toolkit for Scientific Literature Review

1 code implementation2 Feb 2024 Shubham Agarwal, Issam H. Laradji, Laurent Charlin, Christopher Pal

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.

RAG Retrieval

StarVector: Generating Scalable Vector Graphics Code from Images

1 code implementation17 Dec 2023 Juan A. Rodriguez, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, David Vazquez, Christopher Pal, Marco Pedersoli

These visual tokens are pre-pended to the SVG token embeddings, and the sequence is modeled by the StarCoder model using next-token prediction, effectively learning to align the visual and code tokens.

Code Generation Vector Graphics

Approximate Caching for Efficiently Serving Diffusion Models

no code implementations7 Dec 2023 Shubham Agarwal, Subrata Mitra, Sarthak Chakraborty, Srikrishna Karanam, Koyel Mukherjee, Shiv Saini

Text-to-image generation using diffusion models has seen explosive popularity owing to their ability in producing high quality images adhering to text prompts.

Denoising Management +1

Outage-Watch: Early Prediction of Outages using Extreme Event Regularizer

no code implementations29 Sep 2023 Shubham Agarwal, Sarthak Chakraborty, Shaddy Garg, Sumit Bisht, Chahat Jain, Ashritha Gonuguntla, Shiv Saini

Our proposed method, Outage-Watch, defines critical service outages as deteriorations in the Quality of Service (QoS) captured by a set of metrics.

Going for GOAL: A Resource for Grounded Football Commentaries

1 code implementation8 Nov 2022 Alessandro Suglia, José Lopes, Emanuele Bastianelli, Andrea Vanzo, Shubham Agarwal, Malvina Nikandrou, Lu Yu, Ioannis Konstas, Verena Rieser

As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding.

Moment Retrieval Retrieval

A Systematic Review of Reproducibility Research in Natural Language Processing

1 code implementation EACL 2021 Anya Belz, Shubham Agarwal, Anastasia Shimorina, Ehud Reiter

Against the background of what has been termed a reproducibility crisis in science, the NLP field is becoming increasingly interested in, and conscientious about, the reproducibility of its results.

Diversity

History for Visual Dialog: Do we really need it?

2 code implementations ACL 2020 Shubham Agarwal, Trung Bui, Joon-Young Lee, Ioannis Konstas, Verena Rieser

Visual Dialog involves "understanding" the dialog history (what has been discussed previously) and the current question (what is asked), in addition to grounding information in the image, to generate the correct response.

Visual Dialog

Planning for Goal-Oriented Dialogue Systems

no code implementations17 Oct 2019 Christian Muise, Tathagata Chakraborti, Shubham Agarwal, Ondrej Bajgar, Arunima Chaudhary, Luis A. Lastras-Montano, Josef Ondrej, Miroslav Vodolan, Charlie Wiecha

Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft.

Goal-Oriented Dialogue Systems slot-filling +1

Improving Context Modelling in Multimodal Dialogue Generation

1 code implementation WS 2018 Shubham Agarwal, Ondrej Dusek, Ioannis Konstas, Verena Rieser

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system.

Decoder Dialogue Generation +1

A Knowledge-Grounded Multimodal Search-Based Conversational Agent

1 code implementation WS 2018 Shubham Agarwal, Ondrej Dusek, Ioannis Konstas, Verena Rieser

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database.

Decoder Question Answering +1

A surprisingly effective out-of-the-box char2char model on the E2E NLG Challenge dataset

1 code implementation WS 2017 Shubham Agarwal, Marc Dymetman

We train a char2char model on the E2E NLG Challenge data, by exploiting {``}out-of-the-box{''} the recently released tfseq2seq framework, using some of the standard options offered by this tool.

Data-to-Text Generation

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