papers

Publications (27)

cs.LG2020

Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning

Armen Aghajanyan, Luke Zettlemoyer, Sonal Gupta

Although pretrained language models can be fine-tuned to produce state-of-the-art results for a very wide range of language understanding tasks, the dynamics of this process are no…

cs.CL2020

Sound Natural: Content Rephrasing in Dialog Systems

Arash Einolghozati, Anchit Gupta, Keith Diedrick +1

We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intent slot tagging and the slot values are direct…

cs.CL2021

Muppet: Massive Multi-task Representations with Pre-Finetuning

Armen Aghajanyan, Anchit Gupta, Akshat Shrivastava +3

We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50…

cs.CL2019

Improving Semantic Parsing for Task Oriented Dialog

Arash Einolghozati, Panupong Pasupat, Sonal Gupta +4

Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018]. In this paper, we present three d…

cs.LG2020

Better Fine-Tuning by Reducing Representational Collapse

Armen Aghajanyan, Akshat Shrivastava, Anchit Gupta +3

Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on t…

cs.CL2021

Domain-matched Pre-training Tasks for Dense Retrieval

Barlas Oğuz, Kushal Lakhotia, Anchit Gupta +8

Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information ret…

cs.CL2018

PyText: A Seamless Path from NLP research to production

Ahmed Aly, Kushal Lakhotia, Shicong Zhao +7

We introduce PyText - a deep learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapid experimentation and of se…

cs.CL2022

UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

Barlas Oguz, Xilun Chen, Vladimir Karpukhin +6

We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases. Departing from prior…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2022

CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training

Patrick Huber, Armen Aghajanyan, Barlas Oğuz +4

With the rise of large-scale pre-trained language models, open-domain question-answering (ODQA) has become an important research topic in NLP. Based on the popular pre-training fin…

cs.CV2024

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

Animesh Sinha, Bo Sun, Anmol Kalia +14

We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sti…

cs.CL2022

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

Xilun Chen, Kushal Lakhotia, Barlas Oğuz +6

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare…

cs.CL2018

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

Sonal Gupta, Rushin Shah, Mrinal Mohit +2

Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots. Previous work on task oriented intent and slot-filling work ha…

cs.CV2023

Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation

Jie An, Songyang Zhang, Harry Yang +4

We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion m…

cs.CL2021

MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark

Haoran Li, Abhinav Arora, Shuohui Chen +3

Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets su…

cs.CL2020

Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

Xilun Chen, Asish Ghoshal, Yashar Mehdad +2

Task-oriented semantic parsing is a critical component of virtual assistants, which is responsible for understanding the user's intents (set reminder, play music, etc.). Recent adv…

cs.CL2021

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Sewon Min, Jordan Boyd-Graber, Chris Alberti +50

We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-domain question answering (QA), where systems take natural language questions as input and…

cs.CV2023

SpaText: Spatio-Textual Representation for Controllable Image Generation

Omri Avrahami, Thomas Hayes, Oran Gafni +6

Recent text-to-image diffusion models are able to generate convincing results of unprecedented quality. However, it is nearly impossible to control the shapes of different regions/…

cs.CL2020

Conversational Semantic Parsing

Armen Aghajanyan, Jean Maillard, Akshat Shrivastava +8

The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the repr…

cs.CL2019

Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog

Sebastian Schuster, Sonal Gupta, Rushin Shah +1

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data…

cs.CL2019

Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog

Varun Gangal, Abhinav Arora, Arash Einolghozati +1

The task of identifying out-of-domain (OOD) input examples directly at test-time has seen renewed interest recently due to increased real world deployment of models. In this work,…

cs.CL2019

Improving Robustness of Task Oriented Dialog Systems

Arash Einolghozati, Sonal Gupta, Mrinal Mohit +1

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are,…

cs.CV2022

Make-A-Video: Text-to-Video Generation without Text-Video Data

Uriel Singer, Adam Polyak, Thomas Hayes +10

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: le…

cs.CL2021

EASE: Extractive-Abstractive Summarization with Explanations

Haoran Li, Arash Einolghozati, Srinivasan Iyer +4

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve…

cs.CV2023

Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation

Samaneh Azadi, Akbar Shah, Thomas Hayes +2

Text-guided human motion generation has drawn significant interest because of its impactful applications spanning animation and robotics. Recently, application of diffusion models…

cs.CV2023

Text-Conditional Contextualized Avatars For Zero-Shot Personalization

Samaneh Azadi, Thomas Hayes, Akbar Shah +3

Recent large-scale text-to-image generation models have made significant improvements in the quality, realism, and diversity of the synthesized images and enable users to control t…

cs.CL2021

El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing

Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda +2

Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales.…