b'Mohit Iyyer'

research

∙ 09/16/2023

Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF

During the last stage of RLHF, a large language model is aligned to huma...

0 Simeng Sun, et al. ∙

research

∙ 05/29/2023

A Critical Evaluation of Evaluations for Long-form Question Answering

Long-form question answering (LFQA) enables answering a wide range of qu...

0 Fangyuan Xu, et al. ∙

research

∙ 05/24/2023

KNN-LM Does Not Improve Open-ended Text Generation

In this paper, we study the generation quality of interpolation-based re...

0 Shufan Wang, et al. ∙

research

∙ 05/23/2023

FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

Evaluating the factuality of long-form text generated by large language ...

0 Sewon Min, et al. ∙

research

∙ 04/06/2023

Large language models effectively leverage document-level context for literary translation, but critical errors persist

Large language models (LLMs) are competitive with the state of the art o...

0 Marzena Karpinska, et al. ∙

research

∙ 03/23/2023

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

To detect the deployment of large language models for malicious use case...

0 Kalpesh Krishna, et al. ∙

research

∙ 03/08/2023

On the Risks of Stealing the Decoding Algorithms of Language Models

A key component of generating text from modern language models (LM) is t...

0 Ali Naseh, et al. ∙

research

∙ 01/30/2023

LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization

While human evaluation remains best practice for accurately judging the ...

4 Kalpesh Krishna, et al. ∙

research

∙ 10/28/2022

You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM

Retrieval-enhanced language models (LMs), which condition their predicti...

0 Andrew Drozdov, et al. ∙

research

∙ 10/25/2022

Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature

Literary translation is a culturally significant task, but it is bottlen...

0 Katherine Thai, et al. ∙

research

∙ 10/25/2022

DEMETR: Diagnosing Evaluation Metrics for Translation

While machine translation evaluation metrics based on string overlap (e....

0 Marzena Karpinska, et al. ∙

research

∙ 10/21/2022

SLING: Sino Linguistic Evaluation of Large Language Models

To understand what kinds of linguistic knowledge are encoded by pretrain...

0 Yixiao Song, et al. ∙

research

∙ 10/13/2022

ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution

Large-scale, high-quality corpora are critical for advancing research in...

0 Ankita Gupta, et al. ∙

research

∙ 05/25/2022

Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation

In this paper, we explore the challenging problem of performing a genera...

6 Tu Vu, et al. ∙

research

∙ 05/19/2022

RankGen: Improving Text Generation with Large Ranking Models

Given an input sequence (or prefix), modern language models often assign...

0 Kalpesh Krishna, et al. ∙

research

∙ 05/19/2022

Modeling Exemplification in Long-form Question Answering via Retrieval

Exemplification is a process by which writers explain or clarify a conce...

0 Shufan Wang, et al. ∙

research

∙ 04/22/2022

ChapterBreak: A Challenge Dataset for Long-Range Language Models

While numerous architectures for long-range language models (LRLMs) have...

0 Simeng Sun, et al. ∙

research

∙ 03/18/2022

RELIC: Retrieving Evidence for Literary Claims

Humanities scholars commonly provide evidence for claims that they make ...

0 Katherine Thai, et al. ∙

research

∙ 09/19/2021

Do Long-Range Language Models Actually Use Long-Range Context?

Language models are generally trained on short, truncated input sequence...

0 Simeng Sun, et al. ∙

research

∙ 09/14/2021

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation

Recent text generation research has increasingly focused on open-ended d...

0 Marzena Karpinska, et al. ∙

research

∙ 09/13/2021

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration

Phrase representations derived from BERT often do not exhibit complex ph...

0 Shufan Wang, et al. ∙

research

∙ 09/13/2021

STraTA: Self-Training with Task Augmentation for Better Few-shot Learning

Despite their recent successes in tackling many NLP tasks, large-scale p...

0 Tu Vu, et al. ∙

research

∙ 09/10/2021

Improved Latent Tree Induction with Distant Supervision via Span Constraints

For over thirty years, researchers have developed and analyzed methods f...

7 Zhiyang Xu, et al. ∙

research

∙ 05/06/2021

TABBIE: Pretrained Representations of Tabular Data

Existing work on tabular representation learning jointly models tables a...

0 Hiroshi Iida, et al. ∙

research

∙ 04/20/2021

WiFiMod: Transformer-based Indoor Human Mobility Modeling using Passive Sensing

Modeling human mobility has a wide range of applications from urban plan...

0 Amee Trivedi, et al. ∙

research

∙ 04/14/2021

IGA : An Intent-Guided Authoring Assistant

While large-scale pretrained language models have significantly improved...

0 Simeng Sun, et al. ∙

research

∙ 04/08/2021

Revisiting Simple Neural Probabilistic Language Models

Recent progress in language modeling has been driven not only by advance...

0 Simeng Sun, et al. ∙

research

∙ 03/29/2021

Changing the Mind of Transformers for Topically-Controllable Language Generation

Large Transformer-based language models can aid human authors by suggest...

13 Haw-Shiuan Chang, et al. ∙

research

∙ 03/10/2021

Hurdles to Progress in Long-form Question Answering

The task of long-form question answering (LFQA) involves retrieving docu...

0 Kalpesh Krishna, et al. ∙

research

∙ 03/03/2021

Weakly-Supervised Open-Retrieval Conversational Question Answering

Recent studies on Question Answering (QA) and Conversational QA (ConvQA)...

1 Chen Qu, et al. ∙

research

∙ 10/30/2020

Analyzing Gender Bias within Narrative Tropes

Popular media reflects and reinforces societal biases through the use of...

0 Dhruvil Gala, et al. ∙

research

∙ 10/12/2020

Reformulating Unsupervised Style Transfer as Paraphrase Generation

Modern NLP defines the task of style transfer as modifying the style of ...

0 Kalpesh Krishna, et al. ∙

research

∙ 10/04/2020

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

Systems for story generation are asked to produce plausible and enjoyabl...

0 Nader Akoury, et al. ∙

research

∙ 09/20/2020

Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models

The discrepancy between maximum likelihood estimation (MLE) and task mea...

6 Subhajit Naskar, et al. ∙

research

∙ 05/22/2020

Open-Retrieval Conversational Question Answering

Conversational search is one of the ultimate goals of information retrie...

0 Chen Qu, et al. ∙

research

∙ 05/02/2020

Exploring and Predicting Transferability across NLP Tasks

Recent advances in NLP demonstrate the effectiveness of training large-s...

0 Tu Vu, et al. ∙

research

∙ 05/02/2020

Hard-Coded Gaussian Attention for Neural Machine Translation

Recent work has questioned the importance of the Transformer's multi-hea...

0 Weiqiu You, et al. ∙

research

∙ 10/27/2019

Thieves on Sesame Street! Model Extraction of BERT-based APIs

We study the problem of model extraction in natural language processing,...

0 Kalpesh Krishna, et al. ∙

research

∙ 09/07/2019

Investigating Sports Commentator Bias within a Large Corpus of American Football Broadcasts

Sports broadcasters inject drama into play-by-play commentary by buildin...

0 Jack Merullo, et al. ∙

research

∙ 08/26/2019

Attentive History Selection for Conversational Question Answering

Conversational question answering (ConvQA) is a simplified but concrete ...

0 Chen Qu, et al. ∙

research

∙ 06/09/2019

Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification

While paragraph embedding models are remarkably effective for downstream...

0 Tu Vu, et al. ∙

research

∙ 06/06/2019

Syntactically Supervised Transformers for Faster Neural Machine Translation

Standard decoders for neural machine translation autoregressively genera...

0 Nader Akoury, et al. ∙

research

∙ 06/06/2019

Generating Question-Answer Hierarchies

The process of knowledge acquisition can be viewed as a question-answer ...

0 Kalpesh Krishna, et al. ∙

research

∙ 05/14/2019

BERT with History Answer Embedding for Conversational Question Answering

Conversational search is an emerging topic in the information retrieval ...

0 Chen Qu, et al. ∙

research

∙ 04/17/2019

Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism

Literary critics often attempt to uncover meaning in a single work of li...

0 Shufan Wang, et al. ∙

research

∙ 04/09/2019

Quizbowl: The Case for Incremental Question Answering

Quizbowl is a scholastic trivia competition that tests human knowledge a...

0 Pedro Rodriguez, et al. ∙

research

∙ 04/03/2019

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders

We introduce deep inside-outside recursive autoencoders (DIORA), a fully...

0 Andrew Drozdov, et al. ∙

research

∙ 08/23/2018

Revisiting the Importance of Encoding Logic Rules in Sentiment Classification

We analyze the performance of different sentiment classification models ...

0 Kalpesh Krishna, et al. ∙

research

∙ 08/21/2018

QuAC : Question Answering in Context

We present QuAC, a dataset for Question Answering in Context that contai...

2 Eunsol Choi, et al. ∙

research

∙ 04/22/2018

Inducing and Embedding Senses with Scaled Gumbel Softmax

Methods for learning word sense embeddings represent a single word with ...

0 Fenfei Guo, et al. ∙

Mohit Iyyer

Featured Co-authors