no code implementations • EMNLP 2021 • Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
no code implementations • EMNLP 2020 • Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O{'}Gorman, Mohit Iyyer, Andrew McCallum
The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*.
no code implementations • insights (ACL) 2022 • Simeng Sun, Brian Dillon, Mohit Iyyer
Recent progress in large pretrained language models (LMs) has led to a growth of analyses examining what kinds of linguistic knowledge are encoded by these models.
no code implementations • 25 May 2022 • Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, Noah Constant
In this paper, we explore the challenging problem of performing a generative task (i. e., summarization) in a target language when labeled data is only available in English.
no code implementations • 19 May 2022 • Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer
We show that not only do state-of-the-art LFQA models struggle to generate relevant examples, but also that standard evaluation metrics such as ROUGE are insufficient to judge exemplification quality.
1 code implementation • 19 May 2022 • Kalpesh Krishna, Yapei Chang, John Wieting, Mohit Iyyer
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts.
1 code implementation • 22 Apr 2022 • Simeng Sun, Katherine Thai, Mohit Iyyer
While numerous architectures for long-range language models (LRLMs) have recently been proposed, a meaningful evaluation of their discourse-level language understanding capabilities has not yet followed.
1 code implementation • ACL 2022 • Katherine Thai, Yapei Chang, Kalpesh Krishna, Mohit Iyyer
Humanities scholars commonly provide evidence for claims that they make about a work of literature (e. g., a novel) in the form of quotations from the work.
no code implementations • EMNLP 2021 • Simeng Sun, Kalpesh Krishna, Andrew Mattarella-Micke, Mohit Iyyer
Language models are generally trained on short, truncated input sequences, which limits their ability to use discourse-level information present in long-range context to improve their predictions.
no code implementations • EMNLP 2021 • Marzena Karpinska, Nader Akoury, Mohit Iyyer
Recent text generation research has increasingly focused on open-ended domains such as story and poetry generation.
1 code implementation • EMNLP 2021 • Tu Vu, Minh-Thang Luong, Quoc V. Le, Grady Simon, Mohit Iyyer
Despite their recent successes in tackling many NLP tasks, large-scale pre-trained language models do not perform as well in few-shot settings where only a handful of training examples are available.
Ranked #1 on
Few-Shot NLI
on SNLI (8 training examples per class)
1 code implementation • EMNLP 2021 • Shufan Wang, Laure Thompson, Mohit Iyyer
Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness.
1 code implementation • EMNLP 2021 • Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O'Gorman, Subendhu Rongali, Dylan Finkbeiner, Shilpa Suresh, Mohit Iyyer, Andrew McCallum
For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing.
1 code implementation • NAACL 2021 • Hiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer
Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT.
1 code implementation • 14 Apr 2021 • Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.
1 code implementation • NAACL 2021 • Simeng Sun, Mohit Iyyer
Recent progress in language modeling has been driven not only by advances in neural architectures, but also through hardware and optimization improvements.
Ranked #37 on
Language Modelling
on WikiText-103
1 code implementation • EACL 2021 • Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, Andrew McCallum
Our framework consists of two components: (1) a method that produces a set of candidate topics by predicting the centers of word clusters in the possible continuations, and (2) a text generation model whose output adheres to the chosen topics.
1 code implementation • NAACL 2021 • Kalpesh Krishna, Aurko Roy, Mohit Iyyer
The task of long-form question answering (LFQA) involves retrieving documents relevant to a given question and using them to generate a paragraph-length answer.
Ranked #3 on
Open-Domain Question Answering
on KILT: ELI5
1 code implementation • 3 Mar 2021 • Chen Qu, Liu Yang, Cen Chen, W. Bruce Croft, Kalpesh Krishna, Mohit Iyyer
Our method is more flexible as it can handle both span answers and freeform answers.
1 code implementation • EMNLP (NLP+CSS) 2020 • Dhruvil Gala, Mohammad Omar Khursheed, Hannah Lerner, Brendan O'Connor, Mohit Iyyer
Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently across media.
1 code implementation • EMNLP 2020 • Kalpesh Krishna, John Wieting, Mohit Iyyer
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs.
1 code implementation • EMNLP 2020 • Nader Akoury, Shufan Wang, Josh Whiting, Stephen Hood, Nanyun Peng, Mohit Iyyer
Systems for story generation are asked to produce plausible and enjoyable stories given an input context.
1 code implementation • ACL 2021 • Sumanta Bhattacharyya, Amirmohammad Rooshenas, Subhajit Naskar, Simeng Sun, Mohit Iyyer, Andrew McCallum
To benefit from this observation, we train an energy-based model to mimic the behavior of the task measure (i. e., the energy-based model assigns lower energy to samples with higher BLEU score), which is resulted in a re-ranking algorithm based on the samples drawn from NMT: energy-based re-ranking (EBR).
1 code implementation • 22 May 2020 • Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
1 code implementation • ACL 2020 • Weiqiu You, Simeng Sun, Mohit Iyyer
Recent work has questioned the importance of the Transformer's multi-headed attention for achieving high translation quality.
1 code implementation • EMNLP 2020 • Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
no code implementations • LREC 2020 • Jordan Boyd-Graber, Fenfei Guo, Leah Findlater, Mohit Iyyer
Text representations are critical for modern natural language processing.
no code implementations • IJCNLP 2019 • Andrew Drozdov, Patrick Verga, Yi-Pei Chen, Mohit Iyyer, Andrew McCallum
Understanding text often requires identifying meaningful constituent spans such as noun phrases and verb phrases.
1 code implementation • ICLR 2020 • Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, Mohit Iyyer
We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model.
1 code implementation • IJCNLP 2019 • Jack Merullo, Luke Yeh, Abram Handler, Alvin Grissom II, Brendan O'Connor, Mohit Iyyer
Sports broadcasters inject drama into play-by-play commentary by building team and player narratives through subjective analyses and anecdotes.
2 code implementations • 26 Aug 2019 • Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W. Bruce Croft, Mohit Iyyer
First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.
1 code implementation • ACL 2019 • Tu Vu, Mohit Iyyer
While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque.
2 code implementations • ACL 2019 • Kalpesh Krishna, Mohit Iyyer
The process of knowledge acquisition can be viewed as a question-answer game between a student and a teacher in which the student typically starts by asking broad, open-ended questions before drilling down into specifics (Hintikka, 1981; Hakkarainen and Sintonen, 2002).
1 code implementation • ACL 2019 • Nader Akoury, Kalpesh Krishna, Mohit Iyyer
Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs.
1 code implementation • NAACL 2019 • Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer, Andrew McCallum
We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree.
Ranked #4 on
Constituency Grammar Induction
on PTB
1 code implementation • 14 May 2019 • Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, Mohit Iyyer
One of the major challenges to multi-turn conversational search is to model the conversation history to answer the current question.
no code implementations • NAACL 2019 • Shufan Wang, Mohit Iyyer
Literary critics often attempt to uncover meaning in a single work of literature through careful reading and analysis.
no code implementations • 9 Apr 2019 • Pedro Rodriguez, Shi Feng, Mohit Iyyer, He He, Jordan Boyd-Graber
Throughout this paper, we show that collaborations with the vibrant trivia community have contributed to the quality of our dataset, spawned new research directions, and doubled as an exciting way to engage the public with research in machine learning and natural language processing.
3 code implementations • 3 Apr 2019 • Andrew Drozdov, Pat Verga, Mohit Yadav, Mohit Iyyer, Andrew McCallum
We introduce deep inside-outside recursive autoencoders (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree.
no code implementations • EMNLP 2018 • Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total).
no code implementations • 27 Sep 2018 • Fenfei Guo, Mohit Iyyer, Leah Findlater, Jordan Boyd-Graber
We present a differentiable multi-prototype word representation model that disentangles senses of polysemous words and produces meaningful sense-specific embeddings without external resources.
1 code implementation • EMNLP 2018 • Kalpesh Krishna, Preethi Jyothi, Mohit Iyyer
We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences.
no code implementations • 21 Aug 2018 • Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total).
no code implementations • 22 Apr 2018 • Fenfei Guo, Mohit Iyyer, Jordan Boyd-Graber
Methods for learning word sense embeddings represent a single word with multiple sense-specific vectors.
no code implementations • EMNLP 2018 • Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, Jordan Boyd-Graber
In existing interpretation methods for NLP, a word's importance is determined by either input perturbation---measuring the decrease in model confidence when that word is removed---or by the gradient with respect to that word.
2 code implementations • NAACL 2018 • Mohit Iyyer, John Wieting, Kevin Gimpel, Luke Zettlemoyer
We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples.
1 code implementation • NAACL 2018 • Varun Manjunatha, Mohit Iyyer, Jordan Boyd-Graber, Larry Davis
Automatic colorization is the process of adding color to greyscale images.
42 code implementations • NAACL 2018 • Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer
We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e. g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i. e., to model polysemy).
Ranked #2 on
Citation Intent Classification
on ACL-ARC
(using extra training data)
Citation Intent Classification
Conversational Response Selection
+7
no code implementations • ACL 2017 • Mohit Iyyer, Wen-tau Yih, Ming-Wei Chang
Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans.
1 code implementation • CVPR 2017 • Mohit Iyyer, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daumé III, Larry Davis
While computers can now describe what is explicitly depicted in natural images, in this paper we examine whether they can understand the closure-driven narratives conveyed by stylized artwork and dialogue in comic book panels.
no code implementations • 4 Nov 2016 • Mohit Iyyer, Wen-tau Yih, Ming-Wei Chang
Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans.
10 code implementations • 24 Jun 2015 • Ankit Kumar, Ozan .Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher
Most tasks in natural language processing can be cast into question answering (QA) problems over language input.
Ranked #54 on
Sentiment Analysis
on SST-2 Binary classification