Varun Manjunatha

Also published as: Varun Manjunath


2023

pdf bib
kNN-LM Does Not Improve Open-ended Text Generation
Shufan Wang | Yixiao Song | Andrew Drozdov | Aparna Garimella | Varun Manjunatha | Mohit Iyyer
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

In this paper, we study the generation quality of interpolation-based retrieval-augmented language models (LMs). These methods, best exemplified by the kNN-LM, interpolate the LM’s predicted distribution of the next word with a distribution formed from the most relevant retrievals for a given prefix. While the kNN-LM and related methods yield impressive decreases in perplexity, we discover that they do not exhibit corresponding improvements in open-ended generation quality, as measured by both automatic evaluation metrics (e.g., MAUVE) and human evaluations. Digging deeper, we find that interpolating with a retrieval distribution actually increases perplexity compared to a baseline LM for the majority of tokens in the WikiText-103 test set, even though the overall perplexity is lower due to a smaller number of tokens for which perplexity dramatically decreases after interpolation. However, when decoding a long sequence at inference time, significant improvements on this smaller subset of tokens are washed out by slightly worse predictions on most tokens. Furthermore, we discover that the entropy of the retrieval distribution increases faster than that of the base LM as the generated sequence becomes longer, which indicates that retrieval is less reliable when using model-generated text as queries (i.e., is subject to exposure bias). We hope that our analysis spurs future work on improved decoding algorithms and interpolation strategies for retrieval-augmented language models.

2022

pdf bib
Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text
Amir Pouran Ben Veyseh | Ning Xu | Quan Tran | Varun Manjunatha | Franck Dernoncourt | Thien Nguyen
Findings of the Association for Computational Linguistics: ACL 2022

Toxic span detection is the task of recognizing offensive spans in a text snippet. Although there has been prior work on classifying text snippets as offensive or not, the task of recognizing spans responsible for the toxicity of a text is not explored yet. In this work, we introduce a novel multi-task framework for toxic span detection in which the model seeks to simultaneously predict offensive words and opinion phrases to leverage their inter-dependencies and improve the performance. Moreover, we introduce a novel regularization mechanism to encourage the consistency of the model predictions across similar inputs for toxic span detection. Our extensive experiments demonstrate the effectiveness of the proposed model compared to strong baselines.

pdf bib
Influence Functions for Sequence Tagging Models
Sarthak Jain | Varun Manjunatha | Byron Wallace | Ani Nenkova
Findings of the Association for Computational Linguistics: EMNLP 2022

Many standard tasks in NLP (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions — which aim to trace predictions back to the training points that informed them — to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the “true” segment influence (measured empirically). We show the practical utility of segment influence by using the method to identify noisy annotations in NER corpora.

pdf bib
Keyphrase Prediction from Video Transcripts: New Dataset and Directions
Amir Pouran Ben Veyseh | Quan Hung Tran | Seunghyun Yoon | Varun Manjunatha | Hanieh Deilamsalehy | Rajiv Jain | Trung Bui | Walter W. Chang | Franck Dernoncourt | Thien Huu Nguyen
Proceedings of the 29th International Conference on Computational Linguistics

Keyphrase Prediction (KP) is an established NLP task, aiming to yield representative phrases to summarize the main content of a given document. Despite major progress in recent years, existing works on KP have mainly focused on formal texts such as scientific papers or weblogs. The challenges of KP in informal-text domains are not yet fully studied. To this end, this work studies new challenges of KP in transcripts of videos, an understudied domain for KP that involves informal texts and non-cohesive presentation styles. A bottleneck for KP research in this domain involves the lack of high-quality and large-scale annotated data that hinders the development of advanced KP models. To address this issue, we introduce a large-scale manually-annotated KP dataset in the domain of live-stream video transcripts obtained by automatic speech recognition tools. Concretely, transcripts of 500+ hours of videos streamed on the behance.net platform are manually labeled with important keyphrases. Our analysis of the dataset reveals the challenging nature of KP in transcripts. Moreover, for the first time in KP, we demonstrate the idea of improving KP for long documents (i.e., transcripts) by feeding models with paragraph-level keyphrases, i.e., hierarchical extraction. To foster future research, we will publicly release the dataset and code.

2021

pdf bib
IGA: An Intent-Guided Authoring Assistant
Simeng Sun | Wenlong Zhao | Varun Manjunatha | Rajiv Jain | Vlad Morariu | Franck Dernoncourt | Balaji Vasan Srinivasan | Mohit Iyyer
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

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. We leverage advances in language modeling to build an interactive writing assistant that generates and rephrases text according to fine-grained author specifications. Users provide input to our Intent-Guided Assistant (IGA) in the form of text interspersed with tags that correspond to specific rhetorical directives (e.g., adding description or contrast, or rephrasing a particular sentence). We fine-tune a language model on a dataset heuristically-labeled with author intent, which allows IGA to fill in these tags with generated text that users can subsequently edit to their liking. A series of automatic and crowdsourced evaluations confirm the quality of IGA’s generated outputs, while a small-scale user study demonstrates author preference for IGA over baseline methods in a creative writing task. We release our dataset, code, and demo to spur further research into AI-assisted writing.

pdf bib
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models
Mengnan Du | Varun Manjunatha | Rajiv Jain | Ruchi Deshpande | Franck Dernoncourt | Jiuxiang Gu | Tong Sun | Xia Hu
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. As a result, these models fail to generalize to real-world out-of-distribution data. In this work, we show that the words in the NLU training set can be modeled as a long-tailed distribution. There are two findings: 1) NLU models have strong preference for features located at the head of the long-tailed distribution, and 2) Shortcut features are picked up during very early few iterations of the model training. These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample. Based on this shortcut measurement, we propose a shortcut mitigation framework LGTR, to suppress the model from making overconfident predictions for samples with large shortcut degree. Experimental results on three NLU benchmarks demonstrate that our long-tailed distribution explanation accurately reflects the shortcut learning behavior of NLU models. Experimental analysis further indicates that LGTR can improve the generalization accuracy on OOD data, while preserving the accuracy on in-distribution data.

pdf bib
TABBIE: Pretrained Representations of Tabular Data
Hiroshi Iida | Dung Thai | Varun Manjunatha | Mohit Iyyer
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

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. While this joint pretraining improves tasks involving paired tables and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table-based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model’s learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.

pdf bib
Syntopical Graphs for Computational Argumentation Tasks
Joe Barrow | Rajiv Jain | Nedim Lipka | Franck Dernoncourt | Vlad Morariu | Varun Manjunatha | Douglas Oard | Philip Resnik | Henning Wachsmuth
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of independent claims, losing out on potentially valuable context provided by the rest of the collection. We introduce a general approach to these tasks motivated by syntopical reading, a reading process that emphasizes comparing and contrasting viewpoints in order to improve topic understanding. To capture collection-level context, we introduce the syntopical graph, a data structure for linking claims within a collection. A syntopical graph is a typed multi-graph where nodes represent claims and edges represent different possible pairwise relationships, such as entailment, paraphrase, or support. Experiments applying syntopical graphs to the problems of detecting stance and aspects demonstrate state-of-the-art performance in each domain, significantly outperforming approaches that do not utilize collection-level information.

2020

pdf bib
A Joint Model for Document Segmentation and Segment Labeling
Joe Barrow | Rajiv Jain | Vlad Morariu | Varun Manjunatha | Douglas Oard | Philip Resnik
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Text segmentation aims to uncover latent structure by dividing text from a document into coherent sections. Where previous work on text segmentation considers the tasks of document segmentation and segment labeling separately, we show that the tasks contain complementary information and are best addressed jointly. We introduce Segment Pooling LSTM (S-LSTM), which is capable of jointly segmenting a document and labeling segments. In support of joint training, we develop a method for teaching the model to recover from errors by aligning the predicted and ground truth segments. We show that S-LSTM reduces segmentation error by 30% on average, while also improving segment labeling.

2018

pdf bib
Discovering Canonical Indian English Accents: A Crowdsourcing-based Approach
Sunayana Sitaram | Varun Manjunath | Varun Bharadwaj | Monojit Choudhury | Kalika Bali | Michael Tjalve
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Learning to Color from Language
Varun Manjunatha | Mohit Iyyer | Jordan Boyd-Graber | Larry Davis
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Automatic colorization is the process of adding color to greyscale images. We condition this process on language, allowing end users to manipulate a colorized image by feeding in different captions. We present two different architectures for language-conditioned colorization, both of which produce more accurate and plausible colorizations than a language-agnostic version. Furthermore, we demonstrate through crowdsourced experiments that we can dramatically alter colorizations simply by manipulating descriptive color words in captions.

2015

pdf bib
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
Mohit Iyyer | Varun Manjunatha | Jordan Boyd-Graber | Hal Daumé III
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)