Alakananda Vempala


2023

pdf bib
Don’t Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text
Ashim Gupta | Carter Blum | Temma Choji | Yingjie Fei | Shalin Shah | Alakananda Vempala | Vivek Srikumar
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite adversarial inputs to make them non-adversarial for a downstream text classifier. Our experiments on four datasets and five attack mechanisms reveal that ATINTER is effective at providing better adversarial robustness than existing defense approaches, without compromising task accuracy. For example, on sentiment classification using the SST-2 dataset, our method improves the adversarial accuracy over the best existing defense approach by more than 4% with a smaller decrease in task accuracy (0.5 % vs 2.5%). Moreover, we show that ATINTER generalizes across multiple downstream tasks and classifiers without having to explicitly retrain it for those settings. For example, we find that when ATINTER is trained to remove adversarial perturbations for the sentiment classification task on the SST-2 dataset, it even transfers to a semantically different task of news classification (on AGNews) and improves the adversarial robustness by more than 10%.

2022

pdf bib
Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning
Vivek Gupta | Shuo Zhang | Alakananda Vempala | Yujie He | Temma Choji | Vivek Srikumar
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

When pre-trained contextualized embedding-based models developed for unstructured data are adapted for structured tabular data, they perform admirably. However, recent probing studies show that these models use spurious correlations, and often predict inference labels by focusing on false evidence or ignoring it altogether. To study this issue, we introduce the task of Trustworthy Tabular Reasoning, where a model needs to extract evidence to be used for reasoning, in addition to predicting the label. As a case study, we propose a two-stage sequential prediction approach, which includes an evidence extraction and an inference stage. First, we crowdsource evidence row labels and develop several unsupervised and supervised evidence extraction strategies for InfoTabS, a tabular NLI benchmark. Our evidence extraction strategy outperforms earlier baselines. On the downstream tabular inference task, using only the automatically extracted evidence as the premise, our approach outperforms prior benchmarks.

2019

pdf bib
Categorizing and Inferring the Relationship between the Text and Image of Twitter Posts
Alakananda Vempala | Daniel Preoţiuc-Pietro
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Text in social media posts is frequently accompanied by images in order to provide content, supply context, or to express feelings. This paper studies how the meaning of the entire tweet is composed through the relationship between its textual content and its image. We build and release a data set of image tweets annotated with four classes which express whether the text or the image provides additional information to the other modality. We show that by combining the text and image information, we can build a machine learning approach that accurately distinguishes between the relationship types. Further, we derive insights into how these relationships are materialized through text and image content analysis and how they are impacted by user demographic traits. These methods can be used in several downstream applications including pre-training image tagging models, collecting distantly supervised data for image captioning, and can be directly used in end-user applications to optimize screen estate.

2018

pdf bib
Annotating Temporally-Anchored Spatial Knowledge by Leveraging Syntactic Dependencies
Alakananda Vempala | Eduardo Blanco
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Annotating If the Authors of a Tweet are Located at the Locations They Tweet About
Vivek Doudagiri | Alakananda Vempala | Eduardo Blanco
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Determining Event Durations: Models and Error Analysis
Alakananda Vempala | Eduardo Blanco | Alexis Palmer
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

This paper presents models to predict event durations. We introduce aspectual features that capture deeper linguistic information than previous work, and experiment with neural networks. Our analysis shows that tense, aspect and temporal structure of the clause provide useful clues, and that an LSTM ensemble captures relevant context around the event.

2017

pdf bib
Determining Whether and When People Participate in the Events They Tweet About
Krishna Chaitanya Sanagavarapu | Alakananda Vempala | Eduardo Blanco
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

This paper describes an approach to determine whether people participate in the events they tweet about. Specifically, we determine whether people are participants in events with respect to the tweet timestamp. We target all events expressed by verbs in tweets, including past, present and events that may occur in the future. We present new annotations using 1,096 event mentions, and experimental results showing that the task is challenging.

2016

pdf bib
Annotating Temporally-Anchored Spatial Knowledge on Top of OntoNotes Semantic Roles
Alakananda Vempala | Eduardo Blanco
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

This paper presents a two-step methodology to annotate spatial knowledge on top of OntoNotes semantic roles. First, we manipulate semantic roles to automatically generate potential additional spatial knowledge. Second, we crowdsource annotations with Amazon Mechanical Turk to either validate or discard the potential additional spatial knowledge. The resulting annotations indicate whether entities are or are not located somewhere with a degree of certainty, and temporally anchor this spatial information. Crowdsourcing experiments show that the additional spatial knowledge is ubiquitous and intuitive to humans, and experimental results show that it can be inferred automatically using standard supervised machine learning techniques.

pdf bib
Beyond Plain Spatial Knowledge: Determining Where Entities Are and Are Not Located, and For How Long
Alakananda Vempala | Eduardo Blanco
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
Inferring Temporally-Anchored Spatial Knowledge from Semantic Roles
Eduardo Blanco | Alakananda Vempala
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies