Yaman Kumar


2023

pdf
Synthesizing Human Gaze Feedback for Improved NLP Performance
Varun Khurana | Yaman Kumar | Nora Hollenstein | Rajesh Kumar | Balaji Krishnamurthy
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human cognitive signals in the form of eyetracking). Prior eye tracking and NLP research reveal that cognitive processes, such as human scanpaths, gleaned from human gaze patterns aid in the understanding and performance of NLP models. However, the collection of real eyetracking data for NLP tasks is challenging due to the requirement of expensive and precise equipment coupled with privacy invasion issues. To address this challenge, we propose ScanTextGAN, a novel model for generating human scanpaths over text. We show that ScanTextGAN-generated scanpaths can approximate meaningful cognitive signals in human gaze patterns. We include synthetically generated scanpaths in four popular NLP tasks spanning six different datasets as proof of concept and show that the models augmented with generated scanpaths improve the performance of all downstream NLP tasks.

2020

pdf
An Annotated Dataset of Discourse Modes in Hindi Stories
Swapnil Dhanwal | Hritwik Dutta | Hitesh Nankani | Nilay Shrivastava | Yaman Kumar | Junyi Jessy Li | Debanjan Mahata | Rakesh Gosangi | Haimin Zhang | Rajiv Ratn Shah | Amanda Stent
Proceedings of the Twelfth Language Resources and Evaluation Conference

In this paper, we present a new corpus consisting of sentences from Hindi short stories annotated for five different discourse modes argumentative, narrative, descriptive, dialogic and informative. We present a detailed account of the entire data collection and annotation processes. The annotations have a very high inter-annotator agreement (0.87 k-alpha). We analyze the data in terms of label distributions, part of speech tags, and sentence lengths. We characterize the performance of various classification algorithms on this dataset and perform ablation studies to understand the nature of the linguistic models suitable for capturing the nuances of the embedded discourse structures in the presented corpus.

2019

pdf
MIDAS at SemEval-2019 Task 6: Identifying Offensive Posts and Targeted Offense from Twitter
Debanjan Mahata | Haimin Zhang | Karan Uppal | Yaman Kumar | Rajiv Ratn Shah | Simra Shahid | Laiba Mehnaz | Sarthak Anand
Proceedings of the 13th International Workshop on Semantic Evaluation

In this paper we present our approach and the system description for Sub Task A and Sub Task B of SemEval 2019 Task 6: Identifying and Categorizing Offensive Language in Social Media. Sub Task A involves identifying if a given tweet is offensive and Sub Task B involves detecting if an offensive tweet is targeted towards someone (group or an individual). Our models for Sub Task A is based on an ensemble of Convolutional Neural Network and Bidirectional LSTM, whereas for Sub Task B, we rely on a set of heuristics derived from the training data. We provide detailed analysis of the results obtained using the trained models. Our team ranked 5th out of 103 participants in Sub Task A, achieving a macro F1 score of 0.807, and ranked 8th out of 75 participants achieving a macro F1 of 0.695.

pdf
MIDAS at SemEval-2019 Task 9: Suggestion Mining from Online Reviews using ULMFit
Sarthak Anand | Debanjan Mahata | Kartik Aggarwal | Laiba Mehnaz | Simra Shahid | Haimin Zhang | Yaman Kumar | Rajiv Shah | Karan Uppal
Proceedings of the 13th International Workshop on Semantic Evaluation

In this paper we present our approach to tackle the Suggestion Mining from Online Reviews and Forums Sub-Task A. Given a review, we are asked to predict whether the review consists of a suggestion or not. Our model is based on Universal Language Model Fine-tuning for Text Classification. We apply various pre-processing techniques before training the language and the classification model. We further provide analysis of the model. Our team ranked 10th out of 34 participants, achieving an F1 score of 0.7011.

pdf
MIDAS@SMM4H-2019: Identifying Adverse Drug Reactions and Personal Health Experience Mentions from Twitter
Debanjan Mahata | Sarthak Anand | Haimin Zhang | Simra Shahid | Laiba Mehnaz | Yaman Kumar | Rajiv Ratn Shah
Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task

In this paper, we present our approach and the system description for the Social Media Mining for Health Applications (SMM4H) Shared Task 1,2 and 4 (2019). Our main contribution is to show the effectiveness of Transfer Learning approaches like BERT and ULMFiT, and how they generalize for the classification tasks like identification of adverse drug reaction mentions and reporting of personal health problems in tweets. We show the use of stacked embeddings combined with BLSTM+CRF tagger for identifying spans mentioning adverse drug reactions in tweets. We also show that these approaches perform well even with imbalanced dataset in comparison to undersampling and oversampling.