Vivek Kulkarni


pdf bib
SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks
Gourab Dey | Adithya V Ganesan | Yash Kumar Lal | Manal Shah | Shreyashee Sinha | Matthew Matero | Salvatore Giorgi | Vivek Kulkarni | H. Schwartz
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)

Social science NLP tasks, such as emotion or humor detection, are required to capture the semantics along with the implicit pragmatics from text, often with limited amounts of training data. Instruction tuning has been shown to improve the many capabilities of large language models (LLMs) such as commonsense reasoning, reading comprehension, and computer programming. However, little is known about the effectiveness of instruction tuning on the social domain where implicit pragmatic cues are often needed to be captured. We explore the use of instruction tuning for social science NLP tasks and introduce Socialite-Llama — an open-source, instruction-tuned Llama. On a suite of 20 social science tasks, Socialite-Llama improves upon the performance of Llama as well as matches or improves upon the performance of a state-of-the-art, multi-task finetuned model on a majority of them. Further, Socialite-Llama also leads to improvement on 5 out of 6 related social tasks as compared to Llama, suggesting instruction tuning can lead to generalized social understanding. All resources including our code, model and dataset can be found through [](

pdf bib
Personalized Text Generation with Fine-Grained Linguistic Control
Bashar Alhafni | Vivek Kulkarni | Dhruv Kumar | Vipul Raheja
Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024)

As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on controllable text generation focuses on controlling the content or modeling specific high-level/coarse-grained attributes that reflect authors’ writing styles, such as formality, domain, or sentiment. In this paper, we focus on controlling fine-grained attributes spanning multiple linguistic dimensions, such as lexical and syntactic attributes. We introduce a novel benchmark to train generative models and evaluate their ability to generate personalized text based on multiple fine-grained linguistic attributes. We systematically investigate the performance of various large language models on our benchmark and draw insights from the factors that impact their performance. We make our code, data, models, and benchmarks publicly available.


pdf bib
CTM - A Model for Large-Scale Multi-View Tweet Topic Classification
Vivek Kulkarni | Kenny Leung | Aria Haghighi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

Automatically associating social media posts with topics is an important prerequisite for effective search and recommendation on many social media platforms. However, topic classification of such posts is quite challenging because of (a) a large topic space (b) short text with weak topical cues, and (c) multiple topic associations per post. In contrast to most prior work which only focuses on post-classification into a small number of topics (10-20), we consider the task of large-scale topic classification in the context of Twitter where the topic space is 10 times larger with potentially multiple topic associations per Tweet. We address the challenges above and propose a novel neural model, that (a) supports a large topic space of 300 topics (b) takes a holistic approach to tweet content modeling – leveraging multi-modal content, author context, and deeper semantic cues in the Tweet. Our method offers an effective way to classify Tweets into topics at scale by yielding superior performance to other approaches (a relative lift of 20% in median average precision score) and has been successfully deployed in production at Twitter.

pdf bib
NTULM: Enriching Social Media Text Representations with Non-Textual Units
Jinning Li | Shubhanshu Mishra | Ahmed El-Kishky | Sneha Mehta | Vivek Kulkarni
Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)

On social media, additional context is often present in the form of annotations and meta-data such as the post’s author, mentions, Hashtags, and hyperlinks. We refer to these annotations as Non-Textual Units (NTUs). We posit that NTUs provide social context beyond their textual semantics and leveraging these units can enrich social media text representations. In this work we construct an NTU-centric social heterogeneous network to co-embed NTUs. We then principally integrate these NTU embeddings into a large pretrained language model by fine-tuning with these additional units. This adds context to noisy short-text social media. Experiments show that utilizing NTU-augmented text representations significantly outperforms existing text-only baselines by 2-5% relative points on many downstream tasks highlighting the importance of context to social media NLP. We also highlight that including NTU context into the initial layers of language model alongside text is better than using it after the text embedding is generated. Our work leads to the generation of holistic general purpose social media content embedding.


pdf bib
LMSOC: An Approach for Socially Sensitive Pretraining
Vivek Kulkarni | Shubhanshu Mishra | Aria Haghighi
Findings of the Association for Computational Linguistics: EMNLP 2021

While large-scale pretrained language models have been shown to learn effective linguistic representations for many NLP tasks, there remain many real-world contextual aspects of language that current approaches do not capture. For instance, consider a cloze test “I enjoyed the _____ game this weekend”: the correct answer depends heavily on where the speaker is from, when the utterance occurred, and the speaker’s broader social milieu and preferences. Although language depends heavily on the geographical, temporal, and other social contexts of the speaker, these elements have not been incorporated into modern transformer-based language models. We propose a simple but effective approach to incorporate speaker social context into the learned representations of large-scale language models. Our method first learns dense representations of social contexts using graph representation learning algorithms and then primes language model pretraining with these social context representations. We evaluate our approach on geographically-sensitive language modeling tasks and show a substantial improvement (more than 100% relative lift on MRR) compared to baselines.


pdf bib
TopicBERT for Energy Efficient Document Classification
Yatin Chaudhary | Pankaj Gupta | Khushbu Saxena | Vivek Kulkarni | Thomas Runkler | Hinrich Schütze
Findings of the Association for Computational Linguistics: EMNLP 2020

Prior research notes that BERT’s computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. While recent work seeks to address these scalability issues at pre-training, these issues are also prominent in fine-tuning especially for long sequence tasks like document classification. Our work thus focuses on optimizing the computational cost of fine-tuning for document classification. We achieve this by complementary learning of both topic and language models in a unified framework, named TopicBERT. This significantly reduces the number of self-attention operations – a main performance bottleneck. Consequently, our model achieves a 1.4x ( 40%) speedup with 40% reduction in CO2 emission while retaining 99.9% performance over 5 datasets.

pdf bib
DialectGram: Automatic Detection of Dialectal Changes with Multi-geographic Resolution Analysis
Hang Jiang | Haoshen Hong | Yuxing Chen | Vivek Kulkarni
Proceedings of the Society for Computation in Linguistics 2020


pdf bib
TWEETQA: A Social Media Focused Question Answering Dataset
Wenhan Xiong | Jiawei Wu | Hong Wang | Vivek Kulkarni | Mo Yu | Shiyu Chang | Xiaoxiao Guo | William Yang Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

With social media becoming increasingly popular on which lots of news and real-time events are reported, developing automated question answering systems is critical to the effective-ness of many applications that rely on real-time knowledge. While previous datasets have concentrated on question answering (QA) for formal text like news and Wikipedia, we present the first large-scale dataset for QA over social media data. To ensure that the tweets we collected are useful, we only gather tweets used by journalists to write news articles. We then ask human annotators to write questions and answers upon these tweets. Unlike otherQA datasets like SQuAD in which the answers are extractive, we allow the answers to be abstractive. We show that two recently proposed neural models that perform well on formal texts are limited in their performance when applied to our dataset. In addition, even the fine-tuned BERT model is still lagging behind human performance with a large margin. Our results thus point to the need of improved QA systems targeting social media text.

pdf bib
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog.
Pushkar Shukla | Carlos Elmadjian | Richika Sharan | Vivek Kulkarni | Matthew Turk | William Yang Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image.


pdf bib
Multi-view Models for Political Ideology Detection of News Articles
Vivek Kulkarni | Junting Ye | Steve Skiena | William Yang Wang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

A news article’s title, content and link structure often reveal its political ideology. However, most existing works on automatic political ideology detection only leverage textual cues. Drawing inspiration from recent advances in neural inference, we propose a novel attention based multi-view model to leverage cues from all of the above views to identify the ideology evinced by a news article. Our model draws on advances in representation learning in natural language processing and network science to capture cues from both textual content and the network structure of news articles. We empirically evaluate our model against a battery of baselines and show that our model outperforms state of the art by 10 percentage points F1 score.

pdf bib
Simple Models for Word Formation in Slang
Vivek Kulkarni | William Yang Wang
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

We propose the first generative models for three types of extra-grammatical word formation phenomena abounding in slang: Blends, Clippings, and Reduplicatives. Adopting a data-driven approach coupled with linguistic knowledge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang – insights which are increasingly relevant in the context of the rising prevalence of slang and non-standard varieties on the Internet

pdf bib
Simple Neologism Based Domain Independent Models to Predict Year of Authorship
Vivek Kulkarni | Yingtao Tian | Parth Dandiwala | Steve Skiena
Proceedings of the 27th International Conference on Computational Linguistics

We present domain independent models to date documents based only on neologism usage patterns. Our models capture patterns of neologism usage over time to date texts, provide insights into temporal locality of word usage over a span of 150 years, and generalize to various domains like News, Fiction, and Non-Fiction with competitive performance. Quite intriguingly, we show that by modeling only the distribution of usage counts over neologisms (the model being agnostic of the particular words themselves), we achieve competitive performance using several orders of magnitude fewer features (only 200 input features) compared to state of the art models some of which use 200K features.


pdf bib
Human Centered NLP with User-Factor Adaptation
Veronica Lynn | Youngseo Son | Vivek Kulkarni | Niranjan Balasubramanian | H. Andrew Schwartz
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We pose the general task of user-factor adaptation – adapting supervised learning models to real-valued user factors inferred from a background of their language, reflecting the idea that a piece of text should be understood within the context of the user that wrote it. We introduce a continuous adaptation technique, suited for real-valued user factors that are common in social science and bringing us closer to personalized NLP, adapting to each user uniquely. We apply this technique with known user factors including age, gender, and personality traits, as well as latent factors, evaluating over five tasks: POS tagging, PP-attachment, sentiment analysis, sarcasm detection, and stance detection. Adaptation provides statistically significant benefits for 3 of the 5 tasks: up to +1.2 points for PP-attachment, +3.4 points for sarcasm, and +3.0 points for stance.

pdf bib
On the Distribution of Lexical Features at Multiple Levels of Analysis
Fatemeh Almodaresi | Lyle Ungar | Vivek Kulkarni | Mohsen Zakeri | Salvatore Giorgi | H. Andrew Schwartz
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Natural language processing has increasingly moved from modeling documents and words toward studying the people behind the language. This move to working with data at the user or community level has presented the field with different characteristics of linguistic data. In this paper, we empirically characterize various lexical distributions at different levels of analysis, showing that, while most features are decidedly sparse and non-normal at the message-level (as with traditional NLP), they follow the central limit theorem to become much more Log-normal or even Normal at the user- and county-levels. Finally, we demonstrate that modeling lexical features for the correct level of analysis leads to marked improvements in common social scientific prediction tasks.