Rakesh Gosangi's research while affiliated with CUNY Graduate Center and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (15)
In this paper, we study the importance of context in predicting the citation worthiness of sentences in scholarly articles. We formulate this problem as a sequence labeling task solved using a hierarchical BiLSTM model. We contribute a new benchmark dataset containing over two million sentences and their corresponding labels. We preserve the senten...
Code-switching is the communication phenomenon where speakers switch between different languages during a conversation. With the widespread adoption of conversational agents and chat platforms, code-switching has become an integral part of written conversations in many multi-lingual communities worldwide. This makes it essential to develop techniqu...
We introduce a new keyphrase generation approach using Generative Adversar-ial Networks (GANs). For a given document , the generator produces a sequence of keyphrases, and the discriminator distinguishes between human-curated and machine-generated keyphrases. We evaluated this approach on standard benchmark datasets. We observed that our model achi...
This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with various contextual embedding models. We also employ label distribution learning to account for annotator disagreements. We experim...
In this paper, we present a dataset containing 9,973 tweets related to the MeToo movement that were manually annotated for five different linguistic aspects: relevance, stance, hate speech, sarcasm, and dialogue acts. We present a detailed account of the data collection and annotation processes. The annotations have a very high inter-annotator agre...
In this paper, we present a keyphrase generation approach using conditional Generative Adversarial Networks (GAN). In our GAN model, the generator outputs a sequence of keyphrases based on the title and abstract of a scientific article. The discriminator learns to distinguish between machine-generated and human-curated keyphrases. We evaluate this...
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We evaluate the proposed architecture using both contextualized and fixed word embedding models on three different benchmark datasets,...
In this paper, we present a dataset containing 9,973 tweets related to the MeToo movement that were manually annotated for five different linguistic aspects: relevance, stance, hate speech, sarcasm, and dialogue acts. We present a detailed account of the data collection and annotation processes. The annotations have a very high inter-annotator agre...
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We evaluate the proposed architecture using both contextualized and fixed word embedding models on three different benchmark datasets...
In this paper, we present a keyphrase generation approach using conditional Generative Adversarial Networks (GAN). In our GAN model, the generator outputs a sequence of keyphrases based on the title and abstract of a scientific article. The discriminator learns to distinguish between machine-generated and human-curated keyphrases. We evaluate this...
Dialogue act (DA) classification has been studied for the past two decades and has several key applications such as workflow automation and conversation analytics. Researchers have used, to address this problem, various traditional machine learning models, and more recently deep neural network models such as hierarchical convolutional neural networ...
Citations
... Through studying the #MeToo movement, several studies [1]- [3] have attempted to aggregate such experiences of sexual abuse to facilitate a better understanding of social media constructs and to bring about social change. It has been found that disclosure of abuse has positive psychological impacts. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/1015300610875402-1619077937499_Q64/Akash-Gautam-5.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/948742589014018-1603209268577_Q64/Puneet-Mathur-4.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/279059406835717-1443544355460_Q64/Debanjan-Mahata.jpg)
... Humans, on the other hand, may sometimes code-switch between languages, especially when there is no appropriate translation, or when readers are more familiar with foreign entities. There have been summarization resources addressing the code-switching phenomenon (Mehnaz et al., 2021), but they focus on summarizing from already code-switched source texts. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/935520699940864-1600056924301_Q64/Uma_Gunturi.jpg)
... Recent research interest towards these tasks often uses label distribution learning (Shirani et al., 2019). MIDAS (Anand et al., 2020) uses label distribution as well as contextual embeddings. One drawback of using label distribution learning is the requirement of annotations, which are not readily available in most datasets. ...
... The second category uses the clustering method to cluster the key-term candidates into different topics and then takes the words nearest to the center of important topics as the extracted key-terms (Liu et al. 2009(Liu et al. , 2010Grineva et al. 2009). Besides, the recent advances of deep learning also bring promising success in the third category, which uses neural network-based methods to generate key-terms (Ahmad et al. 2021;Mou et al. 2016;Bahuleyan and Asri 2020;Chen et al. 2019c;Chan et al. 2019;See et al. 2017;Subramanian et al. 2018;Swaminathan et al. 2020;Ye and Wang 2018;Zhang et al. 2016;Luan et al. 2017;Meng et al. 2017;Paulus et al. 2018;Zhang et al. 2017). The last category leverages some external resources (e.g., knowledge graphs) to further enhance the generation of key-terms (Shi et al. 2017;Tosi and dos Reis 2021). ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/788116243755009-1564912963700_Q64/Avinash-Swaminathan.jpg)
... The model was set up in a way reminiscent of the unsupervised multilingual translation, where multiple independent networks work together to achieve diverse objectives (reconstruction loss, IOB loss, discriminator loss, and the like). The work reported a substantial gain over strong baselines, which included a model similar to CRF/DL [33,50,68]. (Figs. 4 and 5 give a high-level picture of how it works.) ...
Reference: Keyword Extraction: A Modern Perspective
![[object Object]](https://i1.rgstatic.net/ii/profile.image/277501071904779-1443172819577_Q64/Roger-Zimmermann-2.jpg)
