Laiba Mehnaz's research while affiliated with Delhi Technological University 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.

Publications (8)

Figure 1: 1a shows the distribution over number of utterances per...
Performances on automatic metrics for generating English summaries from...
Performances on automatic metrics for generating English summaries from...
Human evaluation of the generated summaries (English) from...
GupShup: An Annotated Corpus for Abstractive Summarization of Open-Domain Code-Switched Conversations
Preprint
Full-text available
  • Apr 2021
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...
Cite
Download full-text
Cite
Download full-text
Figure 1: Confusion matrix training data
Performance of different models on the pro- vided train and test...
Suggestion Mining from Online Reviews using ULMFiT
Preprint
Full-text available
  • Apr 2019
In this paper we present our approach and the system description for Sub Task A of SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. Given a sentence, the task asks to predict whether the sentence consists of a suggestion or not. Our model is based on Universal Language Model Fine-tuning for Text Classification. We apply variou...
Cite
Download full-text
Figure 1: Distribution of classes (OFF -Offensive and NOT -Not...
Figure 3: Confusion Matrix for MIDAS submission 2 for Sub-task A.
Figure 4: Confusion Matrix for MIDAS submission 1 for Sub-task B.
Results for Sub-task A.
Identifying Offensive Posts and Targeted Offense from Twitter
Preprint
Full-text available
  • Apr 2019
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 or not, and Sub Task B involves detecting if an offensive tweet is targeted towards someone (group or an...
Cite
Download full-text
Cite
Download full-text
Cite
Download full-text
Cite
Request full-text
Cite
Download full-text

Citations

... 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. ...
Reference: CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization
View full-text
... After training on the WIkitext 103 dataset, the model is finetuned for a new dataset. Based on ULMFiT, Anand et al. [42] proposed a suggestion-mining approach for forums and online reviews. They also presented a system description for SubTask A of SemEval 2019 Task 9. ...
Reference: BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets
View full-text
... However, shows limited ability with domains containing high types and slang such as social media [36]. The embedding size affects the quality of results, large embeddings provide consistent results [28] while higher dimensions may not improve the performance [100]. Another limitation of word embeddings resides in handling out-of-vocabulary (OOV) words which can be partially overcome using character-level embeddings information [101]. ...
Reference: Sentiment analysis in SemEval: a review of sentiment identification approaches
View
... Methods based on neural networks became a more common choice [25,17]. During the latest instance of SMM4H, co-located with ACL 2019, transformersbased architectures such as BERT [6] and BioBERT [13] were the building blocks of the top performing systems [2,14,15]. However, these recent shared tasks have focused on a very particular type of social media texts: tweets, which are short, highly informal and noisy texts. ...
Reference: Improving Adverse Drug Event Extraction with SpanBERT on Different Text Typologies
View full-text
... Social media applications such as Twitter were effective in raising blood donation requests and dissemination, reducing the gap between blood donors and the people in need. 14,15 Among the various social media applications, WhatsApp was effective in managing the blood donation process. 16 However, a similar study in Brazil identified there was no significant impact of WhatsApp in increasing the number of blood donors and the retention rates of existing donors. ...
Reference: The Impact of WhatsApp on the Blood Donation Process in Saudi Arabia
View full-text