Soujanya Poria

Sentic LDA: Improving on LDA with semantic similarity for aspect-based sentiment analysis

2016

The advent of the Social Web has provided netizens with new tools for creating and sharing, in a time- and cost-efficient way, their contents, ideas, and opinions with virtually the millions of people connected to …

SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis

2020

Deep learning has unlocked new paths towards the emulation of the peculiarly-human capability of learning from examples. While this kind of bottom-up learning works well for tasks such as image classification or object detection, it …

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of coherence with respect to the chronological sequence of events …

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

2022 · arXiv (Cornell University)

Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text classification. SAT first generates two augmented …

Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts

2022 · arXiv (Cornell University)

Multimodal sentiment analysis has gained significant attention due to the proliferation of multimodal content on social media. However, existing studies in this area rely heavily on large-scale supervised data, which is time-consuming and labor-intensive to …

ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation

2023 · arXiv (Cornell University)

There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-represented in the training data. To address this issue, …

PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis

2024 · arXiv (Cornell University)

While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly integrating multimodality, conversation context, fine-granularity, and also covering the changing sentiment …

Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics

2025 · arXiv (Cornell University)

RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing …

A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks

2016 · arXiv (Cornell University)

Sarcasm detection is a key task for many natural language processing tasks. In sentiment analysis, for example, sarcasm can flip the polarity of an "apparently positive" sentence and, hence, negatively affect polarity detection performance. To …

Recent Trends in Deep Learning Based Natural Language Processing

2017 · arXiv (Cornell University)

Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of …

Sentiment Analysis Is a Big Suitcase

2017 · IEEE Intelligent Systems

Although most works approach it as a simple categorization problem, sentiment analysis is actually a suitcase research problem that requires tackling many natural language processing (NLP) tasks. The expression “sentiment analysis” itself is a big …

Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph

2018

AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, Louis-Philippe Morency. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

2018 · IEEE Computational Intelligence Magazine

Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of …

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

2021 · arXiv (Cornell University)

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a …

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

2023

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or …