In this paper, we introduce WikiDes, a novel dataset to generate short descriptions of Wikipedia articles for the problem of text summarization.
This paper addresses the problem of dialogue reasoning with contextualized commonsense inference.
Ranked #1 on Answer Generation on CICERO
Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document.
Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation.
We first focus on sentiments expressed in a sentence, then identify the target aspect and opinion terms for that sentiment.
Ranked #3 on Aspect Sentiment Triplet Extraction on ASTE-Data-V2
We propose several strong multimodal baselines and show the importance of contextual and multimodal information for humor recognition in conversations.
We empirically show that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics.
In this work, we provide deeper theoretical analysis and empirical observations on the identifiability of attention weights.
Commonsense inference to understand and explain human language is a fundamental research problem in natural language processing.
Recently, with the advances made in continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction and it is very difficult to keep track of so many papers.
1 code implementation • 22 Dec 2020 • Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu Bai Jian, Pengfei Hong, Romila Ghosh, Abhinaba Roy, Niyati Chhaya, Alexander Gelbukh, Rada Mihalcea
We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong Transformer-based baselines.
Ranked #1 on Causal Emotion Entailment on RECCON
Zero shot learning -- the problem of training and testing on a completely disjoint set of classes -- relies greatly on its ability to transfer knowledge from train classes to test classes.
Persuasion aims at forming one's opinion and action via a series of persuasive messages containing persuader's strategies.
In this paper, we address the task of utterance level emotion recognition in conversations using commonsense knowledge.
Ranked #8 on Emotion Recognition in Conversation on EmoryNLP
Current approaches to empathetic response generation view the set of emotions expressed in the input text as a flat structure, where all the emotions are treated uniformly.
Most of these approaches account for the context for effective understanding.
As a result, predictions of downstream NLP models can vary noticeably by varying gender words, such as replacing "he" to "she", or even gender-neutral words.
This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context.
Ranked #7 on Dialog Relation Extraction on DialogRE (F1c (v1) metric)
Aspect-based sentiment analysis (ABSA), a popular research area in NLP has two distinct parts -- aspect extraction (AE) and labeling the aspects with sentiment polarity (ALSA).
Cross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of sentiment analysis.
Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago.
Emotion recognition in conversation (ERC) has received much attention, lately, from researchers due to its potential widespread applications in diverse areas, such as health-care, education, and human resources.
Ranked #1 on Emotion Recognition in Conversation on SEMAINE
Multimodal fusion is considered a key step in multimodal tasks such as sentiment analysis, emotion detection, question answering, and others.
This review paper provides an overview of the most popular approaches to automated personality detection, various computational datasets, its industrial applications, and state-of-the-art machine learning models for personality detection with specific focus on multimodal approaches.
Emotion is intrinsic to humans and consequently emotion understanding is a key part of human-like artificial intelligence (AI).
Ranked #6 on Emotion Recognition in Conversation on EC
We argue that knowledge in sarcasm detection can also be beneficial to sentiment classification and vice versa.
Emotion detection in conversations is a necessary step for a number of applications, including opinion mining over chat history, social media threads, debates, argumentation mining, understanding consumer feedback in live conversations, etc.
Ranked #3 on Emotion Recognition in Conversation on SEMAINE
We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations.
Ranked #37 on Emotion Recognition in Conversation on MELD
Sentiment analysis has immense implications in e-commerce through user feedback mining.
We compile baselines, along with dataset split, for multimodal sentiment analysis.
Automatic deception detection is an important task that has gained momentum in computational linguistics due to its potential applications.
Multimodal sentiment analysis is a developing area of research, which involves the identification of sentiments in videos.
Ranked #3 on Emotion Recognition in Conversation on CPED