Search Results for author:
Found 40 papers, 25 papers with code
Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains.
Causal Augmentation for Causal Sentence Classification
Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification.
Methods for Numeracy-Preserving Word Embeddings
We propose a new methodology to assign and learn embeddings for numbers.
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to user preferences in a long-context conversational setting.
From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues
Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions.
CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs
We apply CESAR on InstructDial, a benchmark for instruction-based dialog tasks.
Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations.
"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
We hope this task and dataset can promote further research on TOD and subjective content understanding.
KILM: Knowledge Injection into Encoder-Decoder Language Models
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.
Role of Bias Terms in Dot-Product Attention
Moreover, we argue that the bias term of the value linear transformation has a more prominent role than that of the bias term of the query linear transformation.
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
This work focuses on in-context data augmentation for intent detection.
Ranked #1 on
Intent Detection
on BANKING77 10-shot
Using In-Context Learning to Improve Dialogue Safety
For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.
Analyzing Modality Robustness in Multimodal Sentiment Analysis
In this work, we hope to address that by (i) Proposing simple diagnostic checks for modality robustness in a trained multimodal model.
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
Automatic transfer of text between domains has become popular in recent times.
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks.
Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication
We empirically show that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics.
Zero-Shot Controlled Generation with Encoder-Decoder Transformers
In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero-shot.
Recognizing Emotion Cause in Conversations
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
Recognizing Emotion Cause in Conversations
on RECCON
Domain Divergences: a Survey and Empirical Analysis
Domain divergence plays a significant role in estimating the performance of a model in new domains.
Multimodal Research in Vision and Language: A Review of Current and Emerging Trends
Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data.
MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis
In this paper, we aim to learn effective modality representations to aid the process of fusion.
KinGDOM: Knowledge-Guided DOMain adaptation for sentiment analysis
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.
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research
Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago.
Conversational Transfer Learning for Emotion Recognition
We propose an approach, TL-ERC, where we pre-train a hierarchical dialogue model on multi-turn conversations (source) and then transfer its parameters to a conversational emotion classifier (target).
Ranked #20 on
Emotion Recognition in Conversation
on DailyDialog
Towards Multimodal Sarcasm Detection (An \_Obviously\_ Perfect Paper)
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)
As a first step towards enabling the development of multimodal approaches for sarcasm detection, we propose a new sarcasm dataset, Multimodal Sarcasm Detection Dataset (MUStARD), compiled from popular TV shows.
Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining
With the multitude of companies and organizations abound today, ranking them and choosing one out of the many is a difficult and cumbersome task.
DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
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
Emotion Classification
Emotion Recognition in Conversation
+2
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations.
ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection
Emotion recognition in conversations is crucial for building empathetic machines.
Ranked #55 on
Emotion Recognition in Conversation
on IEMOCAP
Emotion Recognition in Conversation
General Classification
+2
Modeling Inter-Aspect Dependencies for Aspect-Based Sentiment Analysis
Aspect-based Sentiment Analysis is a fine-grained task of sentiment classification for multiple aspects in a sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos
Emotion recognition in conversations is crucial for the development of empathetic machines.
Ranked #57 on
Emotion Recognition in Conversation
on IEMOCAP
CASCADE: Contextual Sarcasm Detection in Online Discussion Forums
The literature in automated sarcasm detection has mainly focused on lexical, syntactic and semantic-level analysis of text.
Ranked #1 on
Sarcasm Detection
on SARC (all-bal)
Multimodal Sentiment Analysis: Addressing Key Issues and Setting up the Baselines
We compile baselines, along with dataset split, for multimodal sentiment analysis.
Texture and Structure Incorporated ScatterNet Hybrid Deep Learning Network (TS-SHDL) For Brain Matter Segmentation
Automation of brain matter segmentation from MR images is a challenging task due to the irregular boundaries between the grey and white matter regions.
Recent Trends in Deep Learning Based Natural Language Processing
Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains.
Benchmarking Multimodal Sentiment Analysis
We propose a framework for multimodal sentiment analysis and emotion recognition using convolutional neural network-based feature extraction from text and visual modalities.
Context-Dependent Sentiment Analysis in User-Generated Videos
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
Emotion Recognition in Conversation
General Classification
+4
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks
Sarcasm detection is a key task for many natural language processing tasks.
