Textual style transfer is the task of transforming stylistic properties ...
The design of automatic speech pronunciation assessment can be categoriz...
Despite advancements in conversational AI, language models encounter
cha...
Filter pruning simultaneously accelerates the computation and reduces th...
Designing systems that can reason across cultures requires that they are...
Mixed-initiative dialogue tasks involve repeated exchanges of informatio...
Building benchmarks to systemically analyze different capabilities of vi...
In this 4-page manuscript we discuss the problem of long-term AI Safety ...
Along with the development of systems for natural language understanding...
Research interest in task-oriented dialogs has increased as systems such...
While current dialogue systems like ChatGPT have made significant
advanc...
Knowledge-based visual question answering (VQA) requires external knowle...
Large language models (LLMs) effectively generate fluent text when the t...
Speech models have long been known to overfit individual speakers for ma...
Large language models (LLMs), such as ChatGPT, are able to generate
huma...
Prompt-based methods with large pre-trained language models (PLMs) have ...
Given the success with in-context learning of large pre-trained language...
Dialogue summarization has recently garnered significant attention due t...
Conversational text-to-SQL is designed to translate multi-turn natural
l...
Training dialogue systems often entails dealing with noisy training exam...
News Image Captioning requires describing an image by leveraging additio...
In task-oriented dialogs such as MultiWoZ (Budzianowski et al., 2018), a...
Existing approaches built separate classifiers to detect nonsense in
dia...
Dialog systems are often designed or trained to output human-like respon...
Affective responses to music are highly personal. Despite consensus that...
Dialogue systems capable of social influence such as persuasion, negotia...
In-context learning (ICL) suffers from oversensitivity to the prompt, wh...
Transformer encoder-decoder models have shown impressive performance in
...
This paper reports on progress towards building an online language learn...
We introduce GODEL (Grounded Open Dialogue Language Model), a large
pre-...
Prompt tuning (PT) is an effective approach to adapting pre-trained lang...
With the increasing adoption of NLP models in real-world products, it be...
Question answering (QA) is a fundamental means to facilitate assessment ...
Transformer-based approaches have shown great success in visual question...
This is a report on the NSF Future Directions Workshop on Automatic
Eval...
Syntax is a fundamental component of language, yet few metrics have been...
Effective human-chatbot conversations need to achieve both coherence and...
Vision-and-Language (V+L) pre-training models have achieved tremendous
s...
Statistical analysis is increasingly confronted with complex data from
g...
Support vector machine (SVM) is a powerful classification method that ha...
Sharing of anti-vaccine posts on social media, including misinformation
...
Currently available grammatical error correction (GEC) datasets are comp...
As task-oriented dialog systems are becoming increasingly popular in our...
Collecting data for training dialog systems can be extremely expensive d...
A commonly observed problem of the state-of-the-art natural language
tec...
Conversational recommendation systems (CRS) engage with users by inferri...
Knowledge-grounded dialogue systems are challenging to build due to the ...
By the asymptotic oracle property, non-convex penalties represented by
m...
Current visual question answering (VQA) tasks mainly consider answering
...
Crowdsourcing platforms are often used to collect datasets for training ...