Related papers: On-Device Emoji Classifier Trained with GPT-based …
Jailbreaking techniques trick Large Language Models (LLMs) into producing restricted output, posing a potential threat. One line of defense is to use another LLM as a Judge to evaluate the harmfulness of generated text. However, we reveal…
Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level…
Identifying scientific publications that are within a dynamic field of research often requires costly annotation by subject-matter experts. Resources like widely-accepted classification criteria or field taxonomies are unavailable for a…
In affective computing, the task of Emotion Recognition in Conversations (ERC) has emerged as a focal area of research. The primary objective of this task is to predict emotional states within conversations by analyzing multimodal data…
The release of ChatGPT has uncovered a range of possibilities whereby large language models (LLMs) can substitute human intelligence. In this paper, we seek to understand whether ChatGPT has the potential to reproduce human-generated label…
Positive, supportive online communication in social media (candy speech) has the potential to foster civility, yet automated detection of such language remains underexplored, limiting systematic analysis of its impact. We investigate how…
Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply…
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homophone, while the user intended a synonym. Our goal is to…
Emoticons are indispensable in online communications. With users' growing needs for more customized and expressive emoticons, recent messaging applications begin to support (limited) multi-modal emoticons: e.g., enhancing emoticons with…
This paper introduces a novel dataset and evaluation benchmark designed to assess and improve small language models deployable on edge devices, with a focus on user profiling from multi-session natural language interactions in smart home…
Chat GPT belongs to the category of Generative Pre-trained Transformer (GPT) language models, which have received specialized training to produce text based on natural language inputs. Its purpose is to imitate human-like conversation and…
State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and…
Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise…
Voice assistants like Siri, Google Assistant, Alexa etc. are used widely across the globe for home automation, these require the use of special phrases also known as hotwords to wake it up and perform an action like "Hey Alexa!", "Ok…
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fail to connect the generated outputs and desired target…
Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that…
Generating emotion-specific talking head videos from audio input is an important and complex challenge for human-machine interaction. However, emotion is highly abstract concept with ambiguous boundaries, and it necessitates disentangled…
Online writing lacks the non-verbal cues present in face-to-face communication, which provide additional contextual information about the utterance, such as the speaker's intention or affective state. To fill this void, a number of…
Fuzzy Fingerprints have been successfully used as an interpretable text classification technique, but, like most other techniques, have been largely surpassed in performance by Large Pre-trained Language Models, such as BERT or RoBERTa.…
Mobile messaging apps offer an increasing range of emotional expressions, such as emojis to help users manually augment their texting experiences. Accessibility of such augmentations is limited in voice messaging. With the term "speejis" we…