Related papers: Automated Utterance Labeling of Conversations Usin…
This study analyzes changes in the attention mechanisms of large language models (LLMs) when used to understand natural conversations between humans (human-human). We analyze three use cases of LLMs: interactions over web content, code, and…
This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for…
AI chatbots have made vast strides in technology improvement in recent years and are already operational in many industries. Advanced Natural Language Processing techniques, based on deep networks, efficiently process user requests to carry…
Natural language processing (NLP) is becoming an important means for automatic recognition of human traits and states, such as intoxication, presence of psychiatric disorders, presence of airway disorders and states of stress. Such…
Conversational systems are now capable of producing impressive and generally relevant responses. However, we have no visibility nor control of the socio-emotional strategies behind state-of-the-art Large Language Models (LLMs), which poses…
Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus on improving task-based conversational assistants online,…
Experimental methods for estimating the impacts of text on human evaluation have been widely used in the social sciences. However, researchers in experimental settings are usually limited to testing a small number of pre-specified text…
The unstructured nature of clinical notes within electronic health records often conceals vital patient-related information, making it challenging to access or interpret. To uncover this hidden information, specialized Natural Language…
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be…
Personality refers to individual differences in behavior, thinking, and feeling. With the growing availability of digital footprints, especially from social media, automated methods for personality assessment have become increasingly…
Large Language Models (LLMs) are increasingly used in everyday life and research. One of the most common use cases is conversational interactions, enabled by the language generation capabilities of LLMs. Just as between two humans, a…
Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), e.g., open-ended question, statement of opinion, or request for an opinion, is a key step in Natural Language Understanding (NLU) for…
Recent advances in natural language processing (NLP) in online social media are evidently owed to large-scale datasets. However, labeling, storing, and processing a large number of textual data points, e.g., tweets, has remained…
Automated label generation for clusters of scientific documents is a common task in bibliometric workflows. Traditionally, labels were formed by concatenating distinguishing characteristics of a cluster's documents; while straightforward,…
We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…
Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual labels limits scalability. Recent studies leverage large…
Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…
Open-ended survey data constitute an important basis in research as well as for making business decisions. Collecting and manually analysing free-text survey data is generally more costly than collecting and analysing survey data consisting…
Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…
In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs). This scenario is observed for many mainstream IPDAs…