Related papers: Thematic Fit Bits: Annotation Quality and Quantity…

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These models are trained with fully supervised learning where the…

When speaking or writing, people omit information that seems clear and evident, such that only part of the message is expressed in words. Especially in argumentative texts it is very common that (important) parts of the argument are implied…

Pairwise preferences over model responses are widely collected to evaluate and provide feedback to large language models (LLMs). Given two alternative model responses to the same input, a human or AI annotator selects the "better" response.…

In Computed Tomography, machine learning is often used for automated data processing. However, increasing model complexity is accompanied by increasingly large volume datasets, which in turn increases the cost of model training. Unlike most…

Recent dialogue coherence models use the coherence features designed for monologue texts, e.g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels. It…

Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code. Aside from aiding programming-related tasks, anecdotal evidence suggests that including code in pretraining…

When pre-trained on large unsupervised textual corpora, language models are able to store and retrieve factual knowledge to some extent, making it possible to use them directly for zero-shot cloze-style question answering. However, storing…

Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most…

This paper describes our contributions to the Shared Task of the 9th Workshop on Argument Mining (2022). Our approach uses Large Language Models for the task of Argument Quality Prediction. We perform prompt engineering using GPT-3, and…

Argument mining systems often consider contextual information, i.e. information outside of an argumentative discourse unit, when trained to accomplish tasks such as argument component identification, classification, and relation extraction.…

Morality plays an important role in culture, identity, and emotion. Recent advances in natural language processing have shown that it is possible to classify moral values expressed in text at scale. Morality classification relies on human…

Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preference dataset are critical to the effectiveness of preference…

In supervised learning, low quality annotations lead to poorly performing classification and detection models, while also rendering evaluation unreliable. This is particularly apparent on temporal data, where annotation quality is affected…

Most studies on language model pretraining focus on large datasets, leaving open questions about optimization in data-constrained settings. In such settings, the effects of training data order and of including alternative versions of the…

Argument mining has garnered increasing attention over the years, with the recent advancement of Large Language Models (LLMs) further propelling this trend. However, current argument relations remain relatively simplistic and foundational,…

Segmentation and classification of large numbers of instances, such as cell nuclei, are crucial tasks in digital pathology for accurate diagnosis. However, the availability of high-quality datasets for deep learning methods is often limited…

Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive…

Embedding retrofitting adjusts pre-trained word vectors using knowledge graph constraints to improve domain-specific retrieval. However, the effectiveness of retrofitting depends critically on knowledge graph quality, which in turn depends…

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus…

Annotating music items with music genres is crucial for music recommendation and information retrieval, yet challenging given that music genres are subjective concepts. Recently, in order to explicitly consider this subjectivity, the…