Related papers: MAP Lexicon is useful for segmentation and word di…

Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to…

Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible…

Medical dialogue information extraction is becoming an increasingly significant problem in modern medical care. It is difficult to extract key information from electronic medical records (EMRs) due to their large numbers. Previously,…

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these…

Large language models (LLMs) have demonstrated significant potential in solving recommendation tasks. With proven capabilities in understanding user preferences, LLM personalization has emerged as a critical area for providing tailored…

Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a…

Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatically accurate but inconsistent with visual inputs. In this…

The use of words to convey speaker's intent is traditionally distinguished from the `mention' of words for quoting what someone said, or pointing out properties of a word. Here we show that computationally modeling this use-mention…

Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal…

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

This paper explores the impact of incorporating sentiment, emotion, and domain-specific lexicons into a transformer-based model for depression symptom estimation. Lexicon information is added by marking the words in the input transcripts of…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

This paper presents our segmentation system developed for the MLP 2017 shared tasks on cross-lingual word segmentation and morpheme segmentation. We model both word and morpheme segmentation as character-level sequence labelling tasks. The…

Recordings gathered with child-worn devices promised to revolutionize both fundamental and applied speech sciences by allowing the effortless capture of children's naturalistic speech environment and language production. This promise hinges…

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

Many techniques in computer vision, machine learning, and statistics rely on the fact that a signal of interest admits a sparse representation over some dictionary. Dictionaries are either available analytically, or can be learned from a…

In recent years, pretrained language models have revolutionized the NLP world, while achieving state of the art performance in various downstream tasks. However, in many cases, these models do not perform well when labeled data is scarce…

Overall, the two main contributions of this work include the application of sentence simplification to association extraction as described above, and the use of distributional semantics for concept extraction. The proposed work on concept…