相关论文: POLAR:A Per-User Association Test in Embedding Spa…

Hate speech detection is a critical, yet challenging problem in Natural Language Processing (NLP). Despite the existence of numerous studies dedicated to the development of NLP hate speech detection approaches, the accuracy is still poor.…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Existing corpora for intrinsic evaluation are not targeted towards tasks in informal domains such as Twitter or news comment forums. We want to test whether a representation of informal words fulfills the promise of eliding explicit text…

Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models.…

Multi-domain sentiment classification deals with the scenario where labeled data exists for multiple domains but insufficient for training effective sentiment classifiers that work across domains. Thus, fully exploiting sentiment knowledge…

When performing Polarity Detection for different words in a sentence, we need to look at the words around to understand the sentiment. Massively pretrained language models like BERT can encode not only just the words in a document but also…

Recently, there have been efforts to encode the linguistic information of speech using a self-supervised framework for speech synthesis. However, predicting representations from surrounding representations can inadvertently entangle speaker…

Sentiment analysis aims to uncover emotions conveyed through information. In its simplest form, it is performed on a polarity basis, where the goal is to classify information with positive or negative emotion. Recent research has explored…

Recent years have seen an increased interest in establishing association between faces and voices of celebrities leveraging audio-visual information from YouTube. Prior works adopt metric learning methods to learn an embedding space that is…

Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage. Previous works use hand-crafted features or classification tasks to train their authorship…

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…

Standard probabilistic linear discriminant analysis (PLDA) for speaker recognition assumes that the sample's features (usually, i-vectors) are given by a sum of three terms: a term that depends on the speaker identity, a term that models…

Vector representations obtained from word embedding are the source of many groundbreaking advances in natural language processing. They yield word representations that are capable of capturing semantics and analogies of words within a text…

This work presents a large-scale analysis of artificial intelligence (AI) and machine learning (ML) references within news articles and scientific publications between 2011 and 2019. We implement word association measurements that…

Text embeddings are widely used to analyse large corpora of complex texts. However, it is unclear whether the embeddings capture the same semantic distances as the human experts using them. Ensuring alignment between embedding…

Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a…

Argumentative dialogues across political divides can reduce polarization, yet opportunities for citizens to engage with opposing views in accessible and structured ways remain limited. AI dialogue partners offer a scalable framework for…

The x-vector architecture has recently achieved state-of-the-art results on the speaker verification task. This architecture incorporates a central layer, referred to as temporal pooling, which stacks statistical parameters of the acoustic…

Word embeddings improve the performance of NLP systems by revealing the hidden structural relationships between words. Despite their success in many applications, word embeddings have seen very little use in computational social science NLP…

Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typically employ either supervised latent user embeddings, which are effective for retrieval but…