Related papers: Interpretation of Semantic Tweet Representations

The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction.…

In this paper, we analyze several neural network designs (and their variations) for sentence pair modeling and compare their performance extensively across eight datasets, including paraphrase identification, semantic textual similarity,…

Natural Language Processing enables computers to understand human language by analysing and classifying text efficiently with deep-level grammatical and semantic features. Existing models capture features by learning from large corpora with…

Accurate and interpretable detection of depressive language in social media is useful for early interventions of mental health conditions, and has important implications for both clinical practice and broader public health efforts. In this…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

With the recent advance of representation learning algorithms on graphs (e.g., DeepWalk/GraphSage) and natural languages (e.g., Word2Vec/BERT) , the state-of-the art models can even achieve human-level performance over many downstream…

Language identification of social media text has been an interesting problem of study in recent years. Social media messages are predominantly in code mixed in non-English speaking states. Prior knowledge by pre-training contextual…

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by…

We show that information about social relationships can be used to improve user-level sentiment analysis. The main motivation behind our approach is that users that are somehow "connected" may be more likely to hold similar opinions;…

In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed. We investigate the compression of sentence embeddings using a neural encoder-decoder architecture, which is trained by…

Leveraging short-text contents to estimate the occupation of microblog authors has significant gains in many applications. Yet challenges abound. Firstly brief textual contents come with excessive lexical noise that makes the inference…

A novel Twitter context aided content caching (TAC) framework is proposed for enhancing the caching efficiency by taking advantage of the legibility and massive volume of Twitter data. For the purpose of promoting the caching efficiency,…

Labeled property graphs often contain rich textual attributes that can enhance analytical tasks when properly leveraged. This work explores the use of pretrained text embedding models to enable efficient semantic analysis in such graphs. By…

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of…

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…

We demonstrate that user preferences can be represented and predicted across topical domains using large-scale social modeling. Given information about popular entities favored by a user, we project the user into a social embedding space…

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…