Related papers: Contextual Salience for Fast and Accurate Sentence…

In text documents such as news articles, the content and key events usually revolve around a subset of all the entities mentioned in a document. These entities, often deemed as salient entities, provide useful cues of the aboutness of a…

Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many…

Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important…

While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence…

We formulate coherence modeling as a regression task and propose two novel methods to combine techniques from our setup with pairwise approaches. The first of our methods is a model that we call "first-next," which operates similarly to…

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the…

Co-occurrence statistics based word embedding techniques have proved to be very useful in extracting the semantic and syntactic representation of words as low dimensional continuous vectors. In this work, we discovered that dictionary…

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…

We intend to generate low-dimensional explicit distributional semantic vectors. In explicit semantic vectors, each dimension corresponds to a word, so word vectors are interpretable. In this research, we propose a new approach to obtain…

Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking the explicit disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither…

Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience.…

Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently being translated. However, while many current methods…

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Text features that are correlated with class labels, but do not directly cause them, are sometimesuseful for prediction, but they may not be insightful. As an alternative to traditional correlation-basedfeature selection, causal inference…

The skip-gram (SG) model learns word representation by predicting the words surrounding a center word from unstructured text data. However, not all words in the context window contribute to the meaning of the center word. For example, less…

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…

Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characteristics of the CSRL task have been overlooked by the existing…