Related papers: Mask-Align: Self-Supervised Neural Word Alignment

The use of language is subject to variation over time as well as across social groups and knowledge domains, leading to differences even in the monolingual scenario. Such variation in word usage is often called lexical semantic change…

Despite the recent success of contextualized language models on various NLP tasks, language model itself cannot capture textual coherence of a long, multi-sentence document (e.g., a paragraph). Humans often make structural decisions on what…

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the…

Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm…

The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been…

Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one prevailing strategy is…

Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level. To obtain word (phoneme)-level scores, current methods usually rely on aligning components to obtain…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic…

In this paper we propose a neural network model with a novel Sequential Attention layer that extends soft attention by assigning weights to words in an input sequence in a way that takes into account not just how well that word matches a…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip. We align originally unaligned and unannotated…

We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by…

We introduce a neural machine translation model that views the input and output sentences as sequences of characters rather than words. Since word-level information provides a crucial source of bias, our input model composes representations…

This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only…

This paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases. Our approach identifies specific components -…

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…