Related papers: MUSS: Multilingual Unsupervised Sentence Simplific…
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this…
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating…
Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural…
In this work, we present a novel, machine-learning approach for constructing Multiclass Interpretable Scoring Systems (MISS) - a fully data-driven methodology for generating single, sparse, and user-friendly scoring systems for multiclass…
Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora. This method relies on the assumption that the two…
Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who…
Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…
Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
Text summarization aims to generate a short summary for an input text. In this work, we propose a Non-Autoregressive Unsupervised Summarization (NAUS) approach, which does not require parallel data for training. Our NAUS first performs…
Unlabeled data learning has attracted considerable attention recently. However, it is still elusive to extract the expected high-level semantic feature with mere unsupervised learning. In the meantime, semi-supervised learning (SSL)…
The core challenge faced by multi-document summarization is the complexity of relationships among documents and the presence of information redundancy. Graph clustering is an effective paradigm for addressing this issue, as it models the…
Recent multilingual pre-trained models have shown better performance in various multilingual tasks. However, these models perform poorly on multilingual retrieval tasks due to lacking multilingual training data. In this paper, we propose to…
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…
Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not…
Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well…
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.…
Semantic hashing represents documents as compact binary vectors (hash codes) and allows both efficient and effective similarity search in large-scale information retrieval. The state of the art has primarily focused on learning hash codes…
Parallel cross-lingual summarization data is scarce, requiring models to better use the limited available cross-lingual resources. Existing methods to do so often adopt sequence-to-sequence networks with multi-task frameworks. Such…
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of…