Related papers: An Unsupervised Method for Building Sentence Simpl…
In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders.…
The massive collection of user posts across social media platforms is primarily untapped for artificial intelligence (AI) use cases based on the sheer volume and velocity of textual data. Natural language processing (NLP) is a subfield of…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
Data curation is a critical yet under-researched step in the machine translation training paradigm. To train translation systems, data acquisition relies primarily on human translations and digital parallel sources or, to a limited degree,…
Translation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT'22…
Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…
Cross-Language Information Retrieval (CLIR) and machine translation (MT) resources, such as dictionaries and parallel corpora, are scarce and hard to come by for special domains. Besides, these resources are just limited to a few languages,…
Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that…
Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. However, recent unsupervised models are extractive,…
Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual…
Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…
With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder…
We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but differ in an auxiliary…
We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We also release trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and…
Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…
Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus on unsupervised STS that works on various domains but only…
Recent work has highlighted the advantage of jointly learning grounded sentence representations from multiple languages. However, the data used in these studies has been limited to an aligned scenario: the same images annotated with…