Related papers: Graph-based Filtering of Out-of-Vocabulary Words f…

Words embedding (distributed word vector representations) have become an essential component of many natural language processing (NLP) tasks such as machine translation, sentiment analysis, word analogy, named entity recognition and word…

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and…

Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…

Hate speech detection is a challenging problem with most of the datasets available in only one language: English. In this paper, we conduct a large scale analysis of multilingual hate speech in 9 languages from 16 different sources. We…

In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples. With an automatic annotation toolkit, ERRANT,…

Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to…

Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn…

To resolve the semantic ambiguity in texts, we propose a model, which innovatively combines a knowledge graph with an improved attention mechanism. An existing knowledge base is utilized to enrich the text with relevant contextual concepts.…

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…

Categorical variables often appear in datasets for classification and regression tasks, and they need to be encoded into numerical values before training. Since many encoders have been developed and can significantly impact performance,…

In extreme classification problems, learning algorithms are required to map instances to labels from an extremely large label set. We build on a recent extreme classification framework with logarithmic time and space, and on a general…

The task of assigning and validating internationally accepted commodity code (HS code) to traded goods is one of the critical functions at the customs office. This decision is crucial to importers and exporters, as it determines the tariff…

In this paper, we propose Neural Phrase-to-Phrase Machine Translation (NP$^2$MT). Our model uses a phrase attention mechanism to discover relevant input (source) segments that are used by a decoder to generate output (target) phrases. We…

In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction. Distinguishing reusable translations from noisy segments and learning to reuse them…

Decoder transformers have continued increasing in scale reaching hundreds of billions of parameters. Due to their scale the same decoder sets state-of-the-art results on various language tasks via prompting or fine-tuning. Yet, these large…

Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that…

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper…

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…

Recently, encoder-decoder models are widely used in social media text summarization. However, these models sometimes select noise words in irrelevant sentences as part of a summary by error, thus declining the performance. In order to…

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a…