English
Related papers

Related papers: Neural Machine Translation without Embeddings

200 papers

We aim to shed light on the strengths and weaknesses of the newly introduced neural machine translation paradigm. To that end, we conduct a multifaceted evaluation in which we compare outputs produced by state-of-the-art neural machine…

Computation and Language · Computer Science 2017-01-12 Antonio Toral , Víctor M. Sánchez-Cartagena

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in…

Computation and Language · Computer Science 2026-03-05 Chunyuan Deng , Sanket Lokegaonkar , Colin Lockard , Besnik Fetahu , Nasser Zalmout , Xian Li

Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…

Computation and Language · Computer Science 2019-12-10 Carlos Escolano , Marta R. Costa-jussà , José A. R. Fonollosa

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Computation and Language · Computer Science 2016-10-07 Kim Anh Nguyen , Sabine Schulte im Walde , Ngoc Thang Vu

We introduce a powerful approach for Neural Machine Translation (NMT), whereby, during training and testing, together with the input we provide its phonetic encoding and the variants of such an encoding. This way we obtain very significant…

Computation and Language · Computer Science 2019-11-12 Abdul Rafae Khan , Jia Xu

The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Statistical MT, which mainly relies on various count-based…

Computation and Language · Computer Science 2020-10-01 Felix Stahlberg

The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We explore a setting where many different predictions are made on a single piece of text.…

Computation and Language · Computer Science 2020-04-30 Jingfei Du , Myle Ott , Haoran Li , Xing Zhou , Veselin Stoyanov

The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens---they embed them as distributed vectors. Is this…

Computation and Language · Computer Science 2019-09-19 Eric Wallace , Yizhong Wang , Sujian Li , Sameer Singh , Matt Gardner

Transliteration is a key component of machine translation systems and software internationalization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing…

Computation and Language · Computer Science 2016-11-01 Mihaela Rosca , Thomas Breuel

Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the…

Computation and Language · Computer Science 2023-11-28 Dewen Zeng , Nan Du , Tao Wang , Yuanzhong Xu , Tao Lei , Zhifeng Chen , Claire Cui

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not…

Computation and Language · Computer Science 2024-04-02 Marco Cognetta , Tatsuya Hiraoka , Naoaki Okazaki , Rico Sennrich , Yuval Pinter

Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. This makes decoding decisions based on partial source prefixes even though the full source is…

Computation and Language · Computer Science 2019-08-19 Kyra Yee , Nathan Ng , Yann N. Dauphin , Michael Auli

Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…

Computation and Language · Computer Science 2024-03-04 Jinbiao Yang

Transformer-based large language models (LLMs) rely on contextual embeddings which generate different (continuous) representations for the same token depending on its surrounding context. Nonetheless, words and tokens typically have a…

Computation and Language · Computer Science 2025-07-10 Qitong Wang , Mohammed J. Zaki , Georgios Kollias , Vasileios Kalantzis

Despite an ever growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the…

Computation and Language · Computer Science 2019-12-12 Gözde Gül Şahin , Clara Vania , Ilia Kuznetsov , Iryna Gurevych

Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning…

Computation and Language · Computer Science 2025-10-16 A. Bochkov

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Computation and Language · Computer Science 2025-06-12 Darius Feher , Ivan Vulić , Benjamin Minixhofer

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree…

Computation and Language · Computer Science 2018-08-29 Xinyi Wang , Hieu Pham , Pengcheng Yin , Graham Neubig

Tokenization is the first step in modern neural language model pipelines where an input text is converted to a sequence of subword tokens. We introduce from first principles a finite-state transduction framework which can efficiently encode…

Computation and Language · Computer Science 2024-10-22 Marco Cognetta , Naoaki Okazaki