Related papers: CTQScorer: Combining Multiple Features for In-cont…

Context modeling plays a critical role in building multi-turn dialogue systems. Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational…

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…

This paper compares a qualitative reasoning model of translation with a quantitative statistical model. We consider these models within the context of two hypothetical speech translation systems, starting with a logic-based design and…

Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text…

Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English…

StackOverflow has become an emerging resource for talent recognition in recent years. While users exploit technical language on StackOverflow, recruiters try to find the relevant candidates for jobs using their own terminology. This…

Human evaluation is crucial for assessing rapidly evolving language models but is influenced by annotator proficiency and task design. This study explores the integration of comparative judgment into human annotation for machine translation…

Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer). Nowadays,…

We propose two methods of learning vector representations of words and phrases that each combine sentence context with structural features extracted from dependency trees. Using several variations of neural network classifier, we show that…

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…

Recent studies have shown that the multi-encoder models are agnostic to the choice of context, and the context encoder generates noise which helps improve the models in terms of BLEU score. In this paper, we further explore this idea by…

In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained…

While quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled data is often lacking due to the high…

Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. It is…

Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR). With the help of deep learning, neural machine translation (NMT) has shown promising results on various tasks. However, NMT is generally trained…

Machine translation (MT) requires a wide range of linguistic capabilities, which current end-to-end models are expected to learn implicitly by observing aligned sentences in bilingual corpora. In this work, we ask: \emph{How well do MT…

The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it…

Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and…

The increase in parameter size of multimodal large language models (MLLMs) introduces significant capabilities, particularly in-context learning, where MLLMs enhance task performance without updating pre-trained parameters. This…

While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…