相关论文: Finnish SQuAD: A Simple Approach to Machine Transl…

Large Language Models (LLMs) have led to significant improvements in the Knowledge Base Question Answering (KBQA) task. However, datasets used in KBQA studies do not capture the true complexity of KBQA tasks. They either have simple…

Reading comprehension is a well studied task, with huge training datasets in English. This work focuses on building reading comprehension systems for Czech, without requiring any manually annotated Czech training data. First of all, we…

Fine-grained Entity Typing is a tough task which suffers from noise samples extracted from distant supervision. Thousands of manually annotated samples can achieve greater performance than millions of samples generated by the previous…

Spoken Language Understanding (SLU) systems must balance performance and efficiency, particularly in resource-constrained environments. Existing methods apply distillation and quantization separately, leading to suboptimal compression as…

This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting…

Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this…

Machine-translated benchmark datasets reduce costs and offer scale, but noise, loss of structure, and uneven quality weaken confidence. What matters is not merely whether we can translate, but also whether we can measure and verify…

This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese. To this end, we develop an error taxonomy…

Human evaluation of machine translation is in an arms race with translation model quality: as our models get better, our evaluation methods need to be improved to ensure that quality gains are not lost in evaluation noise. To this end, we…

Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles and long documents, due to their quadratic complexity.…

In this paper, we present TransMLA, a framework that seamlessly converts any GQA-based pre-trained model into an MLA-based model. Our approach enables direct compatibility with DeepSeek's codebase, allowing these models to fully leverage…

Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of the semantic representation to a strongly pre-trained…

Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos and then employs a translation module to translate glosses into spoken sentences. Most existing works focus on the…

Deep learning approaches to semantic parsing require a large amount of labeled data, but annotating complex logical forms is costly. Here, we propose Syntactic Question Abstraction and Retrieval (SQAR), a method to build a neural semantic…

When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt "Translate the following sentence from [src lang] into [tgt lang]:". However, in many…

We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challenges, current datasets in this domain have been either…

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also…

Sign language translation (SLT) systems, which are often decomposed into video-to-gloss (V2G) recognition and gloss-to-text (G2T) translation through the pivot gloss, heavily relies on the availability of large-scale parallel G2T pairs.…

We present Mi{\dh}eind's submission for the English$\to$Icelandic and Icelandic$\to$English subsets of the 2021 WMT news translation task. Transformer-base models are trained for translation on parallel data to generate backtranslations…