Related papers: Picard understanding Darmok: A Dataset and Model f…
There is a huge imbalance between languages currently spoken and corresponding resources to study them. Most of the attention naturally goes to the "big" languages: those which have the largest presence in terms of media and number of…
Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Although there are billions of parallel sentences for a few…
Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable for tasks like…
Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-first datasets often lack control over the reasoning required. We propose Macaron, a…
Automated security protocol verifiers such as ProVerif and Tamarin have been increasingly applied to verify large scale complex real-world protocols. While their ability to automate difficult reasoning processes required to handle protocols…
Human languages are full of metaphorical expressions. Metaphors help people understand the world by connecting new concepts and domains to more familiar ones. Large pre-trained language models (PLMs) are therefore assumed to encode…
We release Samas\=amayik, a novel, meticulously curated, large-scale Hindi-Sanskrit corpus, comprising 92,196 parallel sentences. Unlike most data available in Sanskrit, which focuses on classical era text and poetry, this corpus aggregates…
We introduce KazParC, a parallel corpus designed for machine translation across Kazakh, English, Russian, and Turkish. The first and largest publicly available corpus of its kind, KazParC contains a collection of 371,902 parallel sentences…
Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations and is essential for the development of communicative social agents. In this paper, we introduce a novel challenge,…
Both image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages. We use both types of pairs in MURAL (MUltimodal, MUltitask Representations Across Languages), a dual…
This paper presents a summary of the findings that we obtained based on the shared task on machine translation of Dravidian languages. We stood first in three of the five sub-tasks which were assigned to us for the main shared task. We…
Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…
Machine translation (MT) is a rapidly expanding field that has experienced significant advancements in recent years with the development of models capable of translating multiple languages with remarkable accuracy. However, the…
Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a parallel corpus for…
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…
In machine translation, a common problem is that the translation of certain words even if translated can cause incomprehension of the target language audience due to different cultural backgrounds. A solution to solve this problem is to add…
We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets. DuoRC contains 186,089 unique…
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations…
This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete…
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification,…