相关论文: LERIL : Collaborative Effort for Creating Lexical …

In this paper we present a unification-based lexical platform designed for highly inflected languages (like Roman ones). A formalism is proposed for encoding a lemma-based lexical source, well suited for linguistic generalizations. From…

Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties…

Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In…

In this paper, I present our work on DeepRAG, a specialized embedding model we built specifically for Hindi language in RAG systems. While LLMs have gotten really good at generating text, their performance in retrieval tasks still depends…

In this paper, we survey Text Summarization (TS) datasets in Indian Languages (ILs), which are also low-resource languages (LRLs). We seek to answer one primary question: is the pool of Indian Language Text Summarization (ILTS) dataset…

The effectiveness of Large Language Models (LLMs) depends heavily on the availability of high-quality post-training data, particularly instruction-tuning and preference-based examples. Existing open-source datasets, however, often lack…

Although Wikipedia is the largest multilingual encyclopedia, it remains inherently incomplete. There is a significant disparity in the quality of content between high-resource languages (HRLs, e.g., English) and low-resource languages…

Indic languages like Hindi and Tamil are underrepresented in the natural language processing (NLP) field compared to languages like English. Due to this underrepresentation, performance on NLP tasks (such as search algorithms) in Indic…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

This paper explores the kinds of probabilistic relations that are important in syntactic disambiguation. It proposes that two widely used kinds of relations, lexical dependencies and structural relations, have complementary disambiguation…

Language technology has the potential to facilitate intercultural communication through meaningful translations. However, the current state of language technology is deeply entangled with colonial knowledge due to path dependencies and…

Natural Language Inference (NLI) is the task of inferring the logical relationship, typically entailment or contradiction, between a premise and hypothesis. Code-mixing is the use of more than one language in the same conversation or…

The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources…

This study examines the practical applications and methodological implications of Machine Translation in Indian Languages, specifically Bangla, Malayalam, and Telugu, within emerging translation workflows and in relation to existing…

Named Entity Recognition (NER) is a useful component in Natural Language Processing (NLP) applications. It is used in various tasks such as Machine Translation, Summarization, Information Retrieval, and Question-Answering systems. The…

Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes. Agnostic of this process, today's language models are trained to generate only the…

Scaling existing applications and solutions to multiple human languages has traditionally proven to be difficult, mainly due to the language-dependent nature of preprocessing and feature engineering techniques employed in traditional…

Code-mixing, the blending of linguistic elements from distinct languages to form meaningful sentences, is common in multilingual settings, yielding hybrid languages like Hinglish and Minglish. Marathi, India's third most spoken language,…

While recent advances in language modeling have resulted in powerful generation models, their generation style remains implicitly dependent on the training data and can not emulate a specific target style. Leveraging the generative…

In this work, we describe a system that detects paraphrases in Indian Languages as part of our participation in the shared Task on detecting paraphrases in Indian Languages (DPIL) organized by Forum for Information Retrieval Evaluation…