Natural Language Processing RELIES on Linguistics

• URL: http://arxiv.org/abs/2405.05966v3
• Date: Fri, 22 Nov 2024 15:36:32 GMT
• Title: Natural Language Processing RELIES on Linguistics
• Authors: Juri Opitz, Shira Wein, Nathan Schneider,
• Abstract summary: We argue the acronym RELIES that encapsulates six major facets where linguistics contributes to NLP. This list is not exhaustive, nor is linguistics the main point of reference for every effort under these themes.
• Score: 13.142686158720021
• License:
• Abstract: Large Language Models (LLMs) have become capable of generating highly fluent text in certain languages, without modules specially designed to capture grammar or semantic coherence. What does this mean for the future of linguistic expertise in NLP? We highlight several aspects in which NLP (still) relies on linguistics, or where linguistic thinking can illuminate new directions. We argue our case around the acronym RELIES that encapsulates six major facets where linguistics contributes to NLP: Resources, Evaluation, Low-resource settings, Interpretability, Explanation, and the Study of language. This list is not exhaustive, nor is linguistics the main point of reference for every effort under these themes; but at a macro level, these facets highlight the enduring importance of studying machine systems vis-\`a-vis systems of human language.

Related papers

• How does a Multilingual LM Handle Multiple Languages? [0.0]
  This study critically examines capabilities in multilingual understanding, semantic representation, and cross-lingual knowledge transfer. It assesses semantic similarity by analyzing multilingual word embeddings for consistency using cosine similarity. It examines BLOOM-1.7B and Qwen2 through Named Entity Recognition and sentence similarity tasks to understand their linguistic structures.
  arXiv  Detail & Related papers  (2025-02-06T18:08:14Z)
• IOLBENCH: Benchmarking LLMs on Linguistic Reasoning [8.20398036986024]
  We introduce IOLBENCH, a novel benchmark derived from International Linguistics Olympiad (IOL) problems. This dataset encompasses diverse problems testing syntax, morphology, phonology, and semantics. We find that even the most advanced models struggle to handle the intricacies of linguistic complexity.
  arXiv  Detail & Related papers  (2025-01-08T03:15:10Z)
• How Do Multilingual Language Models Remember Facts? [50.13632788453612]
  We show that previously identified recall mechanisms in English largely apply to multilingual contexts. We localize the role of language during recall, finding that subject enrichment is language-independent. In decoder-only LLMs, FVs compose these two pieces of information in two separate stages.
  arXiv  Detail & Related papers  (2024-10-18T11:39:34Z)
• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  Lens is a novel approach to enhance multilingual capabilities of large language models (LLMs) It operates by manipulating the hidden representations within the language-agnostic and language-specific subspaces from top layers of LLMs. It achieves superior results with much fewer computational resources compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)
• What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects [60.8361859783634]
  We survey speakers of dialects and regional languages related to German. We find that respondents are especially in favour of potential NLP tools that work with dialectal input.
  arXiv  Detail & Related papers  (2024-02-19T09:15:28Z)
• Natural Language Processing for Dialects of a Language: A Survey [56.93337350526933]
  State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.
  arXiv  Detail & Related papers  (2024-01-11T03:04:38Z)
• Ling-CL: Understanding NLP Models through Linguistic Curricula [17.44112549879293]
  We employ a characterization of linguistic complexity from psycholinguistic and language acquisition research. We develop data-driven curricula to understand the underlying linguistic knowledge that models learn to address NLP tasks.
  arXiv  Detail & Related papers  (2023-10-31T01:44:33Z)
• CLSE: Corpus of Linguistically Significant Entities [58.29901964387952]
  We release a Corpus of Linguistically Significant Entities (CLSE) annotated by experts. CLSE covers 74 different semantic types to support various applications from airline ticketing to video games. We create a linguistically representative NLG evaluation benchmark in three languages: French, Marathi, and Russian.
  arXiv  Detail & Related papers  (2022-11-04T12:56:12Z)
• Including Signed Languages in Natural Language Processing [48.62744923724317]
  Signed languages are the primary means of communication for many deaf and hard of hearing individuals. This position paper calls on the NLP community to include signed languages as a research area with high social and scientific impact.
  arXiv  Detail & Related papers  (2021-05-11T17:37:55Z)
• The State and Fate of Linguistic Diversity and Inclusion in the NLP World [12.936270946393483]
  Language technologies contribute to promoting multilingualism and linguistic diversity around the world. Only a very small number of the over 7000 languages of the world are represented in the rapidly evolving language technologies and applications.
  arXiv  Detail & Related papers  (2020-04-20T07:19:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.